CN117558428B - Imaging optimization method and system for liver MRI - Google Patents
Imaging optimization method and system for liver MRI Download PDFInfo
- Publication number
- CN117558428B CN117558428B CN202410048192.7A CN202410048192A CN117558428B CN 117558428 B CN117558428 B CN 117558428B CN 202410048192 A CN202410048192 A CN 202410048192A CN 117558428 B CN117558428 B CN 117558428B
- Authority
- CN
- China
- Prior art keywords
- breathing
- imaging
- data
- representative
- patient
- 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.)
- Active
Links
- 238000003384 imaging method Methods 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 title claims abstract description 36
- 210000004185 liver Anatomy 0.000 title claims abstract description 27
- 238000005457 optimization Methods 0.000 title claims abstract description 19
- 230000029058 respiratory gaseous exchange Effects 0.000 claims abstract description 179
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 230000006698 induction Effects 0.000 claims abstract description 14
- 230000001939 inductive effect Effects 0.000 claims abstract description 4
- 230000000241 respiratory effect Effects 0.000 claims description 16
- 238000004088 simulation Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 9
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 206010006322 Breath holding Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 108091008698 baroreceptors Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 208000019423 liver disease Diseases 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 210000001774 pressoreceptor Anatomy 0.000 description 1
- 108020003175 receptors Proteins 0.000 description 1
Classifications
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
-
- 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 classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/02—Methods for producing synthetic speech; Speech synthesisers
- G10L13/027—Concept to speech synthesisers; Generation of natural phrases from machine-based concepts
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Data Mining & Analysis (AREA)
- Surgery (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Audiology, Speech & Language Pathology (AREA)
- High Energy & Nuclear Physics (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- General Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses an imaging optimization method and system for liver MRI, which belong to the technical field of imaging optimization of liver MRI and comprise a data induction module, a monitoring module and an imaging module. The data induction module is used for inducing the historical patient data to form a plurality of representative classifications and representative breathing curves corresponding to the representative classifications; summarizing the optimal scanning schemes corresponding to different representative classifications and representative breathing curves; the monitoring module is used for carrying out real-time respiration monitoring on the inspected patient, acquiring patient information, and determining corresponding representative classification and representative respiration curve according to the patient information; identifying an optimal scanning scheme representing a breathing curve, and determining corresponding optimal breathing data according to the optimal scanning scheme; when the imaging requirement is met, generating a corresponding imaging instruction; the imaging module is used for imaging management of liver MRI, and when an imaging instruction is acquired, imaging acquisition of a patient is carried out according to an optimal scanning scheme, and a corresponding imaging image is obtained.
Description
Technical Field
The invention belongs to the technical field of imaging optimization of liver MRI, and particularly relates to an imaging optimization method and system for liver MRI.
Background
Liver MRI examinations have unique advantages for diagnosing and assessing liver disease, their safe, non-radiative, multi-parameter, multi-view imaging capabilities over other diagnostic means. Among them, T2 weighted imaging (T2 WI) is an indispensable part in liver MRI, and is widely used for diagnosis and monitoring of focal lesions of the liver. T2WI can be implemented by a variety of acquisition strategies and scanning parameters, and different T2WI sequences may require the use of breath-hold or respiratory gating techniques of the patient to acquire high quality images, depending on their acquisition times and strategies. However, the breathing regularity and breath-holding ability of the patient directly affect the quality of the image. For this problem, it is important to select a scan pattern and parameters that are compatible with the breathing characteristics of the patient. This not only improves image quality, reduces the failure rate of scanning, but also saves scanning time and improves patient comfort. There is currently no method for intelligently selecting the optimal scanning scheme according to individual differences in the breathing situation of patients. Based on the above, the invention provides an imaging optimization method and an imaging optimization system for liver MRI.
Disclosure of Invention
In order to solve the problems of the above proposal, the invention provides an imaging optimization method and a system for liver MRI.
The aim of the invention can be achieved by the following technical scheme:
an imaging optimization system for liver MRI comprises a data induction module, a monitoring module and an imaging module;
the data induction module is used for inducing historical patient data to form a plurality of representative classifications and representative breathing curves corresponding to the representative classifications; the best scan schemes corresponding to the different representative classifications and the representative breathing curves are summarized.
Further, the working method of the data induction module comprises the following steps:
acquiring historical patient data; processing the historical patient data according to a preset characteristic data processing template to obtain a plurality of pieces of historical patient characteristic data;
splitting and combining the obtained characteristic data of each historical patient to form a plurality of first merging sets and second merging sets;
performing intersection processing on each first merging set and each second merging set to form a plurality of representative classifications and representative breathing curves corresponding to each representative classification; and sets the corresponding optimal scanning scheme.
Further, the method for splitting and combining the obtained historical patient characteristic data comprises the following steps:
splitting data corresponding to patient condition characteristics and physical condition characteristics in the historical patient characteristic data into first combined analysis data; splitting the data corresponding to the breathing parameter characteristics and the imaging characteristics in the historical patient characteristic data into second combined analysis data;
carrying out merging analysis on the first merging analysis data to obtain a plurality of first merging sets;
and carrying out merging analysis on the second merging analysis data to obtain a plurality of second merging sets.
Further, the method for performing the merging analysis on the first merging analysis data includes:
step SA1: carrying out coordinate transformation on the first combined analysis data to form a plurality of first coordinates; inputting each of the obtained first coordinates into a coordinate space;
step SA2: calculating Euclidean distance between the first coordinates;
step SA3: combining the first coordinates with the Euclidean distance smaller than the threshold value X1 to form new first coordinates, and forming a corresponding combined chain according to the two corresponding original first coordinates;
after completing the combination of the two first coordinates once, returning to the step SA2 until no first coordinates which can be combined exist;
step SA4: and identifying a merging chain set corresponding to each first coordinate in the coordinate space, and generating a coordinate region corresponding to the first coordinate according to the obtained merging chain set, wherein the coordinate region is marked as a first merging set.
Further, the method for performing the merging analysis on the second merging analysis data includes:
step SC1: converting the second combined analysis data to form a corresponding second coordinate;
step SC2: setting corresponding imaging curves according to the obtained second coordinates, and integrating the imaging curves into the same coordinate system;
step SC3: identifying a combined value between each of the imaging curves;
step SC4: combining the two imaging curves with the combination value not greater than the threshold value X2 to form a new imaging curve, marking a region between the two corresponding imaging curves, and marking the region as an imaging region;
after completing the combination of the two imaging curves once, returning to the step SC3 until no imaging curve can be combined;
step SA5: and identifying imaging areas corresponding to the imaging curves, and merging the imaging areas to form a second merging set corresponding to the imaging curves.
Further, the method for performing intersection processing on each first merging set and each second merging set comprises the following steps:
identifying first merging analysis data corresponding to the first merging set and the second merging set respectively, determining corresponding first intersection sets and second intersection sets according to the first merging analysis data corresponding to the first merging analysis data respectively, and determining corresponding representative classification according to the first intersection sets; and determining a corresponding representative breathing curve according to the second intersection.
The monitoring module is used for carrying out real-time respiration monitoring on an inspected patient, obtaining patient information and determining corresponding representative classification and representative respiration curves according to the patient information; identifying the optimal scanning scheme representing the breathing curve, and determining corresponding optimal breathing data according to the optimal scanning scheme;
acquiring real-time respiratory data of a patient; the obtained real-time breathing data are marked in real time in the representative breathing curve, and a corresponding breathing adjustment curve is obtained; marking coordinate points of the real-time breathing data in the breathing adjustment curve as real-time breathing points, and marking coordinate points of the optimal breathing data in the breathing adjustment curve as optimal breathing points;
identifying corresponding real-time breathing points and optimal breathing points in a breathing adjustment curve, generating corresponding patient guiding voice according to the identified real-time breathing points and the optimal breathing points, and controlling breathing by a patient according to the generated patient guiding voice; when the imaging requirement is met, a corresponding imaging instruction is generated, and the obtained imaging instruction and the optimal scanning scheme are sent to the imaging module.
Further, the method of determining a representative classification and a representative breathing curve from patient information comprises:
processing the obtained patient data according to a preset characteristic data processing template to obtain corresponding patient matching data; matching the obtained patient matching data with each representative classification to obtain a representative classification corresponding to the patient matching data, and identifying a representative breathing curve corresponding to the representative classification; the obtained representative classification and representative breathing curve are output.
Further, the method for generating corresponding patient guiding voice according to the real-time breathing point and the optimal breathing point comprises the following steps:
performing voice simulation according to each representative breathing curve and representative classification, establishing a corresponding voice library, and establishing a corresponding AI voice model based on the voice library;
and identifying the corresponding real-time breathing point and the optimal breathing point, and analyzing through the AI voice model to obtain the corresponding patient guiding voice.
The imaging module is used for imaging management of liver MRI, receives imaging instructions sent by the monitoring module in real time, and when the imaging instructions are received, carries out imaging acquisition of a patient according to an optimal scanning scheme to obtain corresponding imaging images.
An imaging optimization method for liver MRI, the method comprising:
summarizing the historical patient data to form a plurality of representative classifications and representative breathing curves corresponding to the representative classifications; the best scan schemes corresponding to the different representative classifications and the representative breathing curves are summarized.
Patient information is acquired, and corresponding representative classification and representative breathing curves are determined according to the patient information; identifying an optimal scanning scheme representing the breathing curve, and determining corresponding optimal breathing data according to the optimal scanning scheme;
acquiring real-time respiratory data of a patient; the obtained real-time breathing data are marked in real time in the representative breathing curve, and a corresponding breathing adjustment curve is obtained; marking coordinate points of the real-time breathing data in the breathing adjustment curve as real-time breathing points, and marking coordinate points of the optimal breathing data in the breathing adjustment curve as optimal breathing points;
identifying corresponding real-time breathing points and optimal breathing points in a breathing adjustment curve, generating corresponding patient guiding voice according to the identified real-time breathing points and the optimal breathing points, and controlling breathing by a patient according to the generated patient guiding voice; when the imaging requirement is met, imaging acquisition of the patient is carried out according to the optimal scanning scheme, and a corresponding imaging image is obtained.
Compared with the prior art, the invention has the beneficial effects that:
through the mutual cooperation among the data induction module, the monitoring module and the imaging module, the optimal scanning scheme of the patient can be intelligently determined, and the imaging effect and the scanning efficiency are greatly improved.
By setting the induction module, various historical patient data are utilized, and potential uses of the historical patient data are mined; meanwhile, accurate classification is performed in a plurality of corresponding modes, finer classification is achieved, subsequent imaging precision is improved, and the problem that an individual customized scanning scheme cannot be achieved in some related systems at present is solved. And (3) analyzing through an AI voice model to obtain corresponding patient guiding voice, and training the patient to form a better breathing mode or master a correct breath-hold mode.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a functional block diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, an imaging optimization system for liver MRI includes a data induction module, a monitoring module, and an imaging module;
the data induction module is used for inducing historical patient data to form a plurality of representative classifications and representative breathing curves corresponding to the representative classifications; the best scan schemes corresponding to the different representative classifications and the representative breathing curves are summarized.
Acquiring a large amount of historical data of liver MRI imaging, namely historical patient data; establishing a corresponding characteristic data processing template according to characteristic items such as patient disease characteristics, physical condition characteristics, respiratory parameter characteristics, imaging characteristics and the like; the method comprises the steps of extracting corresponding historical patient characteristic data from each piece of historical patient data according to each characteristic item; the patient condition characteristics are used for extracting physical parameters related to physical quality of a patient, and because the parameters for standard physical quality of a human body are various, specific application situations need to be combined with acquisition equipment of a hospital to determine which physical quality indexes are adopted; the disease condition of the patient is characterized by corresponding disease conditions; the breathing parameter is characterized in that the breathing parameter of the patient is acquired by using a breathing gating technology (baroreceptors), an oral and nasal airflow receptor or a camera (the chest movement condition of the patient can be acquired) and the like, and the corresponding breathing characteristic is extracted; the imaging characteristics are evaluated by corresponding medical and technical staff according to corresponding scanning images, including subjective scores (overall image quality, motion artifacts, liver edges, blood vessel definition and the like) and objective scores (signal to noise ratio, contrast noise ratio and the like), the imaging characteristics are evaluated in an imaging score mode, the value range is [0, 100], imaging scores corresponding to different standards are preset, and then the corresponding imaging scores are set according to corresponding standard references; or uniformly evaluating the imaging scores of the imaging by a manual obtaining mode; allowing for some scoring error.
Processing the obtained historical patient data according to the set characteristic data processing template to obtain a plurality of pieces of historical patient characteristic data;
splitting and combining the obtained historical patient characteristic data to form a plurality of first merging sets and second merging sets;
performing intersection processing on the first merging set and the second merging set to form a plurality of representative classifications and representative breathing curves corresponding to the representative classifications;
determining corresponding intersections according to the first merging analysis data corresponding to the second merging sets and the first merging analysis data corresponding to the first merging sets, and dividing the first merging sets of the corresponding intersections to form the first merging sets of the corresponding intersections, namely representing classification; and then dividing according to the second merging set corresponding to the intersection part, determining the second merging set corresponding to the intersection part, and determining the middle curve of the second merging set, namely the representative breathing curve.
After each representative classification and corresponding representative breathing curve are determined, the optimal scanning schemes corresponding to different representative classifications and representative breathing curves can be generalized according to the corresponding historical scanning data or directly compiled by relevant expert personnel for demonstration and application.
In one embodiment, the corresponding intelligent model can be directly established based on the existing intelligent technology, and the intelligent model is directly analyzed, for example, the neural network technology is utilized to establish the intelligent model, the input data is respiratory data, and the output data is the optimal scanning scheme.
Illustratively, respiratory features of a patient are collected, multiple sets of T2WI images of the same patient are obtained by using T2WI sequences acquired by different technologies (compressed sensing, parallel acquisition, acceleration technologies such as semi-fourier transform, deep learning reconstruction, etc., propeller artifact removal technology, etc.) and different acquisition modes (respiratory gating/breath-hold), and correlations between image quality of different scan sequences and respiratory features of the patient are obtained by analysis. Thereby, the data training model is utilized to obtain the personalized optimal scanning scheme of the patient.
In other embodiments, because the corresponding intelligent model needs to be built with great manpower and material resources, the existing various related models can be screened, and the intelligent model with the highest precision can be selected for application.
The method for splitting and merging the obtained historical patient characteristic data comprises the following steps:
splitting data corresponding to patient condition characteristics and physical condition characteristics in the historical patient characteristic data into first combined analysis data; splitting the data corresponding to the breathing parameter characteristics and the imaging characteristics in the historical patient characteristic data into second combined analysis data;
carrying out merging analysis on the first merging analysis data to obtain a plurality of first merging sets;
and carrying out merging analysis on the second merging analysis data to obtain a plurality of second merging sets.
The method for carrying out the combination analysis on the first combination analysis data comprises the following steps:
step SA1: coordinate transformation is carried out on the first merging analysis data to form a plurality of first coordinates; performing item-by-item assignment on the first merging analysis data by presetting a corresponding assignment mode to form a corresponding data set, forming coordinates according to a corresponding ordering sequence, and marking the coordinates as first coordinates; for the selection of a preset assignment mode, the unified standard of corresponding item data is basically needed, and the preferential selection application is carried out according to the actual situation of a user; inputting each obtained first coordinate into a coordinate space;
step SA2: calculating Euclidean distance between the first coordinates;
step SA3: combining the first coordinates with the Euclidean distance smaller than the threshold value X1 to form new first coordinates, and forming a corresponding combined chain according to the two corresponding original first coordinates; the two first coordinates which need to be combined are connected by straight line segments, and the corresponding straight line segments are the combining chains; the new first coordinates are obtained by combining the two first coordinates;
after completing the combination of the two first coordinates once, returning to the step SA2 until no first coordinates which can be combined exist;
step SA4: identifying a merging chain set corresponding to each first coordinate in a coordinate space, generating a coordinate region corresponding to the first coordinate according to the obtained merging chain set, and marking the coordinate region as a first merging set; that is, the two ends of each adjacent merging chain are connected to form an enclosed area, namely a coordinate area.
The method for carrying out the combination analysis on the second combination analysis data comprises the following steps:
step SC1: converting the second combined analysis data to form a second coordinate with the respiratory parameter as a horizontal axis and the imaging score as a vertical axis, and converting the non-numerical data according to a preset assignment conversion mode; forming a corresponding second coordinate;
step SC2: setting a corresponding imaging curve according to each obtained second coordinate, generating a corresponding second coordinate according to the historical related data of the patient, and generating a corresponding imaging curve based on the existing curve generation technology; i.e. a plurality of imaging curves can be obtained from a plurality of second combined data; integrating each imaging curve into the same coordinate system;
step SC3: identifying a combined value between the imaging curves; the representative combined value can be determined by using the related numerical values such as similarity, comparison difference, precision and the like; the combined value is the degree of difference between the two curves;
step SC4: combining the two imaging curves with the combination value not greater than the threshold value X2 to form a new imaging curve, marking a region between the two corresponding imaging curves, and marking the region as an imaging region; a new imaging curve, i.e. an intermediate curve;
after completing the combination of the two imaging curves once, returning to the step SC3 until no imaging curve can be combined;
step SA5: and identifying imaging areas corresponding to the imaging curves, and merging the imaging areas to form a second merging set, namely, a merging set among the imaging areas.
By setting the induction module, various historical patient data are utilized, and potential uses of the historical patient data are mined; meanwhile, accurate classification is performed in a plurality of corresponding modes, finer classification is achieved, subsequent imaging precision is improved, and the problem that an individual customized scanning scheme cannot be achieved in some related systems at present is solved.
The monitoring module is used for carrying out real-time respiration monitoring on an inspected patient, obtaining patient information, and processing the obtained patient data according to a preset characteristic data processing template to obtain corresponding patient matching data, namely data corresponding to the first combined analysis data; according to the obtained patient matching data, matching the corresponding representative classification, obtaining the representative classification corresponding to the patient matching data, and identifying the representative breathing curve corresponding to the representative classification;
identifying an optimal scanning scheme representing the breathing curve, and determining corresponding optimal breathing data according to the optimal scanning scheme;
setting corresponding respiratory monitoring equipment, such as respiratory gating, diaphragm navigation technology or mouth and nose airflow sensors, etc. to monitor respiratory parameters of patients; obtaining real-time respiratory data of a patient; the obtained real-time breathing data are marked in real time in a representative breathing curve, and the current representative breathing curve is marked as a breathing adjustment curve; marking coordinate points of the real-time breathing data in the breathing adjustment curve as real-time breathing points, and marking coordinate points of the optimal breathing data in the breathing adjustment curve as optimal breathing points;
and identifying corresponding real-time breathing points and optimal breathing points in the breathing adjustment curve, generating corresponding patient guiding voice according to the identified real-time breathing points and the optimal breathing points, performing breathing control by a patient according to the generated patient guiding voice, generating corresponding imaging instructions when the imaging requirements are met, and transmitting the obtained imaging instructions and the optimal scanning scheme to the imaging module.
The method for generating corresponding patient guiding voice according to the identified real-time breathing points and the optimal breathing points comprises the following steps:
according to the representative breathing curves and the representative classifications, carrying out voice simulation, determining breathing adjustment modes of reaching the optimal breathing point at real-time breathing points under different conditions, setting by combining data of guiding the breathing of a patient by daily medical staff, obtaining breathing adjustment modes under different conditions after summarizing simulation, and summarizing and establishing a corresponding voice library; and then the corresponding AI voice model is established by combining the existing AI voice technology; and generating corresponding patient guiding voice according to the representative classification, the representative breathing curve, the real-time breathing point and the optimal breathing point through the AI voice model.
Through the mutual coordination between the induction module and the monitoring module, the optimal breathing data of the patient can be intelligently determined, and the patient is intelligently guided to breathe and adjust based on the optimal breathing data, so that the imaging effect and the guiding effect are greatly improved; the problem that the patient is inconvenient to accurately perform breathing adjustment when detecting is solved; the guiding efficiency is improved.
The imaging module is used for imaging management of liver MRI, receives imaging instructions sent by the monitoring module in real time, and when the imaging instructions are received, carries out imaging acquisition of a patient according to an optimal scanning scheme to obtain corresponding imaging images.
An imaging optimization method for liver MRI, the method comprising:
summarizing the historical patient data to form a plurality of representative classifications and representative breathing curves corresponding to the representative classifications; the best scan schemes corresponding to the different representative classifications and the representative breathing curves are summarized.
Patient information is acquired, and corresponding representative classification and representative breathing curves are determined according to the patient information; identifying an optimal scanning scheme representing a breathing curve, and determining corresponding optimal breathing data according to the optimal scanning scheme;
acquiring real-time respiratory data of a patient; real-time marking the obtained real-time respiration data in a representative respiration curve to obtain a corresponding respiration adjustment curve; marking coordinate points of the real-time breathing data in the breathing adjustment curve as real-time breathing points, and marking coordinate points of the optimal breathing data in the breathing adjustment curve as optimal breathing points;
identifying corresponding real-time breathing points and optimal breathing points in a breathing adjustment curve, generating corresponding patient guiding voice according to the identified real-time breathing points and the optimal breathing points, and controlling breathing by a patient according to the generated patient guiding voice; when the imaging requirement is met, imaging acquisition of the patient is carried out according to the optimal scanning scheme, and a corresponding imaging image is obtained.
Reference is made to an embodiment of an imaging optimization system for liver MRI for the portions not disclosed in this embodiment.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas which are obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and preset parameters and preset thresholds in the formulas are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (4)
1. An imaging optimization system for liver MRI, comprising a data induction module, a monitoring module and an imaging module;
the data induction module is used for inducing historical patient data to form a plurality of representative classifications and representative breathing curves corresponding to the representative classifications; summarizing the optimal scanning schemes corresponding to different representative classifications and representative breathing curves;
the monitoring module is used for carrying out real-time respiration monitoring on an inspected patient, obtaining patient information and determining corresponding representative classification and representative respiration curves according to the patient information; identifying an optimal scanning scheme representing the breathing curve, and determining corresponding optimal breathing data according to the optimal scanning scheme;
acquiring real-time respiratory data of a patient; the obtained real-time breathing data are marked in real time in the representative breathing curve, and a corresponding breathing adjustment curve is obtained; marking coordinate points of the real-time breathing data in the breathing adjustment curve as real-time breathing points, and marking coordinate points of the optimal breathing data in the breathing adjustment curve as optimal breathing points;
identifying corresponding real-time breathing points and optimal breathing points in a breathing adjustment curve, generating corresponding patient guiding voice according to the identified real-time breathing points and the optimal breathing points, and controlling breathing by a patient according to the generated patient guiding voice; when the imaging requirement is met, generating a corresponding imaging instruction, and transmitting the obtained imaging instruction and the optimal scanning scheme to an imaging module;
the imaging module is used for imaging management of liver MRI, receives imaging instructions sent by the monitoring module in real time, and when the imaging instructions are received, carries out imaging acquisition of a patient according to an optimal scanning scheme to obtain corresponding imaging images;
the working method of the data induction module comprises the following steps:
acquiring historical patient data; processing the historical patient data according to a preset characteristic data processing template to obtain a plurality of pieces of historical patient characteristic data;
splitting and combining the obtained characteristic data of each historical patient to form a plurality of first merging sets and second merging sets;
performing intersection processing on each first merging set and each second merging set to form a plurality of representative classifications and representative breathing curves corresponding to each representative classification, and setting a corresponding optimal scanning scheme;
the method for splitting and merging the obtained historical patient characteristic data comprises the following steps:
splitting data corresponding to patient condition characteristics and physical condition characteristics in the historical patient characteristic data into first combined analysis data; splitting the data corresponding to the breathing parameter characteristics and the imaging characteristics in the historical patient characteristic data into second combined analysis data;
carrying out merging analysis on the first merging analysis data to obtain a plurality of first merging sets;
carrying out merging analysis on the second merging analysis data to obtain a plurality of second merging sets;
the method for carrying out the combination analysis on the first combination analysis data comprises the following steps:
step SA1: carrying out coordinate transformation on the first combined analysis data to form a plurality of first coordinates; inputting each of the obtained first coordinates into a coordinate space;
step SA2: calculating Euclidean distance between the first coordinates;
step SA3: combining the first coordinates with the Euclidean distance smaller than the threshold value X1 to form new first coordinates, and forming a corresponding combined chain according to the two corresponding original first coordinates;
after completing the combination of the two first coordinates once, returning to the step SA2 until no first coordinates which can be combined exist;
step SA4: identifying a merging chain set corresponding to each first coordinate in a coordinate space, and generating a coordinate region corresponding to the first coordinate according to the obtained merging chain set, wherein the coordinate region is marked as a first merging set;
the method for carrying out the combination analysis on the second combination analysis data comprises the following steps:
step SC1: converting the second combined analysis data to form a corresponding second coordinate;
step SC2: setting corresponding imaging curves according to the obtained second coordinates, and integrating the imaging curves into the same coordinate system;
step SC3: identifying a combined value between each of the imaging curves;
step SC4: combining the two imaging curves with the combination value not greater than the threshold value X2 to form a new imaging curve, marking a region between the two corresponding imaging curves, and marking the region as an imaging region;
after completing the combination of the two imaging curves once, returning to the step SC3 until no imaging curve can be combined;
step SA5: identifying imaging areas corresponding to the imaging curves, and merging the imaging areas to form a second merging set corresponding to the imaging curves;
the method for carrying out intersection processing on each first merging set and each second merging set comprises the following steps:
identifying first merging analysis data corresponding to the first merging set and the second merging set respectively, determining corresponding first intersection sets and second intersection sets according to the first merging analysis data corresponding to the first merging analysis data respectively, and determining corresponding representative classification according to the first intersection sets; and determining a corresponding representative breathing curve according to the second intersection.
2. An imaging optimization system for liver MRI according to claim 1, characterized in that the method of determining the representative classification and the representative breathing curve from the patient information comprises:
processing the obtained patient data according to a preset characteristic data processing template to obtain corresponding patient matching data; matching the obtained patient matching data with each representative classification to obtain a representative classification corresponding to the patient matching data, and identifying a representative breathing curve corresponding to the representative classification; the obtained representative classification and representative breathing curve are output.
3. An imaging optimization system for liver MRI according to claim 1, characterized in that the method of generating corresponding patient guiding voices from real-time breathing points and optimal breathing points comprises:
performing voice simulation according to each representative breathing curve and representative classification, establishing a corresponding voice library, and establishing a corresponding AI voice model based on the voice library;
and identifying the corresponding real-time breathing point and the optimal breathing point, and analyzing through the AI voice model to obtain the corresponding patient guiding voice.
4. An imaging optimization method for liver MRI, characterized in that it is applied to an imaging optimization system for liver MRI as claimed in any one of claims 1 to 3, the method comprising:
summarizing the historical patient data to form a plurality of representative classifications and representative breathing curves corresponding to the representative classifications; summarizing the optimal scanning schemes corresponding to different representative classifications and representative breathing curves;
patient information is acquired, and corresponding representative classification and representative breathing curves are determined according to the patient information; identifying an optimal scanning scheme representing the breathing curve, and determining corresponding optimal breathing data according to the optimal scanning scheme;
acquiring real-time respiratory data of a patient; the obtained real-time breathing data are marked in real time in the representative breathing curve, and a corresponding breathing adjustment curve is obtained; marking coordinate points of the real-time breathing data in the breathing adjustment curve as real-time breathing points, and marking coordinate points of the optimal breathing data in the breathing adjustment curve as optimal breathing points;
identifying corresponding real-time breathing points and optimal breathing points in a breathing adjustment curve, generating corresponding patient guiding voice according to the identified real-time breathing points and the optimal breathing points, and controlling breathing by a patient according to the generated patient guiding voice; when the imaging requirement is met, imaging acquisition of the patient is carried out according to the optimal scanning scheme, and a corresponding imaging image is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410048192.7A CN117558428B (en) | 2024-01-12 | 2024-01-12 | Imaging optimization method and system for liver MRI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410048192.7A CN117558428B (en) | 2024-01-12 | 2024-01-12 | Imaging optimization method and system for liver MRI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117558428A CN117558428A (en) | 2024-02-13 |
| CN117558428B true CN117558428B (en) | 2024-03-22 |
Family
ID=89821941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410048192.7A Active CN117558428B (en) | 2024-01-12 | 2024-01-12 | Imaging optimization method and system for liver MRI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117558428B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117788461B (en) * | 2024-02-23 | 2024-05-07 | 华中科技大学同济医学院附属同济医院 | Magnetic resonance image quality evaluation system based on image analysis |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09299353A (en) * | 1996-05-10 | 1997-11-25 | Tadamichi Meguro | Vapor phase system respiratory function testing system for total health care in view of respiratory function and health care method using it |
| CN101305921A (en) * | 2007-05-17 | 2008-11-19 | 上海西门子医疗器械有限公司 | Method and device for implement CT respiration gate control |
| JP2012183431A (en) * | 2006-02-06 | 2012-09-27 | Toshiba Corp | Magnetic resonance imaging device |
| CN104739418A (en) * | 2014-11-24 | 2015-07-01 | 中国科学院苏州生物医学工程技术研究所 | Respiratory gating system and control method based on three-dimensional vision |
| WO2020111493A1 (en) * | 2018-11-28 | 2020-06-04 | 아주대학교산학협력단 | Device for predicting liver fibrosis by using ct image analysis and method therefor |
| CN114119798A (en) * | 2021-11-24 | 2022-03-01 | 郑州大学第一附属医院 | Radiographic image processing method and device based on respiratory motion |
| CN114176727A (en) * | 2021-12-10 | 2022-03-15 | 南京佗道医疗科技有限公司 | System for marking respiratory phase point in CT image and using method thereof |
| CN114359277A (en) * | 2022-03-18 | 2022-04-15 | 佛山科学技术学院 | Brain image processing method and system for stroke patient |
| CN114494320A (en) * | 2021-12-09 | 2022-05-13 | 华中科技大学同济医学院附属协和医院 | Three-dimensional MRI focus image segmentation method and system |
| CN114795268A (en) * | 2022-05-20 | 2022-07-29 | 上海联影医疗科技股份有限公司 | Intelligent respiratory navigation method, device and storage medium |
| CN114998179A (en) * | 2021-02-26 | 2022-09-02 | 西门子(深圳)磁共振有限公司 | Abdominal scanning method, system and storage medium |
| WO2023275163A1 (en) * | 2021-06-30 | 2023-01-05 | Koninklijke Philips N.V. | Breathing pattern extraction |
| CN116128838A (en) * | 2023-01-14 | 2023-05-16 | 苏州雷泰医疗科技有限公司 | Binocular vision-based respiratory detection system, 4D-CT image reconstruction system and method |
| CN116602649A (en) * | 2023-05-23 | 2023-08-18 | 大连医科大学附属第一医院 | Myocardial acquisition and quantitative analysis system based on PET-MR |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10033063A1 (en) * | 2000-07-07 | 2002-01-24 | Brainlab Ag | Respiration compensated radiation treatment tracks target volume using markers and switches beam |
| US7983735B2 (en) * | 2003-04-15 | 2011-07-19 | General Electric Company | Simulation of nuclear medical imaging |
| US20080269610A1 (en) * | 2007-04-25 | 2008-10-30 | General Electric Company | Method and apparatus for automatic optimization of scanning parameters for ultrasound imaging |
| US10499819B2 (en) * | 2013-01-08 | 2019-12-10 | Capnia, Inc. | Breath selection for analysis |
| US10531812B2 (en) * | 2013-01-16 | 2020-01-14 | Beth Israel Deaconess Medical Center, Inc. | System and method for improved cardiac imaging of subjects with adverse cardiac conditions |
| DE102016202605A1 (en) * | 2016-02-19 | 2017-08-24 | Siemens Healthcare Gmbh | Method for respiratory correlated computed tomographic image acquisition |
| DE102016213632A1 (en) * | 2016-07-26 | 2018-02-01 | Siemens Healthcare Gmbh | Improved acquisition of MR measurement data in a breath-hold study |
| US10909730B2 (en) * | 2017-01-13 | 2021-02-02 | Washington University | Free-breathing and self-navigated MRI method for deformable motion derivation |
-
2024
- 2024-01-12 CN CN202410048192.7A patent/CN117558428B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09299353A (en) * | 1996-05-10 | 1997-11-25 | Tadamichi Meguro | Vapor phase system respiratory function testing system for total health care in view of respiratory function and health care method using it |
| JP2012183431A (en) * | 2006-02-06 | 2012-09-27 | Toshiba Corp | Magnetic resonance imaging device |
| CN101305921A (en) * | 2007-05-17 | 2008-11-19 | 上海西门子医疗器械有限公司 | Method and device for implement CT respiration gate control |
| CN104739418A (en) * | 2014-11-24 | 2015-07-01 | 中国科学院苏州生物医学工程技术研究所 | Respiratory gating system and control method based on three-dimensional vision |
| WO2020111493A1 (en) * | 2018-11-28 | 2020-06-04 | 아주대학교산학협력단 | Device for predicting liver fibrosis by using ct image analysis and method therefor |
| CN114998179A (en) * | 2021-02-26 | 2022-09-02 | 西门子(深圳)磁共振有限公司 | Abdominal scanning method, system and storage medium |
| WO2023275163A1 (en) * | 2021-06-30 | 2023-01-05 | Koninklijke Philips N.V. | Breathing pattern extraction |
| CN114119798A (en) * | 2021-11-24 | 2022-03-01 | 郑州大学第一附属医院 | Radiographic image processing method and device based on respiratory motion |
| CN114494320A (en) * | 2021-12-09 | 2022-05-13 | 华中科技大学同济医学院附属协和医院 | Three-dimensional MRI focus image segmentation method and system |
| CN114176727A (en) * | 2021-12-10 | 2022-03-15 | 南京佗道医疗科技有限公司 | System for marking respiratory phase point in CT image and using method thereof |
| CN114359277A (en) * | 2022-03-18 | 2022-04-15 | 佛山科学技术学院 | Brain image processing method and system for stroke patient |
| CN114795268A (en) * | 2022-05-20 | 2022-07-29 | 上海联影医疗科技股份有限公司 | Intelligent respiratory navigation method, device and storage medium |
| CN116128838A (en) * | 2023-01-14 | 2023-05-16 | 苏州雷泰医疗科技有限公司 | Binocular vision-based respiratory detection system, 4D-CT image reconstruction system and method |
| CN116602649A (en) * | 2023-05-23 | 2023-08-18 | 大连医科大学附属第一医院 | Myocardial acquisition and quantitative analysis system based on PET-MR |
Non-Patent Citations (7)
| Title |
|---|
| Dynamic Liver Magnetic Resonance Imaging During Free Breathing: A Feasibility Study With a Motion Compensated Variable Density Radial Acquisition and a Viewsharing High-Pass Filtering Reconstruction;Christoph H-J Endler;https://pubmed.ncbi.nlm.nih.gov/35136004;20220701;全文 * |
| 一种PET/CT呼吸门控系统的设计;胡红波;邵高峰;丘志芬;;医疗卫生装备;20160215(02);全文 * |
| 一种适合低空机载平台SAR成像运动补偿方法;李杨寰;宋千;周智敏;;信号处理;20100425(04);全文 * |
| 介入式治疗中靶区呼吸运动实时跟踪技术;孙百权;程云章;蔡克尧;;中国医学物理学杂志;20180425(04);全文 * |
| 呼吸导航回波联合腹带加压在肝脏磁共振成像中的应用;关照坤;李新春;何建勋;孙鹏;伍筱梅;;中国CT和MRI杂志;20090420(02);全文 * |
| 呼吸门控下肺功能成像的临床应用;韩萍, 许景红, 杨帆, 冯敢生;同济医科大学学报;19990425(02);全文 * |
| 屏气B-FFE和呼吸门控B-TFE门静脉成像技术的比较研究;郭建锋;沈钧康;徐孝秋;钱铭辉;王玉红;刘金来;;临床放射学杂志;20070720(07);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117558428A (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111528859B (en) | Child ADHD screening and evaluating system based on multi-modal deep learning technology | |
| WO2020224123A1 (en) | Deep learning-based seizure focus three-dimensional automatic positioning system | |
| CN117558428B (en) | Imaging optimization method and system for liver MRI | |
| CN111839489B (en) | Non-contact physiological and psychological health detection system | |
| CN105246407A (en) | Image processing device and program | |
| US20070016109A1 (en) | Infant movement analysis system and infant movement analysis method | |
| CN109528217A (en) | A kind of mood detection and method for early warning based on physiological vibrations analysis | |
| CN109255354A (en) | medical CT-oriented computer image processing method and device | |
| CN114358194A (en) | Gesture tracking based detection method for abnormal limb behaviors of autism spectrum disorder | |
| CN113903082A (en) | Human body gait monitoring algorithm based on dynamic time planning | |
| CN106778047A (en) | A kind of traditional Chinese medical science facial diagnosis integrated system based on various dimensions medical image | |
| Ling et al. | Automatic tracking of aponeuroses and estimation of muscle thickness in ultrasonography: A feasibility study | |
| CN118044813B (en) | Psychological health condition assessment method and system based on multitask learning | |
| CN118213039B (en) | Rehabilitation training data processing method and system based on deep reinforcement learning | |
| CN110575178B (en) | Diagnosis and monitoring integrated medical system for judging motion state and judging method thereof | |
| CN114305418A (en) | Data acquisition system and method for depression state intelligent evaluation | |
| KR20190142618A (en) | Method for monitoring cardiac impulse of fetus and apparatus therefor | |
| CN110192860B (en) | Brain imaging intelligent test analysis method and system for network information cognition | |
| CN116152235A (en) | Cross-modal synthesis method for medical image from CT (computed tomography) to PET (positron emission tomography) of lung cancer | |
| US11786202B2 (en) | Method, system, and medium for analyzing image sequence of periodic physiological activity | |
| CN110693510A (en) | Attention deficit hyperactivity disorder auxiliary diagnosis device and using method thereof | |
| CN117409016B (en) | Automatic segmentation method for magnetic resonance image | |
| Zhang et al. | Auxiliary diagnostic system for ADHD in children based on AI technology | |
| KR20230083966A (en) | Teeth condition analyzing method and system based on deep learning | |
| Cheng et al. | Low rank self-calibrated brain network estimation and autoweighted centralized multi-task learning for early mild cognitive impairment diagnosis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |