WO2018098141A1 - Systems and methods for automated detection in magnetic resonance images - Google Patents

Systems and methods for automated detection in magnetic resonance images Download PDF

Info

Publication number
WO2018098141A1
WO2018098141A1 PCT/US2017/062763 US2017062763W WO2018098141A1 WO 2018098141 A1 WO2018098141 A1 WO 2018098141A1 US 2017062763 W US2017062763 W US 2017062763W WO 2018098141 A1 WO2018098141 A1 WO 2018098141A1
Authority
WO
WIPO (PCT)
Prior art keywords
image data
patient
magnetic resonance
low
brain
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/US2017/062763
Other languages
English (en)
French (fr)
Inventor
Michal Sofka
Jonathan M. Rothberg
Gregory L. Charvat
Tyler S. Ralston
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hyperfine Inc
Original Assignee
Hyperfine Research Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to EP17872998.4A priority Critical patent/EP3545494B1/en
Priority to MX2019005955A priority patent/MX2019005955A/es
Priority to CN201780071307.2A priority patent/CN109983474A/zh
Priority to EP21205232.8A priority patent/EP3968278A1/en
Priority to AU2017363608A priority patent/AU2017363608A1/en
Priority to BR112019010225A priority patent/BR112019010225A8/pt
Priority to CA3043038A priority patent/CA3043038A1/en
Priority to KR1020197016485A priority patent/KR20190087455A/ko
Priority to JP2019527297A priority patent/JP2019535424A/ja
Application filed by Hyperfine Research Inc filed Critical Hyperfine Research Inc
Publication of WO2018098141A1 publication Critical patent/WO2018098141A1/en
Priority to IL266748A priority patent/IL266748A/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R33/00—Arrangements or instruments for measuring magnetic variables
    • G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
    • G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
    • G01R33/48—NMR imaging systems
    • G01R33/54—Signal processing systems, e.g. using pulse sequences ; Generation or control of pulse sequences; Operator console
    • G01R33/56—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution
    • G01R33/5608—Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0048—Detecting, measuring or recording by applying mechanical forces or stimuli
    • A61B5/0055—Detecting, measuring or recording by applying mechanical forces or stimuli by applying suction
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0033—Features or image-related aspects of imaging apparatus, e.g. for MRI, optical tomography or impedance tomography apparatus; Arrangements of imaging apparatus in a room
    • A61B5/004—Features or image-related aspects of imaging apparatus, e.g. for MRI, optical tomography or impedance tomography apparatus; Arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
    • A61B5/0042—Features or image-related aspects of imaging apparatus, e.g. for MRI, optical tomography or impedance tomography apparatus; Arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the brain
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
    • A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/40—Detecting, measuring or recording for evaluating the nervous system
    • A61B5/4058—Detecting, measuring or recording for evaluating the nervous system for evaluating the central nervous system
    • A61B5/4064—Evaluating the brain
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R33/00—Arrangements or instruments for measuring magnetic variables
    • G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
    • G01R33/28—Details of apparatus provided for in groups G01R33/44 - G01R33/64
    • G01R33/38—Systems for generation, homogenisation or stabilisation of the main or gradient magnetic field
    • G01R33/3806—Open magnet assemblies for improved access to the sample, e.g. C-type or U-type magnets
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R33/00—Arrangements or instruments for measuring magnetic variables
    • G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
    • G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
    • G01R33/445—MR involving a non-standard magnetic field B0, e.g. of low magnitude as in the earth's magnetic field or in nanoTesla spectroscopy, comprising a polarizing magnetic field for pre-polarisation, B0 with a temporal variation of its magnitude or direction such as field cycling of B0 or rotation of the direction of B0, or spatially inhomogeneous B0 like in fringe-field MR or in stray-field imaging
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R33/00—Arrangements or instruments for measuring magnetic variables
    • G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
    • G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
    • G01R33/48—NMR imaging systems
    • G01R33/4806—Functional imaging of brain activation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R33/00—Arrangements or instruments for measuring magnetic variables
    • G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
    • G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
    • G01R33/48—NMR imaging systems
    • G01R33/483—NMR imaging systems with selection of signals or spectra from particular regions of the volume, e.g. in vivo spectroscopy
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24143—Distances to neighbourhood prototypes, e.g. restricted Coulomb energy networks [RCEN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2576/00—Medical imaging apparatus involving image processing or analysis
    • A61B2576/02—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part
    • A61B2576/026—Medical imaging apparatus involving image processing or analysis specially adapted for a particular organ or body part for the brain
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R33/00—Arrangements or instruments for measuring magnetic variables
    • G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
    • G01R33/28—Details of apparatus provided for in groups G01R33/44 - G01R33/64
    • G01R33/38—Systems for generation, homogenisation or stabilisation of the main or gradient magnetic field
    • G01R33/383—Systems for generation, homogenisation or stabilisation of the main or gradient magnetic field using permanent magnets
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30016—Brain
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30101—Blood vessel; Artery; Vein; Vascular
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30172—Centreline of tubular or elongated structure
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • G06V2201/031—Recognition of patterns in medical or anatomical images of internal organs
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • Magnetic resonance imaging provides an important imaging modality for numerous applications and is widely utilized in clinical and research settings to produce images of the inside of the human body.
  • MRI is based on detecting magnetic resonance (MR) signals, which are electromagnetic waves emitted by atoms in response to state changes resulting from applied electromagnetic fields.
  • MR magnetic resonance
  • NMR nuclear magnetic resonance
  • Detected MR signals may be processed to produce images, which in the context of medical applications, allows for the investigation of internal structures and/or biological processes within the body for diagnostic, therapeutic and/or research purposes.
  • MRI provides an attractive imaging modality for biological imaging due to its ability to produce non-invasive images having relatively high resolution and contrast without the safety concerns of other modalities (e.g., without needing to expose the subject to ionizing radiation, such as x-rays, or introducing radioactive material into the body). Additionally, MRI is particularly well suited to provide soft tissue contrast, which can be exploited to image subject matter that other imaging modalities are incapable of satisfactorily imaging. Moreover, MR techniques are capable of capturing information about structures and/or biological processes that other modalities are incapable of acquiring.
  • superconducting magnets and associated electronics to generate a strong uniform static magnetic field (BO) in which a subject (e.g., a patient) is imaged.
  • BO uniform static magnetic field
  • Superconducting magnets further require cryogenic equipment to keep the conductors in a superconducting state.
  • the size of such systems is considerable with a typical MRI installment including multiple rooms for the magnetic components, electronics, thermal management system, and control console areas, including a specially shielded room to isolate the magnetic components of the MRI system.
  • the size and expense of MRI systems generally limits their usage to facilities, such as hospitals and academic research centers, which have sufficient space and resources to purchase and maintain them.
  • the high cost and substantial space requirements of high-field MRI systems results in limited availability of MRI scanners. As such, there are frequently clinical situations in which an MRI scan would be beneficial, but is impractical or impossible due to the above-described limitations and as discussed in further detail below.
  • first and second MR data as input to a trained statistical classifier to obtain corresponding first output and second output; identifying, from the first output, at least one initial location of at least one landmark associated with at least one midline structure of the patient's brain; identifying, from the second output, at least one updated location of the at least one landmark associated with the at least one midline structure of the patient's brain; and determining a degree of change in the midline shift using the at least one initial location of the at least one landmark and the at least one updated location of the at least one landmark.
  • Some embodiments are directed to at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of detecting change in degree of midline shift in a brain of a patient positioned within a low-field magnetic resonance imaging (MRI) device.
  • MRI magnetic resonance imaging
  • Some embodiments are directed to a system comprising: at least one computer hardware processor; and at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of detecting change in degree of midline shift in a brain of a patient positioned within a low- field magnetic resonance imaging (MRI) device.
  • MRI magnetic resonance imaging
  • the method comprises, while the patient remains positioned within the low-field MRI device, acquiring first magnetic resonance (MR) image data of the patient's brain; providing the first MR data as input to a trained statistical classifier to obtain corresponding first output; identifying, from the first output, at least one initial location of at least one landmark associated with at least one midline structure of the patient's brain; acquiring second MR image data of the patient's brain subsequent to acquiring the first MR image data; providing the second MR image data as input to the trained statistical classifier to obtain corresponding second output; identifying, from the second output, at least one updated location of the at least one landmark associated with the at least one midline structure of the patient's brain; and determining a degree of change in the midline shift using the at least one initial location of the at least one landmark and the at least one updated location of the at least one landmark.
  • MR magnetic resonance
  • Some embodiments are directed to a method of determining change in size of an abnormality in a brain of a patient positioned within a low-field magnetic resonance imaging (MRI) device, the method comprising: while the patient remains positioned within the low-field MRI device: acquiring first magnetic resonance (MR) image data of the patient's brain; providing the first MR image data as input to a trained statistical classifier to obtain corresponding first output; identifying, using the first output, at least one initial value of at least one feature indicative of a size of an abnormality in the patient's brain; acquiring second MR image data of the patient's brain subsequent to acquiring the first MR image data; providing the second MR image data as input to the trained statistical classifier to obtain corresponding second output; identifying, using the second output, at least one updated value of the at least one feature indicative of the size of the abnormality in the patient's brain;
  • MR magnetic resonance
  • Some embodiments are directed to a low-field magnetic resonance imaging
  • MRI magnetic resonance
  • the low-field MRI device configured to determine change in size of an abnormality in a brain of a patient
  • the low-field MRI device comprising: a plurality of magnetic components, including: a BO magnet configured to produce, at least in part, a BO magnetic field; at least one gradient magnet configured to spatially encode magnetic resonance data; and at least one radio frequency coil configured to stimulate a magnetic resonance response and detect magnetic components configured to, when operated, acquire magnetic resonance image data; and at least one controller configured to operate the plurality of magnet components to, while the patient remains positioned within the low-field magnetic resonance device, acquire first magnetic resonance (MR) image data of the patient's brain, and acquire second MR image data of the patient's brain subsequent to acquiring the first MR image data, wherein the at least one controller further configured to perform: providing the first and second MR image data as input to a trained statistical classifier to obtain corresponding first output and second output; identifying, using the first output, at least one initial value of at least one feature indicative of a size of an abnormal
  • Some embodiments are directed to at least one non-transitory computer- readable storage medium storing processor-executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor, to perform method of determining change in size of an abnormality in a brain of a patient positioned within a low-field magnetic resonance imaging (MRI) device, the method comprising: while the patient remains positioned within the low-field MRI device: acquiring first magnetic resonance (MR) image data of the patient's brain; providing the first MR image data as input to a trained statistical classifier to obtain corresponding first output;
  • MRI magnetic resonance imaging
  • identifying, using the first output, at least one initial value of at least one feature indicative of a size of an abnormality in the patient's brain acquiring second MR image data of the patient's brain subsequent to acquiring the first MR image data; providing the second MR image data as input to the trained statistical classifier to obtain corresponding second output; identifying, using the second output, at least one updated value of the at least one feature indicative of the size of the abnormality in the patient's brain; determining the change in the size of the abnormality using the at least one initial value of the at least one feature and the at least one updated value of the at least one feature.
  • Some embodiments are directed to a system, comprising: at least one computer hardware processor; at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor, to perform method of determining change in size of an abnormality in a brain of a patient positioned within a low-field magnetic resonance imaging (MRI) device.
  • MRI magnetic resonance imaging
  • the method comprises, while the patient remains positioned within the low-field MRI device, acquiring first magnetic resonance (MR) image data of the patient's brain; providing the first MR image data as input to a trained statistical classifier to obtain corresponding first output; identifying, using the first output, at least one initial value of at least one feature indicative of a size of an abnormality in the patient's brain; acquiring second MR image data of the patient's brain subsequent to acquiring the first MR image data; providing the second MR image data as input to the trained statistical classifier to obtain corresponding second output; identifying, using the second output, at least one updated value of the at least one feature indicative of the size of the abnormality in the patient's brain; and determining the change in the size of the abnormality using the at least one initial value of the at least one feature and the at least one updated value of the at least one feature.
  • MR magnetic resonance
  • Some embodiments are directed to a method of detecting change in biological subject matter of a patient positioned within a low-field magnetic resonance imaging (MRI) device, the method comprising: while the patient remains positioned within the low-field MRI device: acquiring first magnetic resonance image data of a portion of the patient;
  • MRI magnetic resonance imaging
  • Some embodiments are directed to a low-field magnetic resonance imaging device configured to detecting change in biological subject matter of a patient positioned with the low-field magnetic resonance imaging device, comprising: a plurality of magnetic components, including: a BO magnet configured to produce, at least in part, a BO magnetic field; at least one gradient magnet configured to spatially encode magnetic resonance data; and at least one radio frequency coil configured to stimulate a magnetic resonance response and detect magnetic components configured to, when operated, acquire magnetic resonance image data; and at least one controller configured to operate the plurality of magnet components to, while the patient remains positioned within the low-field magnetic resonance device, acquire first magnetic resonance image data of a portion of the patient, and acquire second magnetic resonance image data of the portion of the patient subsequent to acquiring the first magnetic resonance image data, the at least one controller further configured to align the first magnetic resonance image data and the second magnetic resonance image data, and compare the aligned first magnetic resonance image data and second magnetic resonance image data to detect at least one change in the biological subject matter of the portion of the patient.
  • a plurality of magnetic components including
  • Some embodiments are directed to at least one non-transitory computer- readable storage medium storing processor-executable instructions that, when executed by at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of detecting change in biological subject matter of a patient positioned within a low-field magnetic resonance imaging (MRI) device, the method comprising: while the patient remains positioned within the low-field MRI device: acquiring first magnetic resonance image data of a portion of the patient; acquiring second magnetic resonance image data of the portion of the patient subsequent to acquiring the first magnetic resonance image data; aligning the first magnetic resonance image data and the second magnetic resonance image data; and comparing the aligned first magnetic resonance image data and second magnetic resonance image data to detect at least one change in the biological subject matter of the portion of the patient.
  • MRI magnetic resonance imaging
  • Some embodiments are directed to a system, comprising: at least one computer hardware processor; and at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform a method of detecting change in biological subject matter of a patient positioned within a low-field magnetic resonance imaging (MRI) device, the method comprising: while the patient remains positioned within the low-field MRI device: acquiring first magnetic resonance image data of a portion of the patient; acquiring second magnetic resonance image data of the portion of the patient subsequent to acquiring the first magnetic resonance image data; aligning the first magnetic resonance image data and the second magnetic resonance image data; and comparing the aligned first magnetic resonance image data and second magnetic resonance image data to detect at least one change in the biological subject matter of the portion of the patient.
  • MRI magnetic resonance imaging
  • FIG. 1 is a schematic illustration of a low-field MRI system, in accordance with some embodiments of the technology described herein.
  • FIGS. 2A and 2B illustrate bi-planar magnet configurations for a Bo magnet, in accordance with some embodiments of the technology described herein.
  • FIGS. 2C and 2D illustrate a bi-planar electromagnet configuration for a Bo magnet, in accordance with some embodiments of the technology described herein.
  • FIGS. 2E and 2F illustrate bi-planar permanent magnet configurations for a Bo magnet, in accordance with some embodiments of the technology described herein.
  • FIGS. 3 A and 3B illustrate a transportable low-field MRI system suitable for use with change detection techniques described herein, in accordance with some
  • FIG. 3F illustrates a portable MRI system performing a scan of the knee, in accordance with some embodiments of the technology described herein.
  • FIG. 3G illustrates another example of a portable MRI system, in accordance with some embodiments of the technology described herein.
  • FIG. 4 illustrates a method of performing change detection, in accordance with some embodiments of the technology described herein.
  • FIG. 6 illustrates a method of co-registering MR image data, in accordance with some embodiments of the technology described herein.
  • FIG. 7 A illustrates a midline shift measurement, in accordance with some embodiments of the technology described herein.
  • FIG. 7B illustrates another midline shift measurement, in accordance with some embodiments of the technology described herein.
  • FIG. 8 illustrates a method for determining a degree of change in the midline shift of a patient, in accordance with some embodiments of the technology described herein.
  • FIGs. 9A-C illustrate a convolutional neural network architectures for making midline shift measurements, in accordance with some embodiments of the technology described herein.
  • FIG. 10 illustrates fully convolutional neural network architectures for making midline shift measurements, in accordance with some embodiments of the technology described herein.
  • FIGs. 1 lA-1 IE illustrate measurements that may be used to determine the size of a hemorrhage of a patient, in accordance with some embodiments of the technology described herein.
  • FIGs. 12A-C illustrate measurements that may be used to determine a change in the size of a hemorrhage of a patient, in accordance with some embodiments of the technology described herein.
  • FIG. 13 illustrates a method for determining a degree of change in the size of an abnormality (e.g., hemorrhage) in the brain of a patient, in accordance with some embodiments of the technology described herein.
  • FIG. 14 illustrates a fully convolutional neural network architecture for making measurements that may be used to determine the size of an abnormality (e.g., hemorrhage) in a patient's brain, in accordance with some embodiments of the technology described herein.
  • FIG. 15 illustrates a convolutional neural network architecture for making measurements that may be used to determine the size of an abnormality (e.g., a hemorrhage) in a patient's brain, in accordance with some embodiments of the technology described herein.
  • an abnormality e.g., a hemorrhage
  • FIG. 16 is a diagram of an illustrative computer system on which
  • the MRI scanner market is overwhelmingly dominated by high-field systems, and particularly for medical or clinical MRI applications.
  • the general trend in medical imaging has been to produce MRI scanners with increasingly greater field strengths, with the vast majority of clinical MRI scanners operating at 1.5T or 3T, with higher field strengths of 7T and 9T used in research settings.
  • high-field refers generally to MRI systems presently in use in a clinical setting and, more particularly, to MRI systems operating with a main magnetic field (i.e., a Bo field) at or above 1.5T, though clinical systems operating between .5T and 1.5T are often also characterized as "high-field.”
  • Field strengths between approximately .2T and .5T have been characterized as “mid-field” and, as field strengths in the high-field regime have continued to increase, field strengths in the range between .5T and IT have also been characterized as mid-field.
  • low- field refers generally to MRI systems operating with a Bo field of less than or equal to approximately 0.2T, though systems having a Bo field of between .2T and approximately .3T have sometimes been characterized as low-field as a consequence of increased field strengths at the high end of the high-field regime.
  • low-field MRI systems operating with a Bo field of less than .IT are referred to herein as "very low-field” and low- field MRI systems operating with a Bo field of less than lOmT are referred to herein as "ultra- low field.”
  • An electromagnetically shielded room is required for the MRI system to operate and the floor of the room must be structurally reinforced. Additional rooms must be provided for the high- power electronics and the scan technician's control area. Secure access to the site must also be provided. In addition, a dedicated three-phase electrical connection must be installed to provide the power for the electronics that, in turn, are cooled by a chilled water supply. Additional HVAC capacity typically must also be provided. These site requirements are not only costly, but significantly limit the locations where MRI systems can be deployed.
  • high-field MRI systems require specially adapted facilities to accommodate the size, weight, power consumption and shielding requirements of these systems.
  • a 1.5T MRI system typically weighs between 4-10 tons and a 3T MRI system typically weighs between 8-20 tons.
  • high-field MRI systems generally require significant amounts of heavy and expensive shielding.
  • Many mid-field scanners are even heavier, weighing between 10-20 tons due, in part, to the use of very large permanent magnets and/or yokes.
  • MRI systems typically consume large amounts of power.
  • common 1.5T and 3T MRI systems typically consume between 20- 40kW of power during operation
  • available .5T and .2T MRI systems commonly consume between 5-20kW, each using dedicated and specialized power sources.
  • power consumption is referenced as average power consumed over an interval of interest.
  • the 20-40kW referred to above indicates the average power consumed by conventional MRI systems during the course of image acquisition, which may include relatively short periods of peak power consumption that significantly exceeds the average power consumption (e.g., when the gradient coils and/or RF coils are pulsed over relatively short periods of the pulse sequence). Intervals of peak (or large) power
  • the average power consumption is typically addressed via power storage elements (e.g., capacitors) of the MRI system itself.
  • the average power consumption is the more relevant number as it generally determines the type of power connection needed to operate the device.
  • available clinical MRI systems must have dedicated power sources, typically requiring a dedicated three-phase connection to the grid to power the components of the MRI system. Additional electronics are then needed to convert the three-phase power into single-phase power utilized by the MRI system.
  • the many physical requirements of deploying conventional clinical MRI systems creates a significant problem of availability and severely restricts the clinical applications for which MRI can be utilized.
  • low-field MRI systems can be used to continuously and/or regularly image a portion of anatomy of interest to detect changes occurring therein.
  • NMR neuro-intensive care unit
  • patients are often under general anesthesia for a significant amount of time while the patient is being assessed or during a procedure.
  • CT computed tomography
  • physicians may only have limited access to a computed tomography (CT) device for a patient (e.g., once a day).
  • CT computed tomography
  • CT computed tomography
  • the midline is detected by detecting locations of the attachment points of the falx cerebri, there are other ways of detecting the midline.
  • the midline may be detected by segmenting the left and right brain and the top and bottom part of the brain (as defined by the measurement plane).
  • the at least one landmark associated with the at last one midline structure of the patient' s brain may include an anterior attachment point of the falx cerebri (to the interior table of the patient's skull), a posterior attachment point of the falx cerebri, a point on the septum pellucidum.
  • the at least one landmark may indicate results of segmentation of the left and right sides of brain and/or the top and bottom portions of the brain.
  • determining the degree of change in the midline shift comprises: determining an initial amount of midline shift using the identified initial locations of the anterior attachment point of the falx cerebri, the posterior attachment point of the falx cerebri, and the measurement point on the septum pellucidum; determining an updated amount of midline shift using the identified updated locations of the anterior attachment point of the falx cerebri, the posterior attachment point of the falx cerebri, and the measurement point on the septum pellucidum; and determining the degree of change in the midline shift using the determined initial and updated amounts of midline shift.
  • determining the change in the size of the abnormality involves: (1) determining an initial size of the abnormality using the at least one value of the at least one feature; (2) determining an updated size of the abnormality using the at least one updated value of the at least one feature; and (3) determining the change in the size of the abnormality using the determined initial and updated sizes of the abnormality.
  • FIG. 1 is a block diagram of exemplary components of a MRI system 100.
  • MRI system 100 comprises workstation 104, controller 106, pulse sequences store 108, power management system 110, and magnetic components 120. It should be appreciated that system 100 is illustrative and that a MRI system may have one or more other components of any suitable type in addition to or instead of the
  • controller 106 also interacts with computing device
  • FIG. 2A and 2B illustrate bi-planar magnetic configurations that may be used in a low-field MRI system suitable for use with the change detection techniques described herein.
  • FIG. 2A schematically illustrates a bi-planar magnet configured to produce, at least in part, a portion of a Bo field suitable for low-field MRI.
  • Bi-planar magnet 200 comprises two outer coils 210a and 210b and two inner coils 212a and 212b. When appropriate current is applied to the coils, a magnetic field is generated in the direction indicated by the arrow to produce a Bo field having a field of view between the coils that, when designed and constructed appropriately, may be suitable for low-field MRI.
  • the term "coil” is used herein to refer to any conductor or combination of conductors of any geometry having at least one "turn” that conducts current to produce a magnetic field, thereby forming an electromagnet.
  • the bi-planar geometry illustrated in FIG. 2A is generally unsuitable for high-field MRI due to the difficulty in obtaining a Bo field of sufficient homogeneity at high-field strengths.
  • High-field MRI systems typically utilize solenoid geometries (and superconducting wires) to achieve the high field strengths of sufficient homogeneity for high-field MRI.
  • the bi-planar Bo magnet illustrated in FIG. 2A provides a generally open geometry, facilitating its use with patients who suffer from claustrophobia and may refuse to be imaged with conventional high-field solenoid coil geometries.
  • laminate techniques can be used to implement the Bo magnet in its entirety (e.g., replacing coils 210a and 210b).
  • Exemplary laminate panels 220a and 220b may, additionally or alternatively, have fabricated thereon one or more gradient coils, or portions thereof, to encode the spatial location of received MR signals as a function of frequency or phase.
  • a laminate panel comprises at least one conductive layer patterned to form one or more gradient coils, or a portion of one or more gradient coils, capable of producing or contributing to magnetic fields suitable for providing spatial encoding of detected MR signals when operated in a low-field MRI system.
  • the electromagnetic coils may be formed from any suitable material and dimensioned in any suitable way so as to produce or contribute to a desired Bo magnetic field, as the aspects are not limited for use with any particular type of electromagnet.
  • an electromagnet e.g., electromagnet 2010
  • an electromagnetic coil may be constructed using copper ribbon and mylar insulator having 155 turns to form an inner diameter of
  • the upper and lower coil(s) may be positioned to provide a distance of approximately 10-15 inches (e.g., approximately 12.5 inches) between the lower coil on the upper side and the upper coil on the lower side. It should be appreciated that the dimensions will differ depending on the desired characteristics including, for example, field strength, field of view, etc.
  • plates 2024a, 2024b is steel, for example, a low-carbon steel, silicon steel, cobalt steel, etc.
  • gradient coils (not shown in FIGS. 2C, 2D) of the MRI system are arranged in relatively close proximity to plates 2024a, 2024b inducing eddy currents in the plates.
  • plates 2024a, 2024b and/or frame 2022 may be constructed of silicon steel, which is generally more resistant to eddy current production than, for example, low-carbon steel.
  • yoke 2020 may be constructed using any ferromagnetic material with sufficient magnetic permeability and the individual parts (e.g., frame 2022 and plates 2024a, 2024b) may be constructed of the same or different ferromagnetic material, as the techniques of increasing flux density is not limited for use with any particular type of material or combination of materials. Furthermore, it should be appreciated that yoke 2020 can be formed using different geometries and arrangements.
  • the arms are generally designed to reduce the amount of material needed to support the permanent magnets while providing sufficient cross-section for the return path for the magnetic flux generated by the permanent magnets.
  • Arms 2123a has two supports within a magnetic return path for the Bo field produced by the Bo magnet.
  • Supports 2125a and 2125b are produced with a gap 2127 formed between, providing a measure of stability to the frame and/or lightness to the structure while providing sufficient cross-section for the magnetic flux generated by the permanent magnets.
  • the cross-section needed for the return path of the magnetic flux can be divided between the two support structures, thus providing a sufficient return path while increasing the structural integrity of the frame. It should be appreciated that additional supports may be added to the structure, as the technique is not limited for use with only two supports and any particular number of multiple support structures.
  • exemplary permanent magnets 2110a and 2110b comprise a plurality of rings of permanent magnetic material concentrically arranged with a permanent magnet disk at the center.
  • Each ring may comprise a plurality of stacks of ferromagnetic material to form the respective ring, and each stack may include one or more blocks, which may have any number (including a single block in some embodiments and/or in some of the rings).
  • the blocks forming each ring may be dimensioned and arranged to produce a desired magnetic field.
  • FIGS . 3 A-3B illustrate a portable or cartable low-field MRI system 300 suitable for use in performing change detection techniques described herein, in accordance with some embodiments.
  • System 300 may include magnetic and power components, and potentially other components (e.g., thermal management, console, etc.), arranged together on a single generally transportable and transformable structure.
  • System 300 may be designed to have at least two configurations; a configuration adapted for transport and storage, and a configuration adapted for operation.
  • FIG. 3A shows system 300 when secured for transport and/or storage
  • FIG. 3B shows system 300 when transformed for operation.
  • electromagnetic shielding refers generally to any conductive or magnetic barrier that acts to attenuate at least some electromagnetic radiation and that is positioned to at least partially shield a given space, object or component by attenuating the at least some electromagnetic radiation.
  • electromagnetic shielding for certain electronic components may be configured to attenuate different frequencies than electromagnetic shielding for the imaging region of the MRI system.
  • the spectrum of interest includes frequencies which influence, impact and/or degrade the ability of the MRI system to excite and detect an MR response.
  • the spectrum of interest for the imaging region of an MRI system correspond to the frequencies about the nominal operating frequency (i.e., the Larmor frequency) at a given Bo magnetic field strength for which the receive system is configured to or capable of detecting.
  • This spectrum is referred to herein as the operating spectrum for the MRI system.
  • electromagnetic shielding that provides shielding for the operating spectrum refers to conductive or magnetic material arranged or positioned to attenuate frequencies at least within the operating spectrum for at least a portion of an imaging region of the MRI system.
  • a noise reduction system comprising one or more noise reduction and/or compensation techniques may be performed to suppress at least some of the electromagnetic noise that is not blocked or sufficiently attenuated by shielding 3865.
  • the inventors have developed noise reduction systems configured to suppress, avoid and/or reject electromagnetic noise in the operating environment in which the MRI system is located.
  • these noise suppression techniques work in conjunction with the moveable shields to facilitate operation in the various shielding configurations in which the slides may be arranged. For example, when slides 3960 are arranged as illustrated in FIG. 3F, increased levels of electromagnetic noise will likely enter the imaging region via the openings. As a result, the noise suppression component will detect increased electromagnetic noise levels and adapt the noise suppression and/or avoidance response accordingly.
  • electrical gaskets may be arranged to provide continuous shielding along the periphery of the moveable shield.
  • electrical gaskets 3867a and 3867b may be provided at the interface between slides 3860 and magnet housing to maintain to provide continuous shielding along this interface.
  • the electrical gaskets are beryllium fingers or beryllium- copper fingers, or the like (e.g., aluminum gaskets), that maintain electrical connection between shields 3865 and ground during and after slides 3860 are moved to desired positions about the imaging region.
  • electrical gaskets 3867c are provided at the interface between slides 3860, as illustrated in FIG. 3F so that continuous shielding is provided between slides in arrangements in which the slides are brought together. Accordingly, moveable slides 3860 can provide configurable shielding for the portable MRI system.
  • a motorized component 3880 is provide to allow portable MRI system to be driven from location to location, for example, using a control such as a joystick or other control mechanism provided on or remote from the MRI system.
  • portable MRI system 3800 can be transported to the patient and maneuvered to the bedside to perform imaging, as illustrated in FIGS. 3E and 3F.
  • FIG. 3E illustrates a portable MRI system 3900 that has been transported to a patient's bedside to perform a brain scan.
  • FIG. 3F illustrates portable MRI system 3900 that has been transported to a patient's bedside to perform a scan of the patient's knee.
  • the portable MRI systems described herein may be operated from a portable electronic device, such as a notepad, tablet, smartphone, etc.
  • tablet computer 3875 may be used to operate portable MRI system to run desired imaging protocols and to view the resulting images.
  • Tablet computer 3875 may be connected to a secure cloud to transfer images for data sharing, telemedicine, and/or deep learning on the data sets. Any of the techniques of utilizing network connectivity described in U.S. Application No.
  • FIG. 3G illustrates another example of a portable MRI system, in accordance with some embodiments of the technology described herein.
  • Portable MRI system 4000 may be similar in many respects to portable MRI systems illustrated in FIGS. 3C-3F.
  • slides 4060 are constructed differently, as is shielding 4065, resulting in electromagnetic shields that are easier and less expensive to manufacture.
  • a noise reduction system may be used to allow operation of a portable MRI system in unshielded rooms and with varying degrees of shielding about the imaging region on the system itself, including no, or substantially no, device-level electromagnetic shields for the imaging region.
  • Electromagnetic shielding can be implemented in any suitable way using any suitable materials.
  • electromagnetic shielding may be formed using conductive meshes, fabrics, etc. that can provide a moveable "curtain" to shield the imaging region.
  • Electromagnetic shielding may be formed using one or more conductive straps (e.g., one or more strips of conducting material) coupled to the MRI system as either a fixed, moveable or configurable component to shield the imaging region from electromagnetic interference, some examples of which are described in further detail below.
  • Electromagnetic shielding may be provided by embedding materials in doors, slides, or any moveable or fixed portion of the housing. Electromagnetic shields may be deployed as fixed or moveable components, as the aspects are not limited in this respect.
  • FIG. 4 illustrates a method of monitoring a patient using low-field MRI to detect changes therein, in accordance with some embodiments.
  • first MR image data is acquired by a low-field MRI device of a target portion of anatomy (e.g., a portion of the brain, a portion of a knee, etc.) of a patient positioned within the low-field MRI device.
  • Positioning a patient within the low-field device refers to placing the patient relative to the magnetic components of the low-field MRI device such that a portion of the patient' s anatomy is located within the field of view of the low-field MRI device so that MR image data can be acquired.
  • MR image data is used herein to refer to MR data generically including, but not limited to, MR data prior to image reconstruction (e.g., k-space MR data) and MR data that has been processed in some way (e.g., post- image reconstruction MR data such as a three dimensional (3D) volumetric image). Because both registration and change detection techniques described herein can be performed in any domain (or a combination of domains), the term MR image data is used to refer to acquired MR data agnostic to domain and/or whether image reconstruction (or any other processing) has been performed.
  • MR image data of a patient' s brain may be acquired to monitor temporal changes within the brain (e.g., changes regarding an aneurysm or bleeding within the brain, changes in a tumor or other tissue anomaly, changes in chemical composition, etc.).
  • subsequent (next) MR image data is acquired of the same or substantially the same portion of the anatomy included in the first MR image data.
  • the next MR image data may be acquired immediately following acquisition of the first MR image data, or may be obtained after a desired period of delay (e.g., after 1, 2, 3, 4, 5, 10, 15, 20 minutes, etc.).
  • the next MR image data captures the portion of the anatomy after some finite amount of time has elapsed.
  • the inventors have appreciated that low-field MRI facilitates relatively fast image acquisition, allowing a temporal sequence of MR image data to be acquired in relatively quick succession, thus capturing changes that may be of interest to the physician.
  • the accessibility, availability and/or relative low cost of the low-field MRI system enables MR data to be acquired over extended periods of time at any time interval needed to monitor and/or otherwise observe and evaluate the patient.
  • the next MR image data may be of any form (e.g., a 3D volumetric image, a 2D image, k-space MR data, etc.).
  • the next MR image data (or any subsequent next MR image data acquired) is obtained using the same acquisition parameters used to acquire the first MR image data.
  • the same pulse sequence, field of view, SNR, and resolution may be used to acquire MR signals from the same portion of the patient.
  • the MR image data may be compared to evaluate changes that have occurred within the anatomy being imaged.
  • MR image data may be used to determine whether there is a change in the degree of midline shift in a patient.
  • MR image data may be used to determine whether there is a change in a size of an
  • one or more acquisition parameters may be altered to change the acquisition strategy for acquiring next MR image data, as discussed in further detail below in connection with FIG. 5.
  • the first, next and any subsequent MR image data acquired are referred to as respective "frames" of MR image data.
  • a sequence of frames may be acquired and the individual frames may be registered in a sequence of frames acquired over time.
  • a frame corresponds to acquired MR image data representative of the particular time at which the MR image data was acquired.
  • Frames need not include the same amount of MR image data or correspond to the same field of view, but frames generally need sufficient overlap so that adequate feature descriptors can be detected (e.g., sufficient subject matter in common between frames).
  • the first and next MR image data are co-registered or aligned with one another.
  • Any suitable technique may be used to co-register the first and next MR image data, or any pair of acquired MR image data for which change detection processing is desired.
  • registration may be performed by assuming that the patient is still so that the MR image data is aligned without transforming or deforming the MR image data.
  • More sophisticated registration techniques used to align the MR image data to account for movement of the patient, breathing, etc. include, but are not limited to, the use of deformation models and/or correlation techniques adapted to MR image data acquired at different points in time.
  • co-registering acquired MR image data involves determining a transformation that best aligns the MR image data (e.g., in a least squares sense).
  • the transformation between MR image data acquired at different points in time may include translation, rotation, scale or any suitable linear or non-linear deformation, as the aspects are not limited in this respect.
  • the transformation may be determined at any desired scale. For example, a transformation may be determined for a number of identified sub-regions (e.g., volumes including a number of voxels) of the MR image data, or may be determined for each voxel in the MR image data.
  • the transformation may be determined in any manner, for example, using a deformation model that deforms a mesh or coordinate frame of first MR image data to the coordinate frame of next MR image data and vice versa. Any suitable registration technique may be used, as the aspects are not limited in this respect.
  • An illustrative process for co-registering MR image data acquired at different points in time in accordance with some embodiment, is discussed in further detail below in connection with FIG. 6.
  • one or more changes are detected in the co-registered MR image data.
  • differences between the MR image data can be attributed to changes in the patient's anatomy being imaged (e.g., morphological changes to the anatomy or other changes to the biology or physiology of the imaged anatomy), such as a change in the size of an aneurysm, increased or decreased bleeding, progression or regression of a tumor or other tissue anomaly, changes in chemical composition, or other biological or physiological changes of interest.
  • Change detection can be performed in any suitable way.
  • change detection may be performed in k-space using amplitude and phase information (coherent change detection), or change detection can be performed in the image domain using intensity information (non-coherent change detection).
  • coherent change detection may be more sensitive, revealing changes on the sub-voxel level.
  • non-coherent change detection may be generally less sensitive, change detection in the image domain may be more robust to co-registration errors.
  • change detection may be performed by deriving features from each MR frame in a sequence of MR frames and comparing the features to one another.
  • image processing techniques e.g., including the deep learning techniques described herein
  • the sequence of midline shift measurements may be used to determine whether there is a change in the degree of midline shift for the patient being monitored.
  • image processing techniques may be applied to each MR frame in a sequence of two or more MR frames, obtained by imaging a patient's brain, to identify a respective sequence of two or more measurements of a size of an abnormality in the patient's brain (e.g., a hemorrhage, a lesion, an edema, a stroke core, a stroke penumbra, and/or swelling).
  • a size of an abnormality in the patient's brain e.g., a hemorrhage, a lesion, an edema, a stroke core, a stroke penumbra, and/or swelling.
  • the sequence of size measurements may be used to determine whether there is a change in the size of the abnormality in the brain of a patient being monitored.
  • multi-resolution techniques may be used to perform change detection.
  • the first MR image data may correspond to a baseline high- resolution image
  • subsequently- acquired MR image data may correspond to low- resolution images that may be correlated with the high-resolution baseline image.
  • Acquiring low-resolution images may speed up the frame rate of the change detection process enabling the acquisition of more data in a shorter period of time.
  • Any suitable techniques or criteria may be used to determine which data to acquire for a low-resolution image.
  • the particular data to acquire for a low-resolution image may be determined using, for example, wavelets, selective k-space sampling, polyphase filtering, key-frame based techniques, etc. Sparse sampling of k-space over short time intervals (e.g., time-varying selective sampling of k- space), as an example, results in better time resolution.
  • the selection of particular data to acquire may also be determined by detecting changes between MR image data frames. For example, when a change is detected, a ID or 2D volume selection having a field of view that includes the location of the detected change may be selected for acquisition to interrogate a particular part of the anatomy demonstrating change over time.
  • a finite impulse response (FIR) filter is applied to each "voxel" in the frame, which can be used as a reference. Filtering can also be used to provide a "look-ahead filter” that considers a number of frames over which to perform change detection. For example, a current, previous and next frame may be evaluated using a sliding window to analyze changes over a desired number of frames.
  • FIR finite impulse response
  • change detection is used to selectively determine particular data (e.g., particular lines in k-space) to acquire, such that MR data used for image reconstruction may be acquired in a shorter timeframe than would be required to acquire a full 3D volume.
  • particular data e.g., particular lines in k-space
  • an initial 3D volume may first be acquired. Then, at subsequent points in time, rather than reacquiring the full 3D volume, a subset of the lines in k-space selected based on parts of the image that are changing may be acquired and the previous 3D volume may be updated with the newly acquired data.
  • a particular feature or area of interest may be identified a priori, and the acquisition sequence may be tailored to acquire lines of k-space that will emphasize the identified feature or area of interest. For example, the acquisition sequence may focus on acquiring just the edges of k-space or any other suitable part of k-space.
  • the identified area of interest may be a portion of the anatomy. For example, to analyze a post-surgical bleed, it may not be necessary to acquire data on the entire anatomy. Rather, select portions of k-space that correspond to the anatomy of interest for monitoring may be sampled multiple times in a relatively brief period of time to enable a physician to closely monitor changes in the anatomy of interest over the shorter timescale providing for a high temporal correlation between the acquisitions.
  • the intensity of voxels in 3D images reconstructed from acquired MR data may be compared to evaluate changes as they occur over time.
  • Detected changes either evaluated coherently (e.g., in k-space) or non-coherently (e.g., in 3D images) may be conveyed in any number of ways.
  • changes in the MR image data may be emphasized on displayed images to provide a visual indication to a physician of changes occurring over time.
  • voxels undergoing change can be rendered in color that in turn may be coded according to the extent of the change that occurred. In this manner, a physician can quickly see the "hot spots" that are undergoing significant change.
  • change detection can be performed by analyzing regions over which changes are occurring.
  • connected component analysis may be used to locate contiguous regions where voxel changes have occurred. That is, regions of connected voxels that have undergone change may be emphasized or displayed differently (e.g., using color, shading, etc.) to indicate that changes are occurring in the corresponding regions.
  • Changes detected in acquired MR image data may be conveyed in other ways, as the aspects are not limited in this respect.
  • Shape and volume analysis may also be performed to assess whether a given feature of the anatomy of interest is changing (e.g., growing or shrinking, progressing or regressing, or to otherwise characterize change in the features).
  • image processing techniques can be used to segment MR image data into regions and to assess one or more properties of the segment such as shape, volume, etc. Changes to the one or more segments properties may be conveyed to a physician via a display or otherwise.
  • the size of a tumor may be monitored across a sequence of images to evaluate whether the tumor is increasing or decreasing in size.
  • a brain bleed may be monitored over time wherein the important change to evaluate is the volume of the bleed.
  • acquired MR image data may be processed to segment features of interest (e.g., tumor, bleed, hemorrhage, etc.) and compute the volume of the corresponding feature.
  • segmented volumes can be analyzed in other ways to characterize metrics of interest for the segmented volume.
  • 2D and/or 3D shape descriptors may be applied to the segmented features to characterize any number of aspects or properties of the segmented feature including, but not limited to, volume, surface area, symmetry, "texture,” etc.
  • change detection may be performed on features of interest captured in the acquired MR data to evaluate how the features are changing over time.
  • Changes detected in segmented features can be utilized not only to understand how the feature is evolving in time, but characteristics of the particular features can be compared to stored information to assist in differentiating healthy from unhealthy, normal from anomalous and/or to assess the danger of a particular condition.
  • the information obtained from the MR data may also be stored along with existing information to grow the repository of information that can be used for subsequent data analysis.
  • techniques may be used to remove changes in the data caused by regular or periodic movement, such as breathing or heart beat etc. By determining which parts of the image are changing and which are not, it is possible to focus acquisition on only the parts of the image that are changing and not acquire data for the parts of the image that are not changing. By acquiring a smaller set of data only related to the parts of the image that are changing, the acquisition time is compressed. Additionally, some changes in the image are caused by periodic events such as breathing and heartbeats. In some embodiments, periodic events are modeled based on their periodicity to enable a change detection process to ignore the periodic movements caused by the period events when determining which parts of the image are changing and should be the focus of acquisition.
  • change detection may be performed by detecting the rate of change of MR image data over a sequence of acquired MR image data.
  • a rate of change refers to any functional form of time. Detecting the rate of change may provide richer data regarding the subject matter being imaged, such as indicating the severity of a bleed, size of a hemorrhage, increase in midline shift, the aggressiveness of a lesion, etc.
  • a contrast agent when administered, there is a natural and expected way in which the contrast agent is taken up by the body. The uptake of contrast agent is detected as a signal increase that will register as a change having a particular functional form.
  • the manner in which the signal changes as the contrast agent washes out and/or is metabolized will also give rise to a detectable change in signal that will have a functional form over time.
  • the functional form of changes over time can provide information about the type, aggressiveness or other characteristics of a lesion or other abnormality that can provide clinically useful and/or critical data.
  • a stroke victim may be monitored after a stroke has occurred, changes in the time course of the stroke lesion that differs from expected might be used to alert personnel to unusual changes, provide a measure of drug efficacy, or provide other information relevant to the condition of the patient.
  • detecting rate of change can facilitate higher order analysis of the subject matter being imaged.
  • Techniques are available that facilitate faster acquisition of MR data, enabling quicker image acquisition for low-field MRI.
  • compressed sensing techniques, sparse imaging array techniques and MR fingerprinting are some examples of techniques that can expedite MR image acquisition.
  • Doppler techniques may be used to analyze multiple frames of images over a short period of time to estimate velocities that may be used to filter out parts of the image that are not changing.
  • act 420 may be repeated to obtain further MR image data, either immediately or after waiting for a predetermined amount of time before acquiring subsequent MR image data.
  • Subsequently acquired MR image data may be compared with any MR image data previously acquired to detect changes that have occurred over any desired interval of time (e.g., by repeating act 430 and 440).
  • sequences of MR image data can be obtained and changes detected and conveyed to facilitate understanding of the temporal changes taking place in the portion of the anatomy of the patient being monitored, observed and/or evaluated.
  • any acquired MR image data can be registered and analyzed for change. For example, successive MR image data may be compared so that, for example, changes on a relatively small time scale can be detected. The detected change may be conveyed to a physician so that the anatomy of interest can be continuously, regularly and/or periodically monitored.
  • acquired MR image data may be stored so that a physician can request change detection be performed at desired points of interest.
  • a physician may be interested to see changes that have taken place within the last hour and may specify that change detection be performed between MR image data acquired an hour ago and present time MR image data.
  • the physician may specify an interval of time, may specify multiple times of interest, or may select thumbnails of timestamped images to indicate which MR image data the physician would like change detection performed.
  • the techniques described herein may be used to monitor ongoing changes and/or to evaluate changes that have occurred over any interval of time during which MR image data has been acquired.
  • the above described change detection techniques may be used to enable monitoring, evaluation and observation of a patient over a period of time, thus enabling MRI to be utilized as a monitoring tool in ways that conventional MRI and other modalities cannot be used.
  • acquired MR image data may be used to evaluate change with respect to a stored high-field MRI scan.
  • a patient may be imaged using a high-field MRI scan initially, but subsequent monitoring (which would not be feasible using high-field MRI) would be performed using a low-field MRI system, examples of which are provided herein.
  • the change detection techniques described herein can be applied not only to detecting changes between sets MR image data acquired by a low-field MRI system, but also to detecting changes between MR image data acquired by a high-field MRI system (e.g., initially) and MR image data acquired by a low-field MRI system (e.g., subsequently), regardless of the order in which the high-field MR image data and the low-field MR image data was obtained.
  • FIG. 5 illustrates a method of changing an acquisition strategy based, at least in part, on observations made regarding change detection.
  • the inventors have developed a multi-acquisition console that allows acquisition parameters to be modified on the fly to dynamically update an acquisition strategy implemented by the low-field MRI system. For example, commands to the low-field MRI system can be streamed from the console to achieve dynamic updates to the acquisition process.
  • the inventors have appreciated that the ability to dynamically update acquisition parameters and/or change the acquisition strategy can be exploited to achieve a new paradigm for MRI, enabling the MRI system to be used for monitoring a patient and adapting the acquisition strategy based on observations of the acquired MR image data (e.g., based on change detection information).
  • acts 510-540 may be similar to acts 410- 440 of method 400 illustrated in FIG. 4 to obtain change detection information in regard to MR image data obtained by a low-field MRI system.
  • at least one acquisition parameter may be updated, changed or other modified based on the results of change detection. Acquisition parameters that may be varied are not limited in any respect, and may include any one or combination of field of view, signal-to-noise ratio (SNR), resolution, pulse sequence type, etc. Some examples of acquisition parameters that may be changed are described in further detail below.
  • SNR signal-to-noise ratio
  • change detection information may be used to update the acquisition parameters to, for example, increase SNR of MR data obtained from a particular region. For example, based on characteristics of co-registration (e.g., properties of the transformation, deformation models, etc.) and/or changes observed in particular regions, it may be desirable to increase the SNR in those regions to, for example, better evaluate the subject matter present, to improve further change detection, or otherwise obtaining more information regarding the portion of the anatomy being monitored and/or observed. Similarly, acquisition parameters may be altered to obtain higher resolution MR data for particular regions of the portion of anatomy being monitored/observed. Change detection may reveal that a patient has moved or subject matter of interest is no longer optimally in the field of view. This information may be utilized to dynamically change the field of view of subsequent image acquisition.
  • characteristics of co-registration e.g., properties of the transformation, deformation models, etc.
  • acquisition parameters may be altered to obtain higher resolution MR data for particular regions of the portion of anatomy being monitored/observed.
  • Change detection may reveal that
  • the type of pulse sequence that is applied may be changed based on what is observed in change detection data obtained from acquired MR image data. Different pulse sequences may be better at capturing particular types of information and these differences can be exploited to allow for appropriate exploration based on observed change detection data. Due, at least in part, to the dynamic capability of the system developed by the inventors, different pulse sequences can be interleaved, alternated or otherwise utilized to acquire MR data that captures information of interest.
  • a fast spin echo sequence may have been used to acquire a number of frames of MR image data and the results of change detection may suggest the benefit of changing to a different pulse sequence, for example, a bSSFP sequence to observe a particular change (e.g., to obtain different MR data, to allow for higher SNR or resolution in a particular region, etc.).
  • a bSSFP sequence to observe a particular change (e.g., to obtain different MR data, to allow for higher SNR or resolution in a particular region, etc.).
  • changes that may not be observable using one type of sequence may be seen by changing the type of pulse sequence being used.
  • pulse sequences may be chosen for the type of contrast provided (e.g., Tl, T2, etc.) or the type of information that is captured, and the appropriate pulse sequence can be utilized to obtain MR data, which can be changed dynamically during the monitoring process.
  • the choice of pulse sequence or combination of pulse sequences used can be guided by the change detection information that is obtained.
  • MR data may be captured using a given pulse sequence and, based on obtained change detection information (e.g., based on information obtained by performing act 540), the pulse sequence may be changed to explore a region using magnetic resonance spectroscopy (MRS). In this manner, exploration of the chemical composition of a portion of anatomy being monitored may be initiated as a result of changes observed in the MR data.
  • MRS magnetic resonance spectroscopy
  • the acquisition parameters may be varied dynamically at any time during acquisition. That is, a full acquisition need not complete before altering the acquisition strategy.
  • updating acquisition parameter(s) may be performed based on partial acquisition and/or partial image reconstruction to facilitate an acquisition strategy that is fully dynamic.
  • the ability to dynamically update any one or combination of acquisition parameters allows MRI to be utilized as a monitoring and exploration tool, whereas conventional MRI systems cannot be used in this way.
  • DWI diffusion weighted imaging
  • power savings may be achieved by interleaving acquisitions for a DWI (or other) sequence with acquisitions that require less power.
  • a desired goal e.g., low power consumption, reduced heating, reducing stress on the gradient coils, etc.
  • biological or physiological events that unfold over a relatively short timeframe may be studied using the change detection techniques described herein.
  • change detection techniques For example, for arterial spin labeling, a full data set may be initially obtained, and subsequent acquisitions may sparsely sample the data. Perfusion of the blood over time may be monitored change detection, where the changes in the image correspond to the inflowing blood to a particular region of the imaged anatomy.
  • co-registration of MR image data acquired at different points in time enables the identification of changes in MR data by reducing the effect of patient movement on the change detection process.
  • the co-registration may be accomplished with a model for the effects of deformation.
  • the deformation mesh captures changes in shape and distribution over time, which may occur from subtle movements of the patient or from biological morphology.
  • the k-space acquisition strategy may be updated based on new constraints of the deformed volume. For example, acquisition parameters affecting field of view, SNR, resolution, etc., may be updated based on new constraints of the deformed volume.
  • FIG. 6 illustrates a technique 600 for co-registering frames of MR image data, in accordance with some embodiments.
  • registration technique 600 may be used to align a pair of frames acquired at two separate times.
  • one or more feature descriptors appearing or common to the frames being co-registered are detected.
  • Feature descriptors may be any feature present in the MR image between frames that can be reliably detected.
  • Features may include local characteristics such as edges, corners, ridges, etc. and/or may include region characteristics such as curves, contours, shape, intensity distributions and/or patterns, etc. Any feature or characteristic that can be reliably detected between frames may be used as a feature descriptor, as the aspects are not limited in this respect.
  • Any suitable technique may be used to determine the feature descriptors including, but not limited to, SIFT, SURF, U-SURF, CenSurE, BRIEF, ORB, and corner detector techniques such as FAST, Harris, Hessian, and Shi-Tomasi.
  • the process proceeds to act 620, where associated sub-regions across the frames are correlated.
  • the correlation calculations between sub-regions may be performed in any number of dimensions (e.g., ID, 2D, 3D), as aspects are not limited in this respect.
  • the process proceeds to act 630, where the warped or deformed model from frame to frame is determined based on the correlations between the sub-regions in the different frames.
  • act 640 wherein the model deformation is used to co-register the data across the multiple frames.
  • change detection metrics including, but not limited to those discussed above, such as coherent changes, non-coherent changes, and others including position changes, velocity, acceleration or time derivative vectors may be determined using the co-registered data.
  • Other metrics including segmentation and geometric shape descriptors such as surface area, volume, crinkliness, spherical harmonic basis coefficients, etc. may also be determined based on the co-registered data and optionally the metrics may be used to update acquisition parameters for future acquisitions on the fly as discussed above.
  • Midline shift refers to an amount of displacement of the brain's midline from its normal symmetric position due to trauma (e.g., stroke, hemorrhage, or other injury) and is an important indicator for clinicians of the severity of the brain trauma.
  • the midline shift may be characterized as a shift of the brain past its midline, usually in the direction away from the affected side (e.g., a side with an injury).
  • the midline shift may be measured as the distance between a midline structure of the brain (e.g., a point on the septum pellucidum) and a line designated as the midline.
  • the midline may be coplanar with the falx cerebri (also known as the cerebral falx), which a crescent-shaped fold of the meningeal layer of dura mater that descends vertically in the longitudinal fissure between the cerebral hemispheres of the human brain.
  • the midline may be represented as a line connecting the anterior and posterior attachments of the falx cerebri to the inner table of the skull.
  • the midline 702 is a line connecting the anterior and posterior attachment points 706a and 706b of the falx cerebri.
  • the midline shift may be measured as the distance between the measurement point 706c in the septum pellucidum and the midline 702. That distance is the length of the line 704 defined by endpoints 706c and 706d, and which is orthogonal to midline 702.
  • the midline 712 is a line connecting the anterior and posterior attachment points 716a and 716b of the falx cerebri.
  • the midline shift may be measured as the distance between the measurement point 716c in the septum pellucidum and the midline 712. That distance is the length of the line 714 defined by endpoints 716c and 716d, and which is orthogonal to midline 712.
  • FIG. 8 is a flowchart of an illustrative process 800 for determining a degree of change in the midline shift of a patient, in accordance with some embodiments of the technology described herein.
  • the entirety of process 800 may be performed while the patient is within a low-field MRI device, which may be of any suitable type described herein including, for example, any of the low-field MRI devices illustrated in FIGs. 3A-3G).
  • Process 800 begins at act 802, where the low-field MRI device acquires initial magnetic resonance data of a target portion of the patient's brain.
  • MR image data is used herein to refer to MR data generically including, but not limited to, MR data prior to image reconstruction (e.g., k-space MR data) and MR data that has been processed in some way (e.g., post-image reconstruction MR data such as a three dimensional (3D) volumetric image).
  • the initial MR data may include one or more two-dimensional images of respective brain slices (e.g., two, three, four, five, etc.
  • the slices may be neighboring.
  • the initial MR data may include one or more 2D images of one or more respective slices in which the two lateral ventricles are prominent.
  • the initial MR image data is provided as input to a trained statistical classifier in order to obtain corresponding initial output.
  • the initial MR image data may be pre-processed, for example, by resampling, interpolation, affine transformation, and/or using any other suitable pre-processing techniques, as aspects of the technology described herein are not limited in this respect.
  • the output of the trained statistical classifier may indicate one or more initial locations, in the initial MR data, of one or more landmarks associated with at least one midline structure of the patient's brain. This location or locations may be identified from output of the trained statistical classifier at act 806 of process 800. The output may specify the location(s) directly or indirectly. In the latter case, the location(s) may be derived from information included in the output of the trained statistical classifier.
  • the output of the trained statistical classifier may indicate the locations of the anterior and posterior falx cerebri attachment points and the location of a measurement point in the septum pellucidum.
  • the output of the trained statistical classifier may indicate the locations of the landmarks (e.g., falx cerebri attachment points and measurement point in the septum pellucidum) within the 2D image.
  • the locations of the falx cerebri attachment points and the measurement point in the septum pellucidum may be used to make a midline shift measurement.
  • the trained statistical classifier may be a neural network statistical classifier.
  • the training statistical classifier may include a
  • convolutional neural network e.g., as illustrated in FIGs. 9A and 9B
  • a convolutional neural network and a recurrent neural network such as a long short-term memory network, (e.g., as illustrated in FIGs. 9A and 9C), a fully convolutional neural network (e.g., as illustrated in FIG. 10), and/or any other suitable type of neural network.
  • the trained statistical classifier may be implemented in software, in hardware, or using any suitable combination of software and hardware.
  • one or more machine learning software libraries may be used to implement the trained statistical classifier including, but not limited to, Theano, Torch, Caffe, Keras, and TensorFlow.
  • a statistical classifier e.g., a neural network
  • a trained statistical classifier e.g., a neural network
  • aspects of training the trained statistical classifier used at acts 804 and 806 are described in more detail below.
  • the trained statistical classifier is not limited to being a neural network and may be any other suitable type of statistical classifier (e.g., a support vector machine, a graphical model, a Bayesian classifier, a decision tree classifier, etc.), as aspects of the technology described herein are not limited in this respect.
  • the trained statistical classifier may be a convolutional neural network.
  • FIGs. 9A and 9B show an illustrative example of such a convolutional neural network.
  • an input image (a 256 x 256 image in this example) is provided as input to the convolutional neural network, which processes the input image through an alternating series of convolutional and pooling layers.
  • the convolutional neural network processes the input image using two convolutional layers to obtain 32 256x256 feature maps.
  • a pooling layer e.g., a max pooling layer
  • two more convolutional layers are applied to obtain 64 128x128 feature maps.
  • the resulting 256 32x32 feature maps are provided as input to the portion of the neural network shown in FIG. 9B.
  • the feature maps are processed through at least one fully connected layer to generate predictions.
  • the predictions may, in some embodiments, indicate locations of falx cerebri attachment points (e.g., posterior and anterior attachment points, and a measurement point on the septum pellucidum).
  • FIG. 9A and 9C show another illustrative example of a neural network that may be used as the trained statistical classifier, in some embodiments.
  • the neural network of FIGs. 9A and 9C has a convolutional neural network portion (shown in FIG. 9A, which was described above) and a recurrent neural network portion (shown in FIG. 9C), which may be used to model temporal constraints among input images provided as inputs to the neural network over time.
  • the recurrent neural network portion may be implemented as a long short-term memory (LSTM) neural network.
  • LSTM long short-term memory
  • Such a neural network architecture may be used to process a series of images obtained by a low-field MRI apparatus during performance of a monitoring task. A series of images obtained by the low-field MRI apparatus may be provided as inputs to the CNN-LSTM neural network, within which, features derived from at least one earlier-obtained image may be combined with features obtained from a later- obtained image to generate predictions.
  • the neural networks illustrated in FIGs. 9A-9C may use a kernel size of 3 with a stride of 1 for convolutional layers, a kernel size of "2" for pooling layers, and a variance scaling initializer.
  • the neural networks illustrated in FIGs. 9A-C may be used to process a single image (e.g., a single slice) at a time. In other embodiments, the neural networks illustrated in FIGs. 9A-9C may be used to process multiple slices (e.g., multiple neighboring slices) at the same time. In this way, the features used for prediction point locations (e.g., locations of the falx cerebri attachment points and a measurement point on the septum pellucidum) may be computed using information from a single slice or from multiple neighboring slices. [163] In some embodiments, when multiple slices are being processed by the neural network, the convolutions may be two-dimensional (2D) or three-dimensional (3D) convolutions.
  • the processing may be slice based so that features are calculated for each slice using information from the slice and one or more of its neighboring slices (only from the slice itself or from the slice itself and one or more of its neighbors).
  • the processing may be a fully-3D processing pipeline such that features for multiple slices are computed concurrently using data present in all of the slices.
  • a fully-convolutional neural network architecture may be employed.
  • the output is a single-channel output having the same dimensionality as the input.
  • a map of point locations e.g., falx cerebri attachment points
  • the neural network trained to regress these profiles using mean-squared error loss.
  • FIG. 10 illustrates two different fully convolutional neural network
  • the first architecture with processing involving processing path (a), includes three portions: (1) an output compressive portion comprising a series of alternating convolutional and pooling layers; (2) a long short- term memory portion (indicated by path (a)); and (3) an input expanding portion comprising a series of alternating convolutional and deconvolutional layers.
  • This type of architecture may be used to model temporal constraints, as can the neural network architecture of FIGs. 9A and 9c.
  • the second architecture includes three portions: (1) an output compressive portion comprising a series of alternating convolutional and pooling layers; (2) a convolutional network portion (indicated by path (b)); and (3) an input expanding portion comprising a series of alternating convolutional and deconvolutional layers and a center-of-mass layer.
  • the center of mass layer computes the estimate as a center of mass computed from the regressed location estimates at each location.
  • the neural networks illustrated in FIG. 10 may use a kernel size of 3 for convolutional layers with stride of 1, a kernel size of "2" for the pooling layers, a kernel of size 6 with stride 2 for deconvolutional layers, and a variance scaling initializer.
  • the convolutions may be two-dimensional (2D) or three- dimensional (3D) convolutions.
  • the processing may be slice based so that features are calculated for each slice using information from the slice and one or more of its neighboring slices.
  • the processing may be a fully 3D processing pipeline such that features for multiple slices are computed concurrently using data present in all of the slices.
  • the neural network architectures illustrated in FIGs. 9A-9C and FIG. 10 are illustrative and that variations of these architectures are possible.
  • one or more other neural network layers e.g., a convolutional layer, a deconvolutional layer, a rectified linear unit layer, an upsampling layer, a concatenate layer, a pad layer, etc.
  • the dimensionality of one or more layers may be varied and/or the kernel size for one or more convolutional, pooling, and/or
  • deconvolutional layers may be varied.
  • process 800 proceeds to act 808, where the next MR image data is acquired.
  • the next MR image data is acquired after the initial MR data acquired.
  • acts 804 and 806 may be performed after act 808 is performed
  • act 808 is generally performed after act 802.
  • the next MR image data may be acquired immediately following acquisition of the initial MR image data, or may be obtained after a desired period of delay (e.g., within 1, 2, 3, 4, 5, 10, 15, 20 minutes, within one hour, within two hours, etc.).
  • the next MR image data may be of any form (e.g., a 3D volumetric image, a 2D image, k-space MR data, etc.).
  • the initial MR data and the next MR image data are of the same type.
  • each of the initial and next MR data may include one or more two-dimensional images of one or more respective (e.g., neighboring) brain slices.
  • the initial MR data may include multiple images of neighboring slices obtained at a first time and the next MR data may include multiple images of the same neighboring slices obtained at a second time later than the first time.
  • process 800 proceeds to act 810 where the next MR image data is provided as input to the trained statistical classifier to obtain the corresponding next output.
  • the next MR image data may be pre-processed, for example, by resampling, interpolation, affine transformation, and/or using any other suitable pre-processing techniques, as aspects of the technology described herein are not limited in this respect.
  • the next MR image data may be preprocessed in the same way as the initial MR data was preprocessed.
  • the output of the trained statistical classifier obtained at act 812 may indicate the updated locations of the anterior and posterior falx cerebri attachment points and the updated location of a measurement point in the septum pellucidum.
  • the corresponding output of the trained statistical classifier may indicate the updated locations of the landmarks (e.g., falx cerebri attachment points and measurement point in the septum pellucidum) within the 2D image.
  • the updated locations of the falx cerebri attachment points and the measurement point in the septum pellucidum may be used to make a new/updated midline shift measurement.
  • the trained statistical classifier may be trained, as a multi-task model, such that its output may be used not only to identify one or more locations associated with at least one midline structure of the patient's brain, but also to segment the ventricles.
  • the measurement point to compare on to the midline lies on the septum pellucidum and it is therefore beneficial to use lateral ventricle labels to train a multi-task model, as such a model will identify the location of the septum pellucidum more accurately.
  • the symmetry or asymmetry of the segmented lateral ventricles may help to identify the location of the septum pellucidum more accurately.
  • Such a model may be trained if the training data includes lateral ventricle labels in addition to labels of the measurement point on the septum pellucidum and the falx cerebri attachment points.
  • the trained statistical classifier may be trained using training data comprising labeled scans of patients.
  • the classifier may be trained using training data comprising labeled scans of patients exhibiting midline shift (e.g., stroke patients and/or cancer patients).
  • the scans may be annotated manually by one or more clinical experts.
  • the annotations may include indications of the locations of the falx cerebri attachment points and measurement points on the septum pellucidum.
  • the annotations may include a line representing the midline (instead of or in addition to indications of the locations of the falx cerebri location points). If there is no midline shift in a particular scan, no indication of the midline (a line or attachment points) may be provided.
  • the length of the maximum diameter "A” and the length of the maximum orthogonal diameter "B” may be used to estimate the size (e.g., volume) of an abnormality in any other suitable way, as aspects of the technology described herein are not limited in this respect.
  • 1 ID (a right parietotemporal intraparenchymal hematoma).
  • the machine learning techniques described herein are used to identify the first diameter 1118 of the hemorrhage and the second diameter 1118 of the hemorrhage orthogonal to the first diameter.
  • the lengths of diameters 1118 and 1120 may be used to estimate the size of the hemorrhage shown in FIG. 1 IE (intraparenchymal hemorrhage in the right parietal lobe with mild surrounding edema).
  • FIG. 1 IE intraparenchymal hemorrhage in the right parietal lobe with mild surrounding edema.
  • FIG. 13 is a flowchart of an illustrative process 1300 for determining a degree of change in the size of an abnormality (e.g., a hemorrhage, a lesion, an edema, a stroke core, a stroke penumbra, and/or swelling) in a patient's brain , in accordance with some embodiments of the technology described herein.
  • an abnormality e.g., a hemorrhage, a lesion, an edema, a stroke core, a stroke penumbra, and/or swelling
  • the entirety of process 1300 may be performed while the patient is within a low-field MRI device, which may be of any suitable type described herein including, for example, any of the low-field MRI devices illustrated in FIGs. 3A-3G).
  • the neural network architectures described in FIGs. 14 and 15 may be applied to detecting changes in the size of any suitable type of abnormality, they are not limited to being used solely for detecting changes in size of a hemorrhage.
  • the output of the trained statistical classifier may be used to identify, at act 1306, initial value(s) of feature(s) indicative of the size of a hemorrhage in the patient's brain.
  • the features may be a first maximum diameter of the hemorrhage in a first direction and a second maximum diameter of the hemorrhage in a second direction, which is orthogonal to the first direction.
  • the values may indicate the initial lengths of the diameters and/or the initial endpoints of the diameters (from which the initial lengths may be derived).
  • the features may be corners of a bounding box bounding the perimeter of the hemorrhage and the initial values may be the locations of the corners.
  • the trained statistical classifier may be one of the neural networks described above with reference to FIGs. 9A-9C or FIG. 10.
  • Such a trained statistical classifier may identify point locations in MRI image data.
  • such a trained statistical classifier may be used to identify locations of endpoints of first and second orthogonal diameters of a hemorrhage.
  • such a trained statistical classifier may be used to identify locations of corners of a bounding box of a hemorrhage.
  • the trained statistical classifier may be a
  • deconvolutional layers may be varied.
  • process 1300 proceeds to decision block 1316, where it is determined whether to continue monitoring the size of the hemorrhage for any changes. This
  • the processor 1610 may execute one or more processor-executable instructions stored in one or more non-transitory computer-readable storage media (e.g., the memory 1620), which may serve as non-transitory computer-readable storage media storing processor-executable instructions for execution by the processor 1610.
  • non-transitory computer-readable storage media e.g., the memory 1620
  • inventive concepts may be embodied as a computer readable storage medium (or multiple computer readable storage media) (e.g., a computer memory, one or more floppy discs, compact discs, optical discs, magnetic tapes, flash memories, circuit configurations in Field Programmable Gate Arrays or other semiconductor devices, or other tangible computer storage medium) encoded with one or more programs that, when executed on one or more computers or other processors, perform methods that implement one or more of the various embodiments described above.
  • the computer readable medium or media can be transportable, such that the program or programs stored thereon can be loaded onto one or more different computers or other processors to implement various ones of the aspects described above.
  • computer readable media may be non-transitory media.
  • program or “software” are used herein in a generic sense to refer to any type of computer code or set of computer-executable instructions that can be employed to program a computer or other processor to implement various aspects as described above. Additionally, it should be appreciated that according to one aspect, one or more computer programs that when executed perform methods of the present disclosure need not reside on a single computer or processor, but may be distributed in a modular fashion among a number of different computers or processors to implement various aspects of the present disclosure.
  • Computer-executable instructions may be in many forms, such as program modules, executed by one or more computers or other devices.
  • program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types.
  • functionality of the program modules may be combined or distributed as desired in various embodiments.
  • data structures may be stored in computer-readable media in any suitable form.
  • data structures may be shown to have fields that are related through location in the data structure. Such relationships may likewise be achieved by assigning storage for the fields with locations in a computer-readable medium that convey relationship between the fields.
  • any suitable mechanism may be used to establish a relationship between information in fields of a data structure, including through the use of pointers, tags or other mechanisms that establish relationship between data elements.
  • the software code can be executed on any suitable processor or collection of processors, whether provided in a single computer or distributed among multiple computers.
  • At least one of A and B can refer, in one embodiment, to at least one, optionally including more than one, A, with no B present (and optionally including elements other than B); in another embodiment, to at least one, optionally including more than one, B, with no A present (and optionally including elements other than A); in yet another embodiment, to at least one, optionally including more than one, A, and at least one, optionally including more than one, B (and optionally including other elements); etc.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Surgery (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Neurology (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Condensed Matter Physics & Semiconductors (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Physiology (AREA)
  • Signal Processing (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Quality & Reliability (AREA)
  • Neurosurgery (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Computational Linguistics (AREA)
  • Fuzzy Systems (AREA)
  • Psychiatry (AREA)
PCT/US2017/062763 2016-11-22 2017-11-21 Systems and methods for automated detection in magnetic resonance images Ceased WO2018098141A1 (en)

Priority Applications (10)

Application Number Priority Date Filing Date Title
KR1020197016485A KR20190087455A (ko) 2016-11-22 2017-11-21 자기 공명 이미지들에서의 자동화된 검출을 위한 시스템들 및 방법들
MX2019005955A MX2019005955A (es) 2016-11-22 2017-11-21 Sistemas y metodos para deteccion automatizada en imagenes de resonancia magnetica.
CN201780071307.2A CN109983474A (zh) 2016-11-22 2017-11-21 用于磁共振图像中的自动检测的系统和方法
EP21205232.8A EP3968278A1 (en) 2016-11-22 2017-11-21 Systems and methods for automated detection in magnetic resonance images
AU2017363608A AU2017363608A1 (en) 2016-11-22 2017-11-21 Systems and methods for automated detection in magnetic resonance images
EP17872998.4A EP3545494B1 (en) 2016-11-22 2017-11-21 Automated detection in magnetic resonance images
CA3043038A CA3043038A1 (en) 2016-11-22 2017-11-21 Systems and methods for automated detection in magnetic resonance images
BR112019010225A BR112019010225A8 (pt) 2016-11-22 2017-11-21 Sistemas e métodos para detecção automatizada em imagens de ressonância magnética
JP2019527297A JP2019535424A (ja) 2016-11-22 2017-11-21 磁気共鳴画像における自動検出のためのシステムおよび方法
IL266748A IL266748A (en) 2016-11-22 2019-05-20 Systems and methods for automatic detection in magnetic resonance images

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201662425569P 2016-11-22 2016-11-22
US62/425,569 2016-11-22

Publications (1)

Publication Number Publication Date
WO2018098141A1 true WO2018098141A1 (en) 2018-05-31

Family

ID=62144878

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2017/062763 Ceased WO2018098141A1 (en) 2016-11-22 2017-11-21 Systems and methods for automated detection in magnetic resonance images

Country Status (12)

Country Link
US (7) US10416264B2 (https=)
EP (2) EP3968278A1 (https=)
JP (1) JP2019535424A (https=)
KR (1) KR20190087455A (https=)
CN (1) CN109983474A (https=)
AU (1) AU2017363608A1 (https=)
BR (1) BR112019010225A8 (https=)
CA (1) CA3043038A1 (https=)
IL (1) IL266748A (https=)
MX (1) MX2019005955A (https=)
TW (1) TWI704903B (https=)
WO (1) WO2018098141A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024182799A1 (en) * 2023-03-02 2024-09-06 Neuro42 Inc. A system and method of merging a co-operative mr-compatible robot and a low-field portable mri system

Families Citing this family (114)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102365543A (zh) 2009-01-16 2012-02-29 纽约大学 用全息视频显微术的自动实时粒子表征和三维速度计量
EP3068298B1 (en) 2013-11-15 2025-11-05 New York University Self calibrating parallel transmission by magnetic resonance spin dynamic fingerprinting
US9817093B2 (en) 2014-09-05 2017-11-14 Hyperfine Research, Inc. Low field magnetic resonance imaging methods and apparatus
US10813564B2 (en) 2014-11-11 2020-10-27 Hyperfine Research, Inc. Low field magnetic resonance methods and apparatus
CA3115673A1 (en) 2014-11-11 2016-05-19 Hyperfine Research, Inc. Pulse sequences for low field magnetic resonance
EP3218690B1 (en) 2014-11-12 2022-03-09 New York University Colloidal fingerprints for soft materials using total holographic characterization
HK1251301A1 (zh) 2015-04-13 2019-01-25 Hyperfine, Inc. 磁线圈供电方法和装置
HK1252007A1 (zh) 2015-05-12 2019-05-10 Hyperfine, Inc. 射频线圈方法和装置
US10561337B2 (en) * 2015-08-04 2020-02-18 University Of Virginia Patent Foundation Rapid 3D dynamic arterial spin labeling with a sparse model-based image reconstruction
CN108351288B (zh) 2015-09-18 2021-04-27 纽约大学 精密浆料中大杂质颗粒的全息检测和表征
MX2018011524A (es) 2016-03-22 2019-07-04 Hyperfine Res Inc Métodos y aparato para adaptar campos magnéticos.
US10670677B2 (en) * 2016-04-22 2020-06-02 New York University Multi-slice acceleration for magnetic resonance fingerprinting
TWI667487B (zh) 2016-09-29 2019-08-01 美商超精細研究股份有限公司 射頻線圈調諧方法及裝置
US10627464B2 (en) 2016-11-22 2020-04-21 Hyperfine Research, Inc. Low-field magnetic resonance imaging methods and apparatus
JP2019535424A (ja) 2016-11-22 2019-12-12 ハイパーファイン リサーチ，インコーポレイテッド 磁気共鳴画像における自動検出のためのシステムおよび方法
US10585153B2 (en) 2016-11-22 2020-03-10 Hyperfine Research, Inc. Rotatable magnet methods and apparatus for a magnetic resonance imaging system
US10539637B2 (en) 2016-11-22 2020-01-21 Hyperfine Research, Inc. Portable magnetic resonance imaging methods and apparatus
US10390727B2 (en) * 2017-04-21 2019-08-27 The Charles Stark Draper Laboratory, Inc. Apparatus and method for imaging currents using nanoparticles and low-field magnetic resonance imaging (MRI)
US10753997B2 (en) * 2017-08-10 2020-08-25 Siemens Healthcare Gmbh Image standardization using generative adversarial networks
JP7246903B2 (ja) * 2017-12-20 2023-03-28 キヤノンメディカルシステムズ株式会社 医用信号処理装置
US10365340B1 (en) * 2018-03-01 2019-07-30 Siemens Medical Solutions Usa, Inc. Monitoring dynamics of patient brain state during neurosurgical procedures
MX2020011072A (es) 2018-04-20 2020-11-06 Hyperfine Res Inc Proteccion desplegable para dispositivos portatiles de formacion de imagenes de resonancia magnetica.
US20190351261A1 (en) * 2018-05-18 2019-11-21 Yoav Levy Selective resampling during non-invasive therapy
CA3098461A1 (en) 2018-05-21 2019-11-28 Hyperfine Research, Inc. B0 magnet methods and apparatus for a magnetic resonance imaging system
MX2020012542A (es) 2018-05-21 2021-02-16 Hyperfine Res Inc Cadena de señal de bobina de radiofrecuencia para un sistema de resonancia magnética (mri) de campo bajo.
TW202015621A (zh) 2018-07-19 2020-05-01 美商超精細研究股份有限公司 在磁共振成像中患者定位之方法及設備
CN113795764B (zh) 2018-07-30 2025-03-25 海珀菲纳股份有限公司 用于磁共振图像重建的深度学习技术
TW202012951A (zh) 2018-07-31 2020-04-01 美商超精細研究股份有限公司 低場漫射加權成像
WO2020028228A1 (en) 2018-07-31 2020-02-06 Hyperfine Research, Inc. Medical imaging device messaging service
EP3833253A4 (en) * 2018-08-12 2022-05-04 The Trustees of Columbia University in the City of New York SYSTEM, METHOD AND COMPUTER-ACCESSIBLE MEDIUM FOR FINGERPRINTING TISSUE
EP3833243A4 (en) * 2018-08-12 2022-04-27 The Trustees of Columbia University in the City of New York SYSTEM, METHOD AND COMPUTER-ACCESSIBLE MEDIA FOR MAGNETIC RESONANCE CONTROLLED AUTONOMOUS SCANNER
CN113557526B (zh) 2018-08-15 2025-11-14 海珀菲纳股份有限公司 磁共振成像方法、系统和计算机程序产品
NL2021559B1 (en) 2018-09-04 2020-04-30 Aidence B V Determination of a growth rate of an object in 3D data sets using deep learning
WO2020056274A1 (en) * 2018-09-14 2020-03-19 The Johns Hopkins University Machine learning processing of contiguous slice image data
KR102812888B1 (ko) 2018-09-14 2025-05-27 10250929 캐나다 인코포레이티드 대사 산물 수준의 생체 내 및 비-침습적 측정을 위한 방법 및 시스템
JP7071523B2 (ja) * 2018-09-28 2022-05-19 富士フイルム株式会社 脳のアトラス作成装置、方法及びプログラム
US11436495B2 (en) * 2018-10-02 2022-09-06 Insitu, Inc. a subsidiary of The Boeing Company Change detection in digital images
US11037030B1 (en) * 2018-10-29 2021-06-15 Hrl Laboratories, Llc System and method for direct learning from raw tomographic data
US10799183B2 (en) * 2018-11-07 2020-10-13 General Electric Company Methods and systems for whole body imaging
US10803987B2 (en) * 2018-11-16 2020-10-13 Elekta, Inc. Real-time motion monitoring using deep neural network
CN111223103B (zh) * 2018-11-23 2023-11-21 佳能医疗系统株式会社 医用图像诊断装置以及医用摄像装置
EP3663785A1 (en) * 2018-12-07 2020-06-10 Koninklijke Philips N.V. Functional magnetic resonance imaging artifact removal by means of an artificial neural network
US11948676B2 (en) 2018-12-14 2024-04-02 The Board Of Trustees Of The Leland Stanford Junior University Qualitative and quantitative MRI using deep learning
US10832392B2 (en) * 2018-12-19 2020-11-10 Siemens Healthcare Gmbh Method, learning apparatus, and medical imaging apparatus for registration of images
CA3122087A1 (en) 2018-12-19 2020-06-25 Hyperfine Research, Inc. System and methods for grounding patients during magnetic resonance imaging
EP3903117B1 (en) 2018-12-28 2024-06-26 Hyperfine, Inc. Correcting for hysteresis in magnetic resonance imaging
CN111476938B (zh) * 2019-01-24 2023-04-28 中科晶源微电子技术（北京）有限公司 用于周期性样式的异常检测
US12002203B2 (en) 2019-03-12 2024-06-04 Bayer Healthcare Llc Systems and methods for assessing a likelihood of CTEPH and identifying characteristics indicative thereof
CA3132976A1 (en) 2019-03-12 2020-09-17 Christopher Thomas Mcnulty Systems and methods for magnetic resonance imaging of infants
JP2022526718A (ja) 2019-03-14 2022-05-26 ハイパーファイン，インコーポレイテッド 空間周波数データから磁気共鳴画像を生成するための深層学習技術
BR112021020493A2 (pt) 2019-04-26 2021-12-07 Hyperfine Inc Técnicas para o controle dinâmico de um sistema de imagem de ressonância magnética
WO2020223434A1 (en) * 2019-04-30 2020-11-05 The Trustees Of Columbia University In The City Of New York Classifying neurological disease status using deep learning
JP2022531485A (ja) 2019-05-07 2022-07-06 ハイパーファイン，インコーポレイテッド 乳児の磁気共鳴画像のためのシステム、装置、及び方法
US11967070B2 (en) * 2019-05-13 2024-04-23 The General Hospital Corporation Systems and methods for automated image analysis
WO2020262683A1 (ja) 2019-06-28 2020-12-30 富士フイルム株式会社 医用画像処理装置、方法およびプログラム
CN110346743B (zh) * 2019-07-22 2021-09-14 上海东软医疗科技有限公司 一种磁共振弥散加权成像方法和装置
CN110472670B (zh) * 2019-07-24 2022-03-01 上海联影智能医疗科技有限公司 图像中线检测方法、计算机设备和存储介质
US11698430B2 (en) 2019-08-15 2023-07-11 Hyperfine Operations, Inc. Eddy current mitigation systems and methods
US12262986B2 (en) * 2019-08-22 2025-04-01 Wisconsin Alumni Research Foundation Lesion volume measurements system
JP7535575B2 (ja) 2019-09-18 2024-08-16 バイエル、アクチエンゲゼルシャフト 組織特性を予測、予想、および／または査定するためのシステム、方法、およびコンピュータプログラム製品
JP2022548716A (ja) 2019-09-18 2022-11-21 バイエル、アクチエンゲゼルシャフト 肝臓のｍｒｉ画像の生成
WO2021052896A1 (de) 2019-09-18 2021-03-25 Bayer Aktiengesellschaft Vorhersage von mrt-aufnahmen durch ein mittels überwachten lernens trainiertes vorhersagemodell
US20210093278A1 (en) * 2019-09-30 2021-04-01 GE Precision Healthcare LLC Computed tomography medical imaging intracranial hemorrhage model
EP4042176B1 (en) 2019-10-08 2025-04-30 Hyperfine Operations, Inc. System and methods for detecting electromagnetic interference in patients during magnetic resonance imaging
US20210124001A1 (en) 2019-10-25 2021-04-29 Hyperfine Research, Inc. Systems and methods for detecting patient motion during magnetic resonance imaging
EP4644938A3 (en) 2019-10-25 2025-12-31 Hyperfine Operations, Inc. ARTIFACT REDUCTION IN MAGNETIC RESONANCE IMAGING
US11543338B2 (en) 2019-10-25 2023-01-03 New York University Holographic characterization of irregular particles
WO2021108216A1 (en) 2019-11-27 2021-06-03 Hyperfine Research, Inc. Techniques for noise suppression in an environment of a magnetic resonance imaging system
CN110956636A (zh) * 2019-11-28 2020-04-03 北京推想科技有限公司 一种图像处理方法及装置
US11415651B2 (en) 2019-12-10 2022-08-16 Hyperfine Operations, Inc. Low noise gradient amplification components for MR systems
USD912822S1 (en) 2019-12-10 2021-03-09 Hyperfine Research, Inc. Frame for magnets in magnetic resonance imaging
CN115552269B (zh) 2019-12-10 2026-03-13 海珀菲纳运营有限公司 用于磁共振成像的具有非铁磁框架的永磁体装配件
US11422213B2 (en) 2019-12-10 2022-08-23 Hyperfine Operations, Inc. Ferromagnetic frame for magnetic resonance imaging
USD932014S1 (en) 2019-12-10 2021-09-28 Hyperfine, Inc. Frame for magnets in magnetic resonance imaging
EP3835803B1 (en) * 2019-12-13 2024-03-27 Siemens Healthineers AG System and method for estimating a relative substance composition of a portion of a body of a patient
WO2021167124A1 (ko) * 2020-02-19 2021-08-26 서울대학교 산학협력단 Mri 데이터 및 추가 정보를 이용하는 변환 네트워크부를 포함하는 mri 데이터 변환장치 및 이를 이용한 mri 데이터 변환방법
DE102020202505A1 (de) 2020-02-27 2021-09-02 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren zum Betrieb einer Magnetresonanzmessvorrichtung
US11948302B2 (en) 2020-03-09 2024-04-02 New York University Automated holographic video microscopy assay
DE102020203526A1 (de) * 2020-03-19 2021-09-23 Siemens Healthcare Gmbh Deformationsmodell für ein Gewebe
US12394058B2 (en) 2020-04-03 2025-08-19 Bayer Aktiengesellschaft Generation of radiological images
CN111611218A (zh) * 2020-04-24 2020-09-01 武汉大学 一种基于深度学习的分布式异常日志自动识别方法
CN111563903B (zh) * 2020-04-26 2021-05-28 北京航空航天大学 一种基于深度学习的mri全脑组织分割方法及系统
CN111583212B (zh) * 2020-04-29 2021-11-30 上海杏脉信息科技有限公司 脑部中线移位的确定方法及装置
CN111769844B (zh) * 2020-06-24 2022-08-16 中国电子科技集团公司第三十六研究所 一种单通道同频干扰消除方法和装置
CN111862014A (zh) * 2020-07-08 2020-10-30 深圳市第二人民医院(深圳市转化医学研究院) 一种基于左右侧脑室分割的alvi自动测量方法及装置
DE102020209783A1 (de) * 2020-08-04 2022-02-10 Julius-Maximilians-Universität Würzburg Verfahren zur Aufnahme eines Magnetresonanzbilddatensatzes, Datenträger, Computerprogrammprodukt sowie Magnetresonanzanlage
CN111968103B (zh) * 2020-08-27 2023-05-09 中冶赛迪信息技术(重庆)有限公司 一种钢卷间距检测方法、系统、介质及电子终端
US11861828B2 (en) * 2020-09-01 2024-01-02 Siemens Healthcare Gmbh Automated estimation of midline shift in brain ct images
CN116034398A (zh) * 2020-09-03 2023-04-28 基因泰克公司 用于病变分割的具有注意力的多臂机器学习模型
DE102020213900A1 (de) * 2020-09-30 2022-03-31 Siemens Healthcare Gmbh Verfahren zu einem Bereitstellen einer Positionsinformation einer lokalen Hochfrequenzspule
CN112132878B (zh) * 2020-11-03 2024-04-05 贵州大学 基于卷积神经网络的端到端大脑核磁共振图像配准方法
CN112561055B (zh) * 2020-12-09 2023-11-07 北京交通大学 基于双线性时频分析及卷积神经网络的电磁骚扰辨识方法
WO2022132959A1 (en) * 2020-12-15 2022-06-23 The Truestees Of Columbia University In The City Of New York Multi-contrast denoising of magnetic resonance images using native noise structure
JP7582873B2 (ja) * 2021-01-20 2024-11-13 キヤノンメディカルシステムズ株式会社 磁気共鳴イメージング装置
KR102289648B1 (ko) * 2021-02-03 2021-08-18 주식회사 휴런 의료 영상 기반 허혈성 뇌졸중 검출 및 형태 분류 방법, 장치 및 시스템
US12602754B2 (en) * 2021-03-04 2026-04-14 Rensselaer Polytechnic Institute Dynamic imaging and motion artifact reduction through deep learning
TWI790572B (zh) 2021-03-19 2023-01-21 宏碁智醫股份有限公司 影像相關的檢測方法及檢測裝置
CN113256705A (zh) * 2021-03-23 2021-08-13 杭州依图医疗技术有限公司 颅脑图像的处理方法、显示方法及处理装置
EP4075157A1 (en) * 2021-04-14 2022-10-19 Siemens Healthcare GmbH Method for correcting object specific inhomogeneities in an mr imaging system
US11842492B2 (en) * 2021-04-16 2023-12-12 Natasha IRONSIDE Cerebral hematoma volume analysis
CN113822323B (zh) * 2021-07-21 2025-12-19 腾讯科技（深圳）有限公司 脑部扫描图像的识别处理方法、装置、设备及存储介质
CN113876313B (zh) * 2021-10-19 2024-05-14 江苏麦格思频仪器有限公司 一种具有降噪功能的前置放大器的肢体磁共振系统
CN113947731B (zh) * 2021-12-21 2022-07-22 成都中轨轨道设备有限公司 一种基于接触网安全巡检的异物识别方法及系统
US12501225B2 (en) 2022-01-02 2025-12-16 Poltorak Technologies Llc Bluetooth enabled intercom with hearing aid functionality
CN114511031B (zh) * 2022-02-15 2025-07-01 重庆大学 基于生成对抗网络的电子鼻数据校正方法
CN114708240B (zh) * 2022-04-18 2024-11-22 杭州脉流科技有限公司 基于平扫ct的自动化aspects评分方法、计算机设备、可读存储介质和程序产品
CN115880246B (zh) * 2022-12-06 2026-01-02 深圳市人工智能与机器人研究院 一种电磁检测装置，检测方法及存储介质
CN116982959A (zh) * 2023-06-26 2023-11-03 上海深至信息科技有限公司 一种用于手术室的磁共振成像方法及系统
CN117609881B (zh) * 2023-11-29 2024-04-30 阿童木(广州)智能科技有限公司 一种基于人工智能的金属重叠检测方法及系统
CN120267399B (zh) * 2023-12-28 2025-12-26 华科精准(北京)医疗设备股份有限公司 一种磁共振设备扫描参数矫正方法、消融装置及消融系统
TWI870195B (zh) * 2024-01-05 2025-01-11 臺北醫學大學 用於早期偵測缺血性腦中風病人的腦梗塞核心之影像處理系統及其方法
KR20250113241A (ko) 2024-01-18 2025-07-25 단국대학교 산학협력단 뇌 중심선 편향 정보 분석 시스템 및 방법
WO2025231450A1 (en) * 2024-05-03 2025-11-06 Navarad Corporation Alignment of 3d image data using edges and silhouettes
KR102866355B1 (ko) * 2024-07-15 2025-10-01 한국기초과학지원연구원 고온초전도 자석에서의 자기장 공간균일도 개선장치 및 개선방법

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050245810A1 (en) * 2004-04-28 2005-11-03 Siemens Corporate Research Inc. Method of registering pre-operative high field closed magnetic resonance images with intra-operative low field open interventional magnetic resonance images
US20120184840A1 (en) * 2009-04-07 2012-07-19 Kayvan Najarian Automated Measurement of Brain Injury Indices Using Brain CT Images, Injury Data, and Machine Learning
US20130204115A1 (en) * 2010-06-01 2013-08-08 Synarc Inc. Computer based analysis of mri images
US20130279784A1 (en) * 2010-12-21 2013-10-24 Renishaw (Ireland) Limited Method and apparatus for analysing images
US20130296660A1 (en) * 2012-05-02 2013-11-07 Georgia Health Sciences University Methods and systems for measuring dynamic changes in the physiological parameters of a subject
US20160025832A1 (en) * 2013-03-15 2016-01-28 Cameron Piron System and method for magnetic resonance image acquisition
US20160110904A1 (en) 2014-10-21 2016-04-21 Samsung Electronics Co., Ltd. Magnetic resonance imaging (mri) apparatus and method of processing mr image
US20160140435A1 (en) * 2014-11-14 2016-05-19 Google Inc. Generating natural language descriptions of images

Family Cites Families (334)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3622869A (en) 1967-06-28 1971-11-23 Marcel J E Golay Homogenizing coils for nmr apparatus
US3735306A (en) 1970-10-22 1973-05-22 Varian Associates Magnetic field shim coil structure utilizing laminated printed circuit sheets
US4621299A (en) 1982-11-05 1986-11-04 General Kinetics Inc. High energy degausser
JPS6063972A (ja) 1983-09-17 1985-04-12 Sumitomo Electric Ind Ltd クライオスタツト
US4595899A (en) 1984-07-06 1986-06-17 The Board Of Trustees Of The Leland Stanford Junior University Magnetic structure for NMR applications and the like
JPS6197806A (ja) 1984-10-18 1986-05-16 Yokogawa Medical Syst Ltd Ｎｍｒ画像装置に用いられるマグネツト部の冷却装置
US4638252A (en) 1984-12-21 1987-01-20 General Electric Company Circuit for detecting RF coil assembly position in an MR scanner
US4680545A (en) 1985-01-04 1987-07-14 General Electric Company Method for reduction of acoustical noise generated by magnetic field gradient pulses
US4668915A (en) 1985-03-15 1987-05-26 Honda Giken Kogyo Kabushiki Kaisha Non-uniform field magnetic resonance dual patient imaging system
US5038785A (en) 1985-08-09 1991-08-13 Picker International, Inc. Cardiac and respiratory monitor with magnetic gradient noise elimination
US4675609A (en) 1985-09-18 1987-06-23 Fonar Corporation Nuclear magnetic resonance apparatus including permanent magnet configuration
JP2588700B2 (ja) 1986-09-05 1997-03-05 株式会社 日立メディコ 核磁気共鳴イメ−ジング装置
US4770182A (en) 1986-11-26 1988-09-13 Fonar Corporation NMR screening method
FR2609206B1 (fr) 1986-12-30 1992-02-14 Thomson Cgr Dispositif correcteur par elements magnetiques d'inhomogeneites du champ magnetique dans un aimant
JPS63311945A (ja) 1987-06-12 1988-12-20 Matsushita Electric Ind Co Ltd 核磁気共鳴断層像撮像装置
US5203332A (en) 1987-06-23 1993-04-20 Nycomed Imaging As Magnetic resonance imaging
JPS6464637A (en) 1987-09-07 1989-03-10 Hitachi Medical Corp Nuclear magnetic resonance imaging apparatus
EP0307516A1 (en) 1987-09-18 1989-03-22 Koninklijke Philips Electronics N.V. Magnetic resonance imaging apparatus with eddy-current disturbances correction system
JPH0164637U (https=) 1987-10-19 1989-04-25
JPH01242057A (ja) 1988-03-23 1989-09-27 Toshiba Corp 磁気共鳴イメージング装置
US4893082A (en) 1989-02-13 1990-01-09 Letcher Iii John H Noise suppression in magnetic resonance imaging
US5134374A (en) 1989-06-01 1992-07-28 Applied Superconetics Magnetic field control apparatus
JPH03188831A (ja) 1989-12-20 1991-08-16 Hitachi Medical Corp 磁気共鳴イメージング装置
US5252924A (en) 1991-11-18 1993-10-12 Sumitomo Special Metals Co., Ltd. Magnetic field generating apparatus for MRI
FI86506C (fi) 1990-05-29 1992-09-10 Instrumentarium Oy Avbildningsfoerfarande.
US5153546A (en) 1991-06-03 1992-10-06 General Electric Company Open MRI magnet
JP2561591B2 (ja) 1991-12-27 1996-12-11 住友特殊金属株式会社 Ｍｒｉ用磁界発生装置
US5382904A (en) 1992-04-15 1995-01-17 Houston Advanced Research Center Structured coil electromagnets for magnetic resonance imaging and method for fabricating the same
JPH05344960A (ja) 1992-06-15 1993-12-27 Hitachi Ltd 磁気共鳴検査装置
US6023165A (en) 1992-09-28 2000-02-08 Fonar Corporation Nuclear magnetic resonance apparatus and methods of use and facilities for incorporating the same
US5291137A (en) 1992-11-02 1994-03-01 Schlumberger Technology Corporation Processing method and apparatus for processing spin echo in-phase and quadrature amplitudes from a pulsed nuclear magnetism tool and producing new output data to be recorded on an output record
DE69316837T2 (de) 1992-11-10 1998-07-30 Koninkl Philips Electronics Nv Apparat mittels magnetischer Resonanz mit Lärmunterdrückung
US5490509A (en) 1993-03-18 1996-02-13 The Regents Of The University Of California Method and apparatus for MRI using selectively shaped image volume of homogeneous NMR polarizing field
US5483158A (en) 1993-10-21 1996-01-09 The Regents Of The University Of California Method and apparatus for tuning MRI RF coils
US5423315A (en) 1993-11-22 1995-06-13 Picker International, Inc. Magnetic resonance imaging system with thin cylindrical uniform field volume and moving subjects
US5390673A (en) 1994-01-14 1995-02-21 Cordata, Incorporated Magnetic resonance imaging system
US5463364A (en) 1994-04-13 1995-10-31 Bruker Analytische Messtechnik Gmbh Magnet system for NMR tomography
DE4422781C1 (de) 1994-06-29 1996-02-01 Siemens Ag Aktiv geschirmte planare Gradientenspule für Polplattenmagnete
JPH0831635A (ja) 1994-07-08 1996-02-02 Sumitomo Special Metals Co Ltd Ｍｒｉ用磁界発生装置
DE4424580C2 (de) 1994-07-13 1996-09-05 Bruker Analytische Messtechnik NMR-Scheibenspule
US5451878A (en) 1994-07-15 1995-09-19 General Electric Company Non-resonant gradient field accelerator
AU4408296A (en) 1994-11-28 1996-06-19 Analogic Corporation Ups for medical imaging system
JP3705861B2 (ja) 1996-03-21 2005-10-12 株式会社日立メディコ 超電導磁石装置及びその着磁調整方法
US5864236A (en) 1996-07-05 1999-01-26 Toshiba America Mri, Inc. Open configuration MRI magnetic flux path
US6150911A (en) 1996-07-24 2000-11-21 Odin Technologies Ltd. Yoked permanent magnet assemblies for use in medical applications
US5900793A (en) 1997-07-23 1999-05-04 Odin Technologies Ltd Permanent magnet assemblies for use in medical applications
US6411187B1 (en) 1997-07-23 2002-06-25 Odin Medical Technologies, Ltd. Adjustable hybrid magnetic apparatus
US6157278A (en) 1997-07-23 2000-12-05 Odin Technologies Ltd. Hybrid magnetic apparatus for use in medical applications
AU9364698A (en) 1997-09-25 1999-04-12 Odin Technologies Ltd. Magnetic apparatus for mri
US5936502A (en) 1997-12-05 1999-08-10 Picker Nordstar Inc. Magnet coils for MRI
US6235409B1 (en) 1997-12-17 2001-05-22 Alcoa Inc. Aluminum laminate
US5877665A (en) 1997-12-17 1999-03-02 General Electric Company Thermally passive magnet mounting system for an MRI signa profile magnet in mobile trailer van
US6163154A (en) 1997-12-23 2000-12-19 Magnetic Diagnostics, Inc. Small scale NMR spectroscopic apparatus and method
US6011396A (en) 1998-01-02 2000-01-04 General Electric Company Adjustable interventional magnetic resonance imaging magnet
WO1999040593A1 (en) 1998-02-09 1999-08-12 Odin Medical Technologies Ltd A method for designing open magnets and open magnetic apparatus for use in mri/mrt probes
CA2324269C (en) * 1998-03-18 2007-06-12 Magnetic Imaging Technologies, Inc. Mr methods for imaging pulmonary and cardiac vasculature and evaluating blood flow using dissolved polarized 129xe
US6029081A (en) 1998-03-19 2000-02-22 Picker International, Inc. Movable magnets for magnetic resonance surgery
DE69939216D1 (de) 1998-05-04 2008-09-11 Clad Metals Llc Verfahren zur herstellung eines fünflagenverbandes mit kupferkern und kochgeschirr
US6131690A (en) 1998-05-29 2000-10-17 Galando; John Motorized support for imaging means
JP3034841B2 (ja) 1998-06-05 2000-04-17 ジーイー横河メディカルシステム株式会社 Ｍｒｉ用コイル、クレードル及びｍｒｉ装置
US6417797B1 (en) 1998-07-14 2002-07-09 Cirrus Logic, Inc. System for A multi-purpose portable imaging device and methods for using same
IT1305971B1 (it) 1998-08-31 2001-05-21 Esaote Spa Macchina per il rilevamento di immagini in risonanza magneticanucleare del tipo dedicato al rilevamento d'immagini di limitate
IT1304768B1 (it) 1998-10-05 2001-03-29 Esaote Spa Lettino porta paziente o simili, e macchina, in particolare macchinaper il rilevamento d'immagini in risonanza magnetica nucleare in
US7529575B2 (en) 1998-10-05 2009-05-05 Esaote S.P.A. Nuclear magnetic resonance imaging device
US6259252B1 (en) 1998-11-24 2001-07-10 General Electric Company Laminate tile pole piece for an MRI, a method manufacturing the pole piece and a mold bonding pole piece tiles
US6166544A (en) 1998-11-25 2000-12-26 General Electric Company MR imaging system with interactive image contrast control
US6396266B1 (en) 1998-11-25 2002-05-28 General Electric Company MR imaging system with interactive MR geometry prescription control
JP3817383B2 (ja) 1999-02-24 2006-09-06 株式会社日立製作所 Ｍｒｉ装置
JP2000287950A (ja) 1999-04-07 2000-10-17 Ge Yokogawa Medical Systems Ltd 磁場安定化方法、磁場発生装置および磁気共鳴撮像装置
US6317618B1 (en) 1999-06-02 2001-11-13 Odin Technologies Ltd. Transportable intraoperative magnetic resonance imaging apparatus
US6764858B2 (en) 1999-09-29 2004-07-20 Pharmacia & Upjohn Company Methods for creating a compound library
US7313429B2 (en) 2002-01-23 2007-12-25 Stereotaxis, Inc. Rotating and pivoting magnet for magnetic navigation
US7019610B2 (en) 2002-01-23 2006-03-28 Stereotaxis, Inc. Magnetic navigation system
GB2355075A (en) 1999-10-09 2001-04-11 Marconi Electronic Syst Ltd MRI apparatus with additional data correction coil
JP2001137212A (ja) 1999-11-11 2001-05-22 Hitachi Medical Corp 静磁場発生装置及びそれを用いた磁気共鳴イメージング装置
EP1666910B1 (en) 1999-11-16 2009-03-11 Hitachi Metals, Ltd. Magnetic-field generator comprising a pole-piece unit
US6262576B1 (en) 1999-11-16 2001-07-17 Picker International, Inc. Phased array planar gradient coil set for MRI systems
CN1217201C (zh) 2000-01-19 2005-08-31 千年技术公司 C形磁共振成象系统
GB0007018D0 (en) 2000-03-22 2000-05-10 Akguen Ali Magnetic resonance imaging apparatus and method
US6845262B2 (en) 2000-03-29 2005-01-18 The Brigham And Women's Hospital, Inc. Low-field MRI
US6998841B1 (en) 2000-03-31 2006-02-14 Virtualscopics, Llc Method and system which forms an isotropic, high-resolution, three-dimensional diagnostic image of a subject from two-dimensional image data scans
JP4317646B2 (ja) 2000-06-26 2009-08-19 独立行政法人理化学研究所 核磁気共鳴装置
US6933722B2 (en) 2000-07-05 2005-08-23 Hitachi Medical Corporation Magnetic resonance imaging device and gradient magnetic field coil used for it
US6294972B1 (en) 2000-08-03 2001-09-25 The Mcw Research Foundation, Inc. Method for shimming a static magnetic field in a local MRI coil
EP1355571A2 (en) 2000-08-15 2003-10-29 The Regents Of The University Of California Method and apparatus for reducing contamination of an electrical signal
US20030011451A1 (en) 2000-08-22 2003-01-16 Ehud Katznelson Permanent magnet assemblies for use in medical applications
JP3728199B2 (ja) 2000-11-14 2005-12-21 株式会社日立メディコ 磁気共鳴イメージング装置
US6677752B1 (en) 2000-11-20 2004-01-13 Stereotaxis, Inc. Close-in shielding system for magnetic medical treatment instruments
US6529000B2 (en) 2000-12-29 2003-03-04 Ge Medical Systems Global Technology Company, Llc Method and system for processing magnetic resonance signals to remove transient spike noise
US20020084782A1 (en) 2001-01-04 2002-07-04 Warren Guthrie Noise detector and suppressor for magnetic resonance imaging equipment
EP1356421B1 (en) * 2001-01-23 2009-12-02 Health Discovery Corporation Computer-aided image analysis
US6662434B2 (en) 2001-04-03 2003-12-16 General Electric Company Method and apparatus for magnetizing a permanent magnet
US6518867B2 (en) 2001-04-03 2003-02-11 General Electric Company Permanent magnet assembly and method of making thereof
US6611702B2 (en) 2001-05-21 2003-08-26 General Electric Company Apparatus for use in neonatal magnetic resonance imaging
ITSV20010020A1 (it) 2001-06-08 2002-12-08 Esaote Spa Macchina per l'acquisizione di immagini della zona interna di un corpo in particolare per l'acquisizione di immagini diagnostiche
ITSV20010017A1 (it) 2001-05-28 2002-11-28 Esaote Spa Dispositivo per il rilevamento d'immagini in risonanza magnetica nucleare
JP2003024296A (ja) 2001-07-04 2003-01-28 Ge Medical Systems Global Technology Co Llc 静磁界調整方法およびｍｒｉ装置
US7734075B2 (en) 2001-10-04 2010-06-08 Siemens Medical Solutions Usa, Inc. Contrast-invariant registration of cardiac and renal magnetic resonance perfusion images
US8272582B2 (en) * 2001-11-26 2012-09-25 Gillette Thomas D Systems and methods for producing ozonated water on demand
EP1458287A1 (en) 2001-12-18 2004-09-22 MRI Devices Corporation Method and apparatus for noise tomography
WO2003067267A2 (en) 2002-02-06 2003-08-14 The Regents Of The University Of California Squid detected nmr and mri at ultralow fields
US20050092395A1 (en) 2002-02-15 2005-05-05 Masaaki Aoki Magnetic field generator and its manufacturing method
ITSV20020014A1 (it) 2002-04-09 2003-10-09 Esaote Spa Metodo e dispositivo per la compensazione di campi magnetici di disturbo in volumi di spazio e macchina per il rilevamento di immagini in ri
US7130675B2 (en) 2002-06-28 2006-10-31 Tristan Technologies, Inc. High-resolution magnetoencephalography system and method
JP2004065398A (ja) 2002-08-02 2004-03-04 Hitachi Medical Corp 永久磁石と電磁石から成るハイブリット型磁石を有する磁気共鳴イメージング装置
US7215231B1 (en) 2002-08-16 2007-05-08 Fonar Corporation MRI system
JP2004081264A (ja) 2002-08-23 2004-03-18 Hitachi Medical Corp 遠隔医療システム及び制御モダリティーの遠隔操作装置
EP3067070A1 (en) * 2002-09-24 2016-09-14 The Government of the United States of America as represented by the Secretary of the Department of Health and Human Services Method for convection enhanced delivery of therapeutic agents
FI113615B (fi) 2002-10-17 2004-05-31 Nexstim Oy Kallonmuodon ja sisällön kolmiulotteinen mallinnusmenetelmä
ITSV20020057A1 (it) 2002-11-28 2004-05-29 Esaote Spa Combinazione di macchina per rilevamento di immagini in risonanza nucleare e lettino porta paziente
JP2004187945A (ja) 2002-12-11 2004-07-08 Ge Medical Systems Global Technology Co Llc 医用イメージング装置及び医用イメージングシステム
US20060077027A1 (en) 2003-02-10 2006-04-13 Neomax Co., Ltd. Magnetic field-producing device
ES2303311T3 (es) 2003-02-24 2008-08-01 Basf Se Polimeros que contienen grupos de acido fosforico y/o acido fosfonico para el tratamiento de superficies metalicas.
US6788063B1 (en) 2003-02-26 2004-09-07 Ge Medical Systems Technology Company, Llc Method and system for improving transient noise detection
US6819108B2 (en) 2003-03-21 2004-11-16 General Electric Company Method of magnetic field controlled shimming
WO2004104613A1 (en) 2003-05-20 2004-12-02 Koninklijke Philips Electronics N.V. Digital magnetic resonance gradient pre-emphasis
US20070293753A1 (en) 2003-07-07 2007-12-20 Abdel-Monem El-Sharkawy Radiometric Approach to Temperature Monitoring Using a Magnetic Resonance Scanner
CA2533161C (en) 2003-07-24 2013-04-23 Dune Medical Devices Ltd. Method and apparatus for examining a substance,particularly tissue, to characterize its type
US8203341B2 (en) 2003-09-19 2012-06-19 Xbo Medical Systems Co., Ltd. Cylindrical bi-planar gradient coil for MRI
US7423431B2 (en) 2003-09-29 2008-09-09 General Electric Company Multiple ring polefaceless permanent magnet and method of making
JP2005118098A (ja) 2003-10-14 2005-05-12 Hitachi Medical Corp 磁気共鳴イメージング装置
EP1689484B1 (en) 2003-11-26 2012-10-31 Acist Medical Systems, Inc. Device, method, and computer program product for dispensing media as part of a medical procedure
JP2005237501A (ja) 2004-02-25 2005-09-08 Shin Etsu Chem Co Ltd 磁気回路および磁気回路磁界調整方法
CN1669525A (zh) 2004-03-19 2005-09-21 西门子公司 带有一定位单元的磁共振设备
US7126333B2 (en) 2004-04-19 2006-10-24 Baker Hughes Incorporated Method and apparatus for correcting ringing in NMR signals
ITSV20040020A1 (it) 2004-05-07 2004-08-07 Esaote Spa Struttura magnetica per macchine mri e macchina mri
WO2005116676A1 (en) 2004-05-25 2005-12-08 Hvidovre Hospital Encoding and transmission of signals as rf signals for detection using an mr apparatus
JP2005344960A (ja) 2004-06-01 2005-12-15 Matsushita Electric Ind Co Ltd オイルセパレータ
ITSV20040032A1 (it) 2004-08-05 2004-11-05 Esaote Spa Metodo e sonda per la compensazione di campi magnetici di disturbo in volumi di spazio in particolare nelle macchine per il rilevamento di immagini in risonanza magnetica nucleare
US20060255938A1 (en) 2004-08-09 2006-11-16 Van Den Brink Johan S Saftey provisions for surgical tools and mri
GB0421266D0 (en) 2004-09-24 2004-10-27 Quantx Wellbore Instrumentatio Measurement apparatus and method
US8626342B2 (en) 2004-10-27 2014-01-07 Acist Medical Systems, Inc. Data collection device, system, method, and computer program product for collecting data related to the dispensing of contrast media
US7187169B2 (en) 2004-11-03 2007-03-06 The Regents Of The University Of California NMR and MRI apparatus and method
US8014867B2 (en) 2004-12-17 2011-09-06 Cardiac Pacemakers, Inc. MRI operation modes for implantable medical devices
GB0503622D0 (en) 2005-02-22 2005-03-30 Siemens Magnet Technology Ltd Shielding for mobile MRI systems
US7466133B2 (en) 2005-03-01 2008-12-16 General Electric Company Systems, methods and apparatus of a magnetic resonance imaging system to produce a stray field suitable for interventional use
US20060241333A1 (en) 2005-04-21 2006-10-26 Ksm, Inc. Electromagnetic treatment device
US7307423B2 (en) 2005-05-05 2007-12-11 Wisconsin A.Umni Research Foundation Magnetic resonance elastography using multiple drivers
US8614575B2 (en) 2005-06-17 2013-12-24 The Regents Of The University Of California NMR, MRI, and spectroscopic MRI in inhomogeneous fields
US8514043B2 (en) 2005-09-14 2013-08-20 General Electric Company Systems and methods for passively shielding a magnetic field
US7835785B2 (en) 2005-10-04 2010-11-16 Ascension Technology Corporation DC magnetic-based position and orientation monitoring system for tracking medical instruments
US7642782B2 (en) 2005-10-27 2010-01-05 Koninklijke Philips Electronics N.V. Active decoupling of transmitters in MRI
GB2435327B (en) 2005-11-01 2008-01-09 Siemens Magnet Technology Ltd Transportable magnetic resonance imaging (MRI) system
EP1954189A4 (en) 2005-11-17 2012-05-23 Brain Res Inst Pty Ltd DEVICE AND METHOD FOR DETECTING AND MONITORING ELECTRICAL ACTIVITIES AND MOVEMENTS IN THE SURROUNDINGS OF A MAGNETIC FIELD
US7659719B2 (en) 2005-11-25 2010-02-09 Mr Instruments, Inc. Cavity resonator for magnetic resonance systems
JP5283839B2 (ja) 2005-11-25 2013-09-04 東芝メディカルシステムズ株式会社 医用画像診断システム
CN100411585C (zh) 2005-11-30 2008-08-20 西门子（中国）有限公司 磁共振成像系统的大视野成像装置
US7573268B2 (en) 2006-02-22 2009-08-11 Los Alamos National Security, Llc Direct imaging of neural currents using ultra-low field magnetic resonance techniques
WO2007103953A2 (en) 2006-03-09 2007-09-13 Insight Neuroimaging Systems, Llc Microstrip coil designs for mri devices
WO2007106765A2 (en) 2006-03-11 2007-09-20 Xigo Nanotools Llc Compact and portable low-field pulsed nmr dispersion analyzer
US7271591B1 (en) 2006-03-15 2007-09-18 General Electric Company Methods and apparatus for MRI shims
US8120358B2 (en) 2006-04-13 2012-02-21 The Regents Of The University Of California Magnetic resonance imaging with high spatial and temporal resolution
US8049504B2 (en) 2006-04-24 2011-11-01 Koninklijke Philips Electronics N.V. Simple decoupling of a multi-element RF coil, enabling also detuning and matching functionality
US7821402B2 (en) 2006-05-05 2010-10-26 Quality Electrodynamics IC tags/RFID tags for magnetic resonance imaging applications
US8626266B1 (en) 2006-06-01 2014-01-07 Perinatronics Medical Systems, Inc. ECG triggered heart and arterial magnetic resonance imaging
US20070285197A1 (en) 2006-06-08 2007-12-13 General Electric Company Method for disassembling a magnetic field generator
WO2008008447A2 (en) 2006-07-12 2008-01-17 The Regents Of The University Of California Portable device for ultra-low field magnetic resonance imaging (ulf-mri)
US20080027306A1 (en) 2006-07-31 2008-01-31 General Electric Company System and method for initiating a diagnostic imaging scan
US20080048658A1 (en) 2006-08-24 2008-02-28 Stephen Gerard Hushek Automatic noise cancellation for unshielded mr systems
US7436180B2 (en) 2006-10-04 2008-10-14 General Electric Company Gradient coil apparatus and method of fabricating a gradient coil to reduce artifacts in MRI images
US20080139896A1 (en) 2006-10-13 2008-06-12 Siemens Medical Solutions Usa, Inc. System and Method for Graphical Annotation of Anatomical Images Using a Touch Screen Display
US8850338B2 (en) 2006-10-13 2014-09-30 Siemens Medical Solutions Usa, Inc. System and method for selection of anatomical images for display using a touch-screen display
AU2007308759B2 (en) 2006-10-27 2011-05-12 Nmr Holdings No. 2 Pty Limited Magnets for use in magnetic resonance imaging
US8368402B2 (en) 2006-11-08 2013-02-05 T2 Biosystems, Inc. NMR systems for in vivo detection of analytes
JP4893319B2 (ja) 2007-01-10 2012-03-07 ブラザー工業株式会社 画像形成装置
US7759938B2 (en) 2007-02-05 2010-07-20 Morpho Detection, Inc. Apparatus and method for varying magnetic field strength in magnetic resonance measurements
EP1962100A1 (en) 2007-02-20 2008-08-27 Esaote S.p.A. Magnetic structure for MRI machines and MRI machine particularly for orthopedic or rheumatologic applications
DE102007009203B4 (de) 2007-02-26 2012-03-22 Siemens Ag Verfahren zur Bestimmung oder Anpassung eines Shims zur Homogenisierung eines Magnetfeldes einer Magnetresonanzeinrichtung und zugehörige Magnetresonanzeinrichtung
US7414401B1 (en) 2007-03-26 2008-08-19 General Electric Company System and method for shielded dynamic shimming in an MRI scanner
JP2010525892A (ja) 2007-05-04 2010-07-29 カリフォルニア インスティテュート オブ テクノロジー 低磁場ｓｑｕｉｄ−ｍｒｉ装置、コンポーネント、及び方法
US8175677B2 (en) 2007-06-07 2012-05-08 MRI Interventions, Inc. MRI-guided medical interventional systems and methods
US20120003160A1 (en) 2007-06-29 2012-01-05 Amag Pharmaceuticals, Inc. Macrophage-Enhanced MRI (MEMRI) in a Single Imaging Session
US8335359B2 (en) 2007-07-20 2012-12-18 General Electric Company Systems, apparatus and processes for automated medical image segmentation
US20100219833A1 (en) 2007-07-26 2010-09-02 Emscan Limited Magnet assembly
US8466681B2 (en) 2007-08-30 2013-06-18 Hitachi Medical Corporation Open-type MRI apparatus, and open-type superconducting MRI apparatus
US8570042B2 (en) 2007-08-31 2013-10-29 The Regents Of The University Of California Adjustable permanent magnet assembly for NMR and MRI
CN101162637B (zh) 2007-09-17 2011-05-11 山西省平遥县新星磁材有限公司 超高场强磁选机用永磁体装置
JP4528322B2 (ja) * 2007-09-28 2010-08-18 富士フイルム株式会社 画像表示装置、画像表示方法、および画像表示プログラム
AU2008325088A1 (en) 2007-11-06 2009-05-14 T2 Biosystems, Inc. Small magnet and RF coil for magnetic resonance relaxometry
EP2229097A4 (en) 2007-11-09 2011-01-26 Vista Clara Inc MULTILAYER NUCLEAR CORE MAGNETIC RESONANCE DETECTION AND IMAGING APPARATUS AND METHOD
CA2706717A1 (en) 2007-11-27 2009-06-04 Arjae Spectral Enterprises, Inc. Noise reduction by means of spectral parallelism
WO2009097053A1 (en) 2007-12-14 2009-08-06 The Regents Of The University Of California Magnetic resonance imaging of living systems by remote detection
AU2008343871B2 (en) 2007-12-21 2014-02-06 T2 Biosystems, Inc. Magnetic resonance system with implantable components and methods of use thereof
US7753165B2 (en) 2007-12-21 2010-07-13 Robert Bosch Gmbh Device and method for active noise cancellation in exhaust gas channel of a combustion engine
JP2009240767A (ja) 2008-03-10 2009-10-22 Toshiba Corp 磁気共鳴イメージング装置
EP2262570A1 (en) 2008-03-12 2010-12-22 Navotek Medical Ltd. Combination mri and radiotherapy systems and methods of use
JP5170540B2 (ja) 2008-04-24 2013-03-27 株式会社日立メディコ 磁気共鳴イメージング装置
WO2009137354A1 (en) 2008-05-05 2009-11-12 Mayo Foundation For Medical Education And Research Method for assessing the probability of disease development in tissue
US7714583B2 (en) 2008-06-13 2010-05-11 General Electric Company Power supply for supplying multi-channel, stable, isolated DC power and method of making same
US20110175694A1 (en) 2008-06-24 2011-07-21 Fallone B Gino Magnetic assembly and method for defining a magnetic field for an imaging volume
US7834270B2 (en) 2008-07-07 2010-11-16 Imris Inc. Floating segmented shield cable assembly
US7936170B2 (en) 2008-08-08 2011-05-03 General Electric Co. RF coil and apparatus to reduce acoustic noise in an MRI system
US8255038B2 (en) 2008-08-28 2012-08-28 Siemens Medical Solutions Usa, Inc. System and method for non-uniform image scanning and acquisition
JP5567305B2 (ja) 2008-09-10 2014-08-06 株式会社竹中工務店 磁気シールドシステム及び磁気シールド方法
US8692412B2 (en) 2008-09-27 2014-04-08 Witricity Corporation Temperature compensation in a wireless transfer system
EP2184615A1 (en) 2008-11-05 2010-05-12 Koninklijke Philips Electronics N.V. A magnetic resonance imaging system comprising a power supply unit adapted for providing direct current electrical power
EP2194486A1 (en) 2008-12-04 2010-06-09 Koninklijke Philips Electronics N.V. A method, apparatus, and computer program product for acquiring medical image data
CN102316798A (zh) 2008-12-18 2012-01-11 古鲁姆·泰克勒马林 用于磁共振成像的小型非均匀永磁场发生器
US8328732B2 (en) 2008-12-18 2012-12-11 Devicor Medical Products, Inc. Control module interface for MRI biopsy device
EP2380492B1 (en) 2008-12-26 2021-01-27 National University Corporation Kumamoto University Phase difference enhanced imaging method (padre), phase difference enhanced imaging program, phase difference enhanced imaging apparatus, and magnetic resonance imaging (mri) apparatus
CN101788655A (zh) 2009-01-24 2010-07-28 Ge医疗系统环球技术有限公司 磁共振成像系统以及使该系统中主磁体的温度稳定的方法
US8064183B2 (en) 2009-06-01 2011-11-22 Olliges William E Capacitor based bi-directional degaussing device with chamber
CN102625669B (zh) 2009-06-08 2015-09-23 核磁共振成像介入技术有限公司 能够近实时地跟踪和生成柔性体内装置的动态可视化的mri导向的介入系统
US8198891B2 (en) 2009-06-15 2012-06-12 General Electric Company System, method, and apparatus for magnetic resonance RF-field measurement
GB2471705B (en) 2009-07-09 2011-07-27 Siemens Magnet Technology Ltd Methods and apparatus for storage of energy removed from superconducting magnets
ITGE20090059A1 (it) 2009-07-28 2011-01-29 Esaote Spa Macchina per il rilevamento di immagini mri
WO2011047376A2 (en) 2009-10-16 2011-04-21 Emprimus, Inc. Modular electromagnetically shielded enclosure
US20110142316A1 (en) 2009-10-29 2011-06-16 Ge Wang Tomography-Based and MRI-Based Imaging Systems
KR101616465B1 (ko) 2009-11-02 2016-04-28 펄스 테라퓨틱스, 인코포레이티드 기자성 스테이터 시스템 및 마그네틱 로터의 무선제어 방법
US10162026B2 (en) 2009-11-09 2018-12-25 Vista Clara Inc. Noise canceling in-situ NMR detection
US8816684B2 (en) 2009-11-09 2014-08-26 Vista Clara Inc. Noise canceling in-situ NMR detection
US8378682B2 (en) 2009-11-17 2013-02-19 Muralidhara Subbarao Field image tomography for magnetic resonance imaging
US8593141B1 (en) 2009-11-24 2013-11-26 Hypres, Inc. Magnetic resonance system and method employing a digital squid
CN102686278B (zh) 2009-12-28 2016-01-13 皇家飞利浦电子股份有限公司 治疗设备
RU2573545C2 (ru) 2009-12-28 2016-01-20 Конинклейке Филипс Электроникс Н.В. Трубчатый тепловой переключатель для магнита, не использующего криогенные среды
US8427148B2 (en) 2009-12-31 2013-04-23 Analogic Corporation System for combining magnetic resonance imaging with particle-based radiation systems for image guided radiation therapy
AU2011220724B2 (en) 2010-02-24 2014-09-18 Viewray Technologies, Inc. Split magnetic resonance imaging system
US20110210734A1 (en) 2010-02-26 2011-09-01 Robert David Darrow System and method for mr image scan and analysis
US8970217B1 (en) 2010-04-14 2015-03-03 Hypres, Inc. System and method for noise reduction in magnetic resonance imaging
WO2011127946A1 (en) 2010-04-15 2011-10-20 Elekta Ab (Publ) Radiotherapy apparatus
BR112013001488A2 (pt) 2010-07-23 2016-05-31 Konink Philps Electronics Nv dispositivo de detecção do estado fisiológico para a detecção de um estado fisiológico de um paciente e a minimização da quantidade de interferência gerada durante uma varredura de ressonância magnética por um sistema de ressonância magnética, sistema de irm, método para a detecção de um estado fisiológico de um paciente e a minimização de uma quantidade de interferência gerada durante uma verradura de ressonância magnética, método para a operação de um sistema de irm e dispositivo de detecção de pressão para a detecção de um sinal de pressão e a minimização da quantidade de interferência gerada durante uma varredura de ressonância magnética por um sistema de ressonância magnética com um orifício.
JP5618683B2 (ja) 2010-08-03 2014-11-05 株式会社日立メディコ 磁気共鳴イメージング装置及び輝度不均一補正方法
JP5482554B2 (ja) 2010-08-04 2014-05-07 株式会社村田製作所 積層型コイル
EP2418516A3 (en) 2010-08-12 2014-02-19 E-Pharma Trento S.p.A. Apparatus and method for detecting the presence of a particle of a ferromagnetic metal in a packaging of a paramagnetic material
US9500731B2 (en) 2010-10-15 2016-11-22 Eleazar Castillo Shimming device and method to improve magnetic field homogeneity in magnetic resonance imaging devices
US8638096B2 (en) 2010-10-19 2014-01-28 The Board Of Trustees Of The Leland Stanford Junior University Method of autocalibrating parallel imaging interpolation from arbitrary K-space sampling with noise correlations weighted to reduce noise of reconstructed images
US8409807B2 (en) 2010-10-22 2013-04-02 T2 Biosystems, Inc. NMR systems and methods for the rapid detection of analytes
US8563298B2 (en) 2010-10-22 2013-10-22 T2 Biosystems, Inc. NMR systems and methods for the rapid detection of analytes
US8901928B2 (en) 2010-11-09 2014-12-02 Imris Inc. MRI safety system
CA2822287C (en) * 2010-12-22 2020-06-30 Viewray Technologies, Inc. System and method for image guidance during medical procedures
US8374663B2 (en) 2011-01-31 2013-02-12 General Electric Company Cooling system and method for cooling superconducting magnet devices
WO2012129325A1 (en) 2011-03-22 2012-09-27 The General Hospital Corporation Molecular analysis of tumor samples
US8558547B2 (en) 2011-05-05 2013-10-15 General Electric Company System and method for magnetic resonance radio-frequency field mapping
WO2012170119A1 (en) 2011-06-06 2012-12-13 St. Jude Medical, Atrial Fibrillation Division, Inc. Noise tolerant localization systems and methods
WO2012173635A1 (en) 2011-06-13 2012-12-20 Vanderbilt University Multiple resonance nmr spectroscopy using a single transmitter
US9351662B2 (en) 2011-06-17 2016-05-31 Microsoft Technology Licensing, Llc MRI scanner that outputs bone strength indicators
JP2014523795A (ja) 2011-07-28 2014-09-18 ブリガム・アンド・ウイミンズ・ホスピタル・インコーポレイテッド 肺特性のポータブル磁気共鳴測定のためのシステム及び方法
JP5387629B2 (ja) * 2011-07-30 2014-01-15 株式会社デンソー Ｄｃｄｃコンバータの制御装置
US10571540B2 (en) 2011-08-31 2020-02-25 Insightec, Ltd. Systems and methods for avoiding MRI-originated interference with concurrently used systems
US9254097B2 (en) 2011-09-19 2016-02-09 Los Alamos National Security, Llc System and method for magnetic current density imaging at ultra low magnetic fields
US10151809B2 (en) 2011-10-21 2018-12-11 Hitachi, Ltd. Magnetic resonance imaging apparatus and operating method
FI125397B (en) 2012-01-24 2015-09-30 Elekta Ab A method for using spatial and temporal oversampling in multichannel measurements
TWI587597B (zh) 2012-02-17 2017-06-11 Ｌｇ伊諾特股份有限公司 無線電力傳輸器，無線電力接收器，以及無線電力傳輸系統的電力傳輸方法
US9316707B2 (en) 2012-04-18 2016-04-19 General Electric Company System and method of receive sensitivity correction in MR imaging
US9500727B2 (en) 2012-04-20 2016-11-22 Regents Of The University Of Minnesota System and method for control of RF circuits for use with an MRI system
US9883878B2 (en) 2012-05-15 2018-02-06 Pulse Therapeutics, Inc. Magnetic-based systems and methods for manipulation of magnetic particles
US9244139B2 (en) 2012-05-18 2016-01-26 Neocoil, Llc Method and apparatus for MRI compatible communications
PT2861136T (pt) 2012-06-15 2021-07-13 Massachusetts Gen Hospital Sistema e método de imagem por ressonância magnética que utiliza um conjunto rotativo de ímanes permanentes
US8993898B2 (en) 2012-06-26 2015-03-31 ETS-Lindgren Inc. Movable EMF shield, method for facilitating rapid imaging and treatment of patient
GB201212813D0 (en) 2012-07-19 2012-09-05 Univ Aberdeen Apparatus for use with an MRI scanner
US20140066739A1 (en) 2012-08-29 2014-03-06 Bin He System and method for quantifying or imaging pain using electrophysiological measurements
CN102800057A (zh) 2012-09-18 2012-11-28 苏州安科医疗系统有限公司 一种用于磁共振成像基于相位一致性的图像去噪方法
US9165360B1 (en) 2012-09-27 2015-10-20 Zepmed, Llc Methods, systems, and devices for automated analysis of medical scans
US9910115B2 (en) 2012-10-22 2018-03-06 The General Hospital Corporation System and method for portable magnetic resonance imaging using a rotating array of magnets
US9766316B2 (en) 2012-11-16 2017-09-19 Hitachi, Ltd. Magnetic resonance imaging device and quantitative susceptibility mapping method
WO2014087954A1 (ja) 2012-12-05 2014-06-12 株式会社 日立メディコ 磁気共鳴イメージング装置および磁気共鳴イメージング装置のファンモータの運転方法
US9268572B2 (en) 2012-12-11 2016-02-23 International Business Machines Corporation Modify and execute next sequential instruction facility and instructions therefor
CN103892831A (zh) 2012-12-26 2014-07-02 上海联影医疗科技有限公司 一种磁共振成像方法及磁共振系统
EP2749318A1 (en) 2012-12-28 2014-07-02 Theraclion SA Image-guided therapeutic apparatus and method of preparation of an image-guided therapeutic apparatus for treatment of tissue
CN109008972A (zh) 2013-02-01 2018-12-18 凯内蒂科尔股份有限公司 生物医学成像中的实时适应性运动补偿的运动追踪系统
EP2765437B1 (en) 2013-02-12 2020-05-06 Siemens Healthcare GmbH A simple method to denoise ratio images in magnetic resonance imaging
WO2014152919A1 (en) 2013-03-14 2014-09-25 Arizona Board Of Regents, A Body Corporate Of The State Of Arizona For And On Behalf Of Arizona State University Kernel sparse models for automated tumor segmentation
WO2014143796A2 (en) 2013-03-15 2014-09-18 Mobius Imaging, Llc Mobile x-ray imaging system
WO2014138923A1 (en) 2013-03-15 2014-09-18 Synaptive Medical (Barbados) Inc. Insert imaging device for surgical procedures
GB2512876A (en) * 2013-04-09 2014-10-15 Image Analysis Ltd Methods and apparatus for quantifying inflammation
US9788795B2 (en) 2013-04-12 2017-10-17 The Research Foundation For The State University Of New York Magnetic resonance imaging method
US10311598B2 (en) 2013-05-16 2019-06-04 The Regents Of The University Of California Fully automated localization of electroencephalography (EEG) electrodes
US20160011290A1 (en) 2013-05-21 2016-01-14 Victor Iannello Non-Invasive, In-Vivo Measurement of Blood Constituents Using a Portable Nuclear Magnetic Resonance Device
DE102013210237B4 (de) 2013-06-03 2016-12-29 Siemens Healthcare Gmbh Verfahren zum Betreiben eines mobilen Magnetresonanztomographiesystems
US20140364720A1 (en) * 2013-06-10 2014-12-11 General Electric Company Systems and methods for interactive magnetic resonance imaging
WO2015040473A1 (en) 2013-09-17 2015-03-26 Synaptive Medical (Barbados) Inc. Coil assembly for magnetic resonance imaging
US9655563B2 (en) 2013-09-25 2017-05-23 Siemens Healthcare Gmbh Early therapy response assessment of lesions
DE202013105212U1 (de) 2013-11-17 2014-02-13 Aspect Imaging Ltd. Schließvorrichtung eines MRT-Inkubators
WO2015085257A1 (en) 2013-12-06 2015-06-11 Sonitrack Systems, Inc. Mechanically driven ultrasound scanning system and method
US20150198684A1 (en) 2014-01-13 2015-07-16 Tamer BASHA System and Method For Flexible Automated Magnetic Resonance Imaging Reconstruction
DE202014101104U1 (de) 2014-03-09 2014-05-15 Aspect Imaging Ltd. Eine wärmeisolierende MRT-Ummantelung
JP6791760B2 (ja) * 2014-03-14 2020-11-25 ザ ジェネラル ホスピタル コーポレイション 低磁場マルチチャネル撮像のためのシステムおよび方法
CN103892834B (zh) 2014-03-21 2016-05-25 沈阳中北真空磁电科技有限公司 一种用于核磁共振成像仪的永磁体
US10317502B2 (en) 2014-03-31 2019-06-11 Koninklijke Philips N.V. Magnetic resonance imaging with RF noise detection coils
US20150285882A1 (en) 2014-04-03 2015-10-08 University Of Maryland, Baltimore Portable system and method for mri imaging and tissue analysis
US10605884B2 (en) 2014-04-15 2020-03-31 Imperial College Of Science, Technology And Medicine Transverse field MRI apparatus
JP6629762B2 (ja) * 2014-05-23 2020-01-15 ベンタナ メディカル システムズ， インコーポレイテッド 画像内の生物学的構造及び／又はパターンの検出のためのシステム及び方法
CA3185937A1 (en) 2014-06-02 2015-12-10 Transmedics, Inc. Ex vivo organ care system
CN106716166A (zh) 2014-06-11 2017-05-24 维多利亚互联有限公司 可运输磁共振成像系统
CA2951769A1 (en) 2014-06-30 2016-01-07 Universitat Bern Method for segmenting and predicting tissue regions in patients with acute cerebral ischemia
JP6128691B2 (ja) * 2014-07-10 2017-05-17 富士フイルム株式会社 医用画像計測装置および方法並びにプログラム
US9754371B2 (en) * 2014-07-31 2017-09-05 California Institute Of Technology Multi modality brain mapping system (MBMS) using artificial intelligence and pattern recognition
TWI542328B (zh) 2014-07-31 2016-07-21 國立中央大學 偵測與量化腦梗塞區域的方法
US9678183B2 (en) 2014-08-14 2017-06-13 General Electric Company Wireless actuator circuit for wireless actuation of micro electromechanical system switch for magnetic resonance imaging
US9817093B2 (en) 2014-09-05 2017-11-14 Hyperfine Research, Inc. Low field magnetic resonance imaging methods and apparatus
GB2549213B (en) 2014-11-04 2020-07-15 Synaptive Medical Barbados Inc MRI guided radiation therapy
CA3115673A1 (en) 2014-11-11 2016-05-19 Hyperfine Research, Inc. Pulse sequences for low field magnetic resonance
US10813564B2 (en) 2014-11-11 2020-10-27 Hyperfine Research, Inc. Low field magnetic resonance methods and apparatus
US9874620B2 (en) 2015-02-05 2018-01-23 Ohio State Innovation Foundation Low field magnetic resonance imaging (MRI) scanner for cardiac imaging
HK1251301A1 (zh) 2015-04-13 2019-01-25 Hyperfine, Inc. 磁线圈供电方法和装置
CN107533117B (zh) 2015-04-30 2020-05-01 皇家飞利浦有限公司 用于具有rf噪声的磁共振成像的方法和装置
HK1252007A1 (zh) 2015-05-12 2019-05-10 Hyperfine, Inc. 射频线圈方法和装置
US10194829B2 (en) * 2015-07-07 2019-02-05 Q Bio, Inc. Fast scanning based on magnetic resonance history
US9958521B2 (en) 2015-07-07 2018-05-01 Q Bio, Inc. Field-invariant quantitative magnetic-resonance signatures
KR102454746B1 (ko) 2015-10-01 2022-10-17 삼성전자주식회사 통신 시스템에서 미디어 리소스 식별 정보를 송수신하는 장치 및 방법
US10909675B2 (en) 2015-10-09 2021-02-02 Mayo Foundation For Medical Education And Research System and method for tissue characterization based on texture information using multi-parametric MRI
CN108369642A (zh) 2015-12-18 2018-08-03 加利福尼亚大学董事会 根据头部计算机断层摄影解释和量化急症特征
MX2018011524A (es) 2016-03-22 2019-07-04 Hyperfine Res Inc Métodos y aparato para adaptar campos magnéticos.
US10359486B2 (en) 2016-04-03 2019-07-23 Q Bio, Inc. Rapid determination of a relaxation time
KR20190021344A (ko) 2016-06-20 2019-03-05 버터플라이 네트워크, 인크. 초음파 디바이스를 작동하는 사용자를 보조하기 위한 자동화된 영상 취득
DE102016211072A1 (de) 2016-06-21 2017-12-21 Siemens Healthcare Gmbh Verfahren zu einem Bereitstellen einer Auswahl von zumindest einem Protokollparameter aus einer Vielzahl von Protokollparametern sowie eine Magnetresonanzvorrichtung hierzu
US10210609B2 (en) 2016-09-07 2019-02-19 International Business Machines Corporation Integrated deep learning and clinical image viewing and reporting
US11399732B2 (en) 2016-09-12 2022-08-02 Aspect Imaging Ltd. RF coil assembly with a head opening and isolation channel
US10120045B2 (en) 2016-09-12 2018-11-06 Quality Electrodynamics, Llc Magnetic resonance imaging (MRI) coil with pin diode decoupling circuit
TWI667487B (zh) 2016-09-29 2019-08-01 美商超精細研究股份有限公司 射頻線圈調諧方法及裝置
US10627464B2 (en) 2016-11-22 2020-04-21 Hyperfine Research, Inc. Low-field magnetic resonance imaging methods and apparatus
US10539637B2 (en) 2016-11-22 2020-01-21 Hyperfine Research, Inc. Portable magnetic resonance imaging methods and apparatus
JP2019535424A (ja) 2016-11-22 2019-12-12 ハイパーファイン リサーチ，インコーポレイテッド 磁気共鳴画像における自動検出のためのシステムおよび方法
US10585153B2 (en) 2016-11-22 2020-03-10 Hyperfine Research, Inc. Rotatable magnet methods and apparatus for a magnetic resonance imaging system
US10371733B2 (en) 2017-01-04 2019-08-06 National Instruments Corporation Cold source based noise figure measurement using S-parameters and a vector signal transceiver/vector signal analyzer/spectrum analyzer
EP3879535B1 (en) 2017-06-13 2024-12-11 BostonGene Corporation Systems and methods for identifying cancer treatments from normalized biomarker scores
EP3467531A1 (de) 2017-10-05 2019-04-10 Siemens Healthcare GmbH Magnetresonanztomograph mit aktiver störunterdrückung und verfahren zur störunterdrückung in einem magnetresonanztomographen
MX2020011072A (es) 2018-04-20 2020-11-06 Hyperfine Res Inc Proteccion desplegable para dispositivos portatiles de formacion de imagenes de resonancia magnetica.
CA3098461A1 (en) 2018-05-21 2019-11-28 Hyperfine Research, Inc. B0 magnet methods and apparatus for a magnetic resonance imaging system
MX2020012542A (es) 2018-05-21 2021-02-16 Hyperfine Res Inc Cadena de señal de bobina de radiofrecuencia para un sistema de resonancia magnética (mri) de campo bajo.
JP7224792B2 (ja) 2018-06-28 2023-02-20 キヤノンメディカルシステムズ株式会社 磁気共鳴イメージング装置
TW202015621A (zh) 2018-07-19 2020-05-01 美商超精細研究股份有限公司 在磁共振成像中患者定位之方法及設備
CN113795764B (zh) 2018-07-30 2025-03-25 海珀菲纳股份有限公司 用于磁共振图像重建的深度学习技术
WO2020028228A1 (en) 2018-07-31 2020-02-06 Hyperfine Research, Inc. Medical imaging device messaging service
TW202012951A (zh) 2018-07-31 2020-04-01 美商超精細研究股份有限公司 低場漫射加權成像
CN113557526B (zh) 2018-08-15 2025-11-14 海珀菲纳股份有限公司 磁共振成像方法、系统和计算机程序产品
CA3122087A1 (en) 2018-12-19 2020-06-25 Hyperfine Research, Inc. System and methods for grounding patients during magnetic resonance imaging
EP3903117B1 (en) 2018-12-28 2024-06-26 Hyperfine, Inc. Correcting for hysteresis in magnetic resonance imaging
CA3132976A1 (en) 2019-03-12 2020-09-17 Christopher Thomas Mcnulty Systems and methods for magnetic resonance imaging of infants
JP2022526718A (ja) 2019-03-14 2022-05-26 ハイパーファイン，インコーポレイテッド 空間周波数データから磁気共鳴画像を生成するための深層学習技術
BR112021020493A2 (pt) 2019-04-26 2021-12-07 Hyperfine Inc Técnicas para o controle dinâmico de um sistema de imagem de ressonância magnética
JP2022531485A (ja) 2019-05-07 2022-07-06 ハイパーファイン，インコーポレイテッド 乳児の磁気共鳴画像のためのシステム、装置、及び方法
US11698430B2 (en) 2019-08-15 2023-07-11 Hyperfine Operations, Inc. Eddy current mitigation systems and methods
WO2021108216A1 (en) 2019-11-27 2021-06-03 Hyperfine Research, Inc. Techniques for noise suppression in an environment of a magnetic resonance imaging system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050245810A1 (en) * 2004-04-28 2005-11-03 Siemens Corporate Research Inc. Method of registering pre-operative high field closed magnetic resonance images with intra-operative low field open interventional magnetic resonance images
US20120184840A1 (en) * 2009-04-07 2012-07-19 Kayvan Najarian Automated Measurement of Brain Injury Indices Using Brain CT Images, Injury Data, and Machine Learning
US20130204115A1 (en) * 2010-06-01 2013-08-08 Synarc Inc. Computer based analysis of mri images
US20130279784A1 (en) * 2010-12-21 2013-10-24 Renishaw (Ireland) Limited Method and apparatus for analysing images
US20130296660A1 (en) * 2012-05-02 2013-11-07 Georgia Health Sciences University Methods and systems for measuring dynamic changes in the physiological parameters of a subject
US20160025832A1 (en) * 2013-03-15 2016-01-28 Cameron Piron System and method for magnetic resonance image acquisition
US20160110904A1 (en) 2014-10-21 2016-04-21 Samsung Electronics Co., Ltd. Magnetic resonance imaging (mri) apparatus and method of processing mr image
US20160140435A1 (en) * 2014-11-14 2016-05-19 Google Inc. Generating natural language descriptions of images

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
MARCEL BOSC: "Automatic change detection in multimodal serial MRI: application to multiple sclerosis lesion evolution", ELSEVIER

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024182799A1 (en) * 2023-03-02 2024-09-06 Neuro42 Inc. A system and method of merging a co-operative mr-compatible robot and a low-field portable mri system

Also Published As

Publication number Publication date
TWI704903B (zh) 2020-09-21
US10955504B2 (en) 2021-03-23
EP3545494A1 (en) 2019-10-02
JP2019535424A (ja) 2019-12-12
US12050256B2 (en) 2024-07-30
US20190033414A1 (en) 2019-01-31
EP3968278A1 (en) 2022-03-16
US10534058B2 (en) 2020-01-14
US20180143275A1 (en) 2018-05-24
IL266748A (en) 2019-07-31
US20180143281A1 (en) 2018-05-24
US20180144467A1 (en) 2018-05-24
US20200341095A1 (en) 2020-10-29
BR112019010225A2 (pt) 2019-08-20
US10718842B2 (en) 2020-07-21
AU2017363608A1 (en) 2019-05-23
CA3043038A1 (en) 2018-05-31
US20190033415A1 (en) 2019-01-31
CN109983474A (zh) 2019-07-05
EP3545494A4 (en) 2020-05-27
BR112019010225A8 (pt) 2023-04-04
MX2019005955A (es) 2019-07-10
US20190011521A1 (en) 2019-01-10
US10416264B2 (en) 2019-09-17
US10816629B2 (en) 2020-10-27
EP3545494B1 (en) 2022-01-05
KR20190087455A (ko) 2019-07-24
US10585156B2 (en) 2020-03-10
TW201825047A (zh) 2018-07-16

Similar Documents

Publication Publication Date Title
US12050256B2 (en) Systems and methods for automated detection in magnetic resonance images
US12529743B2 (en) Tensor field mapping
EP3830594B1 (en) Low-field diffusion-weighted magnetic resonance imaging
CN113557526B (zh) 磁共振成像方法、系统和计算机程序产品
JP7152956B2 (ja) テンソル場マッピング
US10359486B2 (en) Rapid determination of a relaxation time
US12114968B2 (en) System and method for magnetic resonance elastography
HK40011163A (en) Systems and methods for automated detection in magnetic resonance images
Hossain Evaluating the ULF MRI (0.64 t) Image Quality Through In Vivo Test-Retest

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17872998

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 3043038

Country of ref document: CA

ENP Entry into the national phase

Ref document number: 2019527297

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2017363608

Country of ref document: AU

Date of ref document: 20171121

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112019010225

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 20197016485

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2017872998

Country of ref document: EP

Effective date: 20190624

ENP Entry into the national phase

Ref document number: 112019010225

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20190520