CN113240078A - Deep learning network-based magnetic resonance R2*Parameter quantization method, medium, and apparatus - Google Patents

Deep learning network-based magnetic resonance R2*Parameter quantization method, medium, and apparatus Download PDF

Info

Publication number
CN113240078A
CN113240078A CN202110469551.2A CN202110469551A CN113240078A CN 113240078 A CN113240078 A CN 113240078A CN 202110469551 A CN202110469551 A CN 202110469551A CN 113240078 A CN113240078 A CN 113240078A
Authority
CN
China
Prior art keywords
magnetic resonance
deep learning
learning network
noise
image
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.)
Granted
Application number
CN202110469551.2A
Other languages
Chinese (zh)
Other versions
CN113240078B (en
Inventor
冯衍秋
陆琪琪
张鑫媛
连梓锋
王华峰
陈凌剑
龚剑
陈武凡
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.)
Southern Medical University
Original Assignee
Southern Medical University
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
Application filed by Southern Medical University filed Critical Southern Medical University
Priority to CN202110469551.2A priority Critical patent/CN113240078B/en
Publication of CN113240078A publication Critical patent/CN113240078A/en
Application granted granted Critical
Publication of CN113240078B publication Critical patent/CN113240078B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/30—Assessment of water resources

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

The invention discloses a magnetic resonance R2 parameter quantification method based on a deep learning network, which comprises the following steps: denoising the input magnetic resonance T2-weighted image using a first deep learning network; simultaneously, performing magnetic resonance R2 quantitative prediction on the magnetic resonance T2 weighted image subjected to noise processing by using a second deep learning network; the first deep learning network and the second deep learning network form a cascade network. The R2 parameter is quantized by using a deep learning algorithm, so that the complexity of the traditional algorithm is avoided, the quantization error is reduced, the calculation speed is increased, and the time required by calculation is shortened.

Description

Deep learning network-based magnetic resonance R2＊Parameter quantization method, medium, and apparatus
Technical Field
The invention belongs to the technical field of medical image processing, and particularly relates to a magnetic resonance R2 parameter quantification method, medium and equipment based on a deep learning network.
Background
Magnetic Resonance Imaging (MRI) is one of the important examination methods in clinical medical imaging. However, due to the limitation of the imaging mechanism, noise is inevitably introduced during the imaging process, mainly including random background noise and structural noise. Background noise is mainly composed of the resistance of the radio frequency coil, the electronic noise of the preamplifier, and dielectric loss and inductive loss in the imaged object (molecular motion, electromagnetic noise generated by charged particles in the human body). Noise in the image may degrade the quality of the image, causing deviations in the displayed signal values of the image, thereby affecting the quantification of other parameter values and, in turn, clinical diagnosis. Therefore, it is important for clinical diagnosis and image analysis that the parameter quantification method is insensitive to noise or can eliminate the influence of noise. Other researchers have proposed various methods for solving the noise-affected quantization result in R2-parameter quantization process, including denoising followed by voxel-wise parameter fitting quantization, and pixel-wise quantization combined with noise statistical model (M)1NCM), voxel-wise quantization with adaptive regularization using information of neighboring voxels (PCANR), and so on. However, most methods have problems of high computational complexity, long computation time, and degradation of quantization accuracy when noise is severe.
Disclosure of Invention
In order to overcome the technical defects, the invention provides a magnetic resonance R2 parameter quantification method based on a deep learning network in a first aspect, which comprises the following steps:
denoising the input magnetic resonance T2-weighted image using a first deep learning network;
meanwhile, a second deep learning network is used for predicting magnetic resonance R2 quantitative parameters of the de-noised magnetic resonance T2 weighted image;
the first deep learning network and the second deep learning network form a cascade network.
As a further improvement of the present invention, before the first deep learning network and the second deep learning network are used, the method further comprises the steps of:
and simultaneously training the first deep network learning network and the second deep network learning network until the networks converge, and verifying that the set loss is stable.
As a further improvement of the present invention, the step of training the first deep learning network and the second deep learning network simultaneously specifically includes the steps of:
performing joint training on the first deep learning network and the second deep learning network simultaneously by adopting a loss function, wherein the loss function is as follows:
Figure BDA0003039104020000021
wherein Φ represents a mapping relationship of the first deep learning network; u represents the mapping relation of the second deep learning network; y represents the input magnetic resonance T2 x weighted noise image at different TE times; x represents an image without noise or an image with good quality; lambda [ alpha ]1And λ2M is an analytical model of T2 attenuation, corresponding to the respective constraint coefficients.
As a further improvement of the present invention, before the step of training the first deep learning network and the second deep learning network at the same time, the method further includes the steps of:
calculating a noise-free multi-echo magnetic resonance T2 weighted image according to the acquired multi-echo magnetic resonance T2 weighted image by using a simulation method;
adding noise to the denoised magnetic resonance T2 weighted image to obtain a magnetic resonance T2 weighted image polluted by the noise;
the noise-free magnetic resonance T2-weighted image and the noise-contaminated magnetic resonance T2-weighted image jointly construct a training set for training a cascade network formed by the first deep learning network and the second deep learning network;
and respectively setting training parameters of the first deep learning network and the second deep learning network.
As a further improvement of the present invention, in the step of adding noise to the denoised image to obtain the magnetic resonance T2 weighted image contaminated by noise, at least one of white noise, gaussian noise, rice noise and non-central chi-square distribution noise is added to the denoised magnetic resonance T2 weighted image.
As a further improvement of the present invention, the step of calculating a noise-free magnetic resonance T2 weighted image from the acquired multi-echo magnetic resonance T2 weighted image by using a simulation method specifically includes the steps of:
denoising the acquired magnetic resonance T2 weighted image by using a traditional denoising method;
calculating parameters by using a traditional least square fitting parameter quantification method to obtain a parameter map;
and obtaining a noise-free magnetic resonance T2 weighted image according to a specific model corresponding to the image acquisition protocol.
As a further improvement of the invention, the first deep learning network and the second deep learning network are jointly trained by adopting a Patch method.
As a further development of the invention, the magnetic resonance T2-weighted images are magnetic resonance T2-weighted images acquired at different echo times.
Compared with the prior art, the invention has the following beneficial effects:
the R2 parameter is quantized by using a deep learning algorithm, so that the complexity of the traditional algorithm is avoided, the quantization error is reduced, the calculation speed is increased, and the time required by calculation is shortened.
In a second aspect of the invention, a computer-readable storage medium is provided, which stores a computer program, which, when executed by a processor, causes the processor to carry out the magnetic resonance R2 parameter quantification method described above.
In a third aspect of the invention, a computer device is provided, comprising a processor and a memory; the memory for storing a computer program; the processor is configured to execute the computer program and to implement the magnetic resonance R2 parameter quantification method described above when the computer program is executed.
Drawings
Embodiments of the invention are described in further detail below with reference to the attached drawing figures, wherein:
fig. 1 is an overall block diagram of a magnetic resonance R2 parameter quantification method according to example 1;
FIG. 2 is a diagram showing the layout of a Denoising deep learning network (first deep learning network for Denoising) and a Mapping deep learning network (second deep learning network for parameter quantization) in embodiment 1;
fig. 3 is a diagram illustrating the technical effects obtained in the embodiment 1.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1
The embodiment discloses a magnetic resonance R2 parameter quantification method based on a deep learning network, as shown in fig. 1 and fig. 2, including the steps of:
s1, denoising the input magnetic resonance T2-weighted image using a first deep learning network, T2 being the effective transverse relaxation time.
Specifically, the input magnetic resonance T2 weighted image is acquired by magnetic resonance acquisition. The input magnetic resonance T2 x-weighted image may be a magnitude image, a "real-valued" image, or a "complex-valued" image, each pixel of which reflects the magnitude, real-valued, or complex value of the MR signal at the corresponding voxel location.
In some embodiments, the input magnetic resonance T2 x weighted image is obtained by fourier transforming the acquired k-space data.
In some embodiments, the acquired k-space data is pre-processed prior to fourier transformation.
In some embodiments, the fourier transformed data is processed to obtain an input magnetic resonance T2 x-weighted image, which may include any suitable processing during the reconstruction process or a combination thereof. The input magnetic resonance T2 x weighted image may have any size, e.g. 64 x 128 pixels, 128 x 128 pixels, 256 x 256 pixels, 512 x 512 pixels, etc.
Due to a number of factors, different levels, different sources, and different distributions of noise may be generated during the acquisition of the input images. The noise is mainly derived from random background noise (e.g., white noise, gaussian noise, rice noise or noise distributed in a non-central chi-square manner), which may be caused by the resistance of the rf coil, the electronic noise of the preamplifier or the dielectric effect of the imaging object itself, so that the denoising process is required.
The first deep learning network may employ a Denoising deep learning network comprising a plurality of convolutional layers, each layer having one or more input channels and one or more output channels. The parameters of the convolution kernel of each convolution layer are learnable, and the values obtained after convolution are transmitted to the activation function, so that the output of the activation function is used as a response.
In some embodiments, the activation function may be a ReLU function, including: normal ReLU function, leaky ReLU function, parametric ReLU function, etc. The input image is received by the first convolutional layer.
In some embodiments, there are one or more convolutional layers between the first convolutional layer and the last convolutional layer. Note that only 8 convolutional layers are shown in fig. 2 for illustration in the exemplary embodiment. In an example embodiment, the Denoising deep learning network is a residual network. It should be noted that the layout of the deep learning network shown in FIG. 2 is for illustration and not for limitation, and any other suitable configuration may be used herein.
S2, the second deep learning network is used to perform magnetic resonance R2 quantitative prediction on the denoised magnetic resonance T2 weighted image, where R2 is the reciprocal of T2, in other words, the parameter quantization in this embodiment is implemented by connecting the first deep learning network and the second deep learning network in series, and the first deep learning network and the second deep learning network are used cooperatively.
The second deep learning network may employ a Mapping deep learning network that includes a plurality of convolutional layers, each layer having one or more input channels and one or more output channels. The parameters of the convolution kernel of each convolution layer are learnable, and the values obtained after convolution are transmitted to the activation function, so that the output of the activation function is used as the corresponding.
In some embodiments, the activation function may be a ReLU function, including: normal ReLU function, leaky ReLU function, parametric ReLU function, etc. The input image is received by the first convolutional layer. In an example embodiment, the Mapping deep learning network is a 6-layer UNet convolutional neural network, comprising an encoder portion and a decoder portion, each having three convolutional layers. The decoder section transforms the image features extracted by the encoder into a parametric image of pixels.
In some embodiments, the number of layers of convolutional layers is not limited to that shown in the example embodiments, while it should be noted that the deep-learning network layout shown in fig. 2 is for illustration and not for limitation, and any other suitable configuration may be used herein.
And S3, the first deep learning network and the second deep learning network form a cascade network.
In the above embodiment, before using the first deep learning network and the second deep learning network, the method further includes:
using the simulation data, the first and second deep learning networks are iteratively trained simultaneously, e.g., different distribution types, different levels of noise may be added to the noise-free simulation image or the multiple TE-time magnetic resonance T2 x-weighted image with good quality to obtain a composite noise-contaminated image. The type of distribution of the noise depends on the hardware and software parameters of the magnetic resonance being imaged. And taking the synthesized image with noise as an input image and taking the magnetic resonance image without noise or with good quality as an output to jointly train the first deep learning network and the second deep learning network. And training the first deep learning network and the second deep learning network until the networks converge, and stopping iteration when the loss of the verification set is stable.
In the above embodiment, the step of training the first deep learning network and the second deep learning network simultaneously specifically includes the steps of:
and (3) performing joint training on the first deep learning network and the second deep learning network by adopting a loss function, wherein the loss function is as follows:
Figure BDA0003039104020000051
wherein Φ represents a mapping relationship of a Denoising deep learning network (i.e. a first deep learning network); u represents the Mapping relation of Mapping deep learning network (namely second deep learning network); y represents the input magnetic resonance T2 x weighted noise image at different TE times; x represents an image without noise or an image with good quality; lambda [ alpha ]1And λ2M is an analytical model of T2 attenuation, corresponding to the respective constraint coefficients.
Figure BDA0003039104020000052
In the above embodiment, before the step of training the first deep learning network and the second deep learning network at the same time, the method further includes the steps of:
calculating a noise-free multi-echo magnetic resonance T2 weighted image according to the acquired multi-echo magnetic resonance T2 weighted image by using a simulation method;
adding noise to the denoised magnetic resonance T2 weighted image to obtain a magnetic resonance T2 weighted image contaminated by noise, specifically: adding at least one of white noise, Gaussian noise, Rice noise and non-central chi-square distributed noise into the denoised magnetic resonance T2-weighted image;
the noise-free magnetic resonance T2-weighted image and the noise-contaminated magnetic resonance T2-weighted image jointly construct a training set for training a cascade network formed by a first deep learning network and a second deep learning network;
and respectively setting training parameters of the first deep learning network and the second deep learning network.
In the above embodiment, the step of calculating a noise-free magnetic resonance T2 weighted image according to the acquired multi-echo magnetic resonance T2 weighted image by using the simulation method specifically includes the steps of:
denoising the acquired magnetic resonance T2 weighted image by using a traditional denoising method;
calculating parameters by using a traditional least square fitting parameter quantification method to obtain a parameter map;
and obtaining a noise-free magnetic resonance T2 weighted image according to a specific model corresponding to the image acquisition protocol.
In the above embodiment, the method of Patch is adopted to train the first deep learning network and the second deep learning network.
In the above described embodiment, the magnetic resonance T2 x weighted image is a magnetic resonance T2 x weighted image acquired at different echo times.
The effect graph obtained by the magnetic resonance R2 parameter quantification method of the present embodiment is shown in fig. 3, wherein the 1 st column image is a clinical magnetic resonance T2 weighted image at different liver iron deposition levels, including four iron deposition levels of normal (normal), mild (millid), moderate (normal) and severe (severe). Columns 2-4 are R2 x parametric images calculated by different methods, respectively. M1NCM is a traditional least square fitting algorithm based on a noise model; PCANR is a traditional self-adaptive neighborhood regularization voxel-by-voxel quantization algorithm; cadamNet (Cascade of differentiating and ma)pping networks) is the magnetic resonance R2 parameter quantization method of this embodiment, and thus it can be seen that the effect of noise on the result is small, and the accuracy of the quantization result is improved. As can be seen from fig. 3, the R2 image obtained by the method of the present invention is similar to the conventional method as a whole, but the framework is smooth and uniform, and the error is smaller; the R2 parameter is quantified by using a deep learning algorithm, so that the complexity of the traditional algorithm is avoided, the calculation speed is increased, and the time required by calculation is shortened.
Example 2
The embodiment discloses a computer device, which comprises a processor and a memory; the memory for storing a computer program; the processor is configured to execute the computer program and, when executing the computer program, implement the magnetic resonance R2 parameter quantification method in embodiment 1.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable storage media, which may include computer readable storage media (or non-transitory media) and communication media (or transitory media).
The term computer-readable storage medium includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer-readable storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
For example, the computer readable storage medium may be an internal storage unit of the network management device in the foregoing embodiment, for example, a hard disk or a memory of the network management device. The computer readable storage medium may also be an external storage device of the network management device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are equipped on the network management device.
Example 3
The embodiment discloses a computer device, which comprises a processor and a memory; the memory for storing a computer program; the processor is configured to execute the computer program and, when executing the computer program, implement the magnetic resonance R2 parameter quantification method in embodiment 1.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, so that any modification, equivalent change and modification made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.

Claims (10)

1. The magnetic resonance R2 parameter quantification method based on the deep learning network is characterized by comprising the following steps:
denoising the input magnetic resonance T2-weighted image using a first deep learning network;
meanwhile, a second deep learning network is used for predicting magnetic resonance R2 quantitative parameters of the de-noised magnetic resonance T2 weighted image;
the first deep learning network and the second deep learning network form a cascade network.
2. The method of quantifying R2 parameters of claim 1, wherein the method further comprises, before using the first and second deep learning networks, the steps of:
and simultaneously training the first deep network learning network and the second deep network learning network until the networks converge, and verifying that the set loss is stable.
3. The method of quantifying R2 parameters according to claim 2, wherein the step of simultaneously training the first deep learning network and the second deep learning network specifically comprises the steps of:
performing joint training on the first deep learning network and the second deep learning network simultaneously by adopting a loss function, wherein the loss function is as follows:
Figure FDA0003039104010000011
wherein Φ represents a mapping relationship of the first deep learning network; u represents the mapping relation of the second deep learning network; y represents the input magnetic resonance T2 at different TE times plusA weighted noise image; x represents an image without noise or an image with good quality; lambda [ alpha ]1And λ2M is an analytical model of T2 attenuation, corresponding to the respective constraint coefficients.
4. The method of magnetic resonance R2 parameter quantification according to claim 2, wherein the step of simultaneously training the first deep learning network and the second deep learning network further comprises the steps of:
calculating a noise-free multi-echo magnetic resonance T2 weighted image according to the acquired multi-echo magnetic resonance T2 weighted image by using a simulation method;
adding noise to the denoised magnetic resonance T2 weighted image to obtain a magnetic resonance T2 weighted image polluted by the noise;
the noise-free magnetic resonance T2-weighted image and the noise-contaminated magnetic resonance T2-weighted image jointly construct a training set for training a cascade network formed by the first deep learning network and the second deep learning network;
and respectively setting training parameters of the first deep learning network and the second deep learning network.
5. The method of claim 4, wherein the step of adding noise to the denoised image to obtain the noise-contaminated magnetic resonance T2-weighted image includes adding at least one of white noise, Gaussian noise, Rice noise, and non-centered chi-squared noise to the denoised magnetic resonance T2-weighted image.
6. The magnetic resonance R2 parameter quantification method as claimed in claim 4, wherein the step of using the simulation method to calculate a noise-free magnetic resonance T2 weighted image from the acquired multi-echo magnetic resonance T2 weighted image comprises the steps of:
denoising the acquired magnetic resonance T2 weighted image by using a traditional denoising method;
calculating parameters by using a traditional least square fitting parameter quantification method to obtain a parameter map;
and obtaining a noise-free magnetic resonance T2 weighted image according to a specific model corresponding to the image acquisition protocol.
7. The method of claim 2, wherein the first deep learning network and the second deep learning network are jointly trained by using a Patch method.
8. The method of magnetic resonance T2 parameter quantification of claim 1, wherein the magnetic resonance T2 weighted images are magnetic resonance T2 weighted images acquired at different echo times.
9. Computer readable storage medium, characterized in that it stores a computer program which, when executed by a processor, causes the processor to implement the magnetic resonance R2 parameter quantification method as claimed in any one of claims 1 to 8.
10. Computer apparatus comprising a processor and a memory; the memory for storing a computer program; the processor for executing the computer program and for implementing the magnetic resonance R2 parameter quantification method of any one of claims 1 to 8 when executing the computer program.
CN202110469551.2A 2021-04-26 2021-04-26 Magnetic resonance R2 based on deep learning network * Parameter quantization method, medium and device Active CN113240078B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110469551.2A CN113240078B (en) 2021-04-26 2021-04-26 Magnetic resonance R2 based on deep learning network * Parameter quantization method, medium and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110469551.2A CN113240078B (en) 2021-04-26 2021-04-26 Magnetic resonance R2 based on deep learning network * Parameter quantization method, medium and device

Publications (2)

Publication Number Publication Date
CN113240078A true CN113240078A (en) 2021-08-10
CN113240078B CN113240078B (en) 2024-03-19

Family

ID=77131286

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110469551.2A Active CN113240078B (en) 2021-04-26 2021-04-26 Magnetic resonance R2 based on deep learning network * Parameter quantization method, medium and device

Country Status (1)

Country Link
CN (1) CN113240078B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6605943B1 (en) * 1999-08-24 2003-08-12 Inner Vision Biometrics Pty Ltd Method of mapping proton transverse relaxation time constants or functions thereof in a target subject to localised movement using nuclear magnetic resonance imaging
US20120268121A1 (en) * 2011-04-19 2012-10-25 Diego Hernando Method for r*2 quantification with magnetic resonance imaging
CN103218788A (en) * 2013-04-24 2013-07-24 南方医科大学 Method for measuring liver magnetic resonance crosswise relaxation rate R2* parameter
CN103714521A (en) * 2013-12-30 2014-04-09 南方医科大学 Liver R2* graph measuring method based on inquiry table
CN105608681A (en) * 2016-02-14 2016-05-25 电子科技大学 Liver magnetic resonance R2* parameter graph drafting method
CN108663644A (en) * 2018-03-14 2018-10-16 厦门大学 Single sweep Quantitative MRI Measurement T based on residual error network reconnection2* imaging method
CN110163812A (en) * 2019-04-10 2019-08-23 深圳大学 Muscle ultrasonic image denoising method, apparatus, storage medium and computer product
CN110782452A (en) * 2019-11-05 2020-02-11 厦门大学 T2 quantitative image imaging method and system
US20200345311A1 (en) * 2019-04-30 2020-11-05 Samsung Electronics Co., Ltd. Magnetic resonance imaging apparatus for generating parametric map from magnetic resonance signal data and method of operating the same
CN111915007A (en) * 2020-07-29 2020-11-10 厦门大学 Magnetic resonance spectrum noise reduction method based on neural network

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6605943B1 (en) * 1999-08-24 2003-08-12 Inner Vision Biometrics Pty Ltd Method of mapping proton transverse relaxation time constants or functions thereof in a target subject to localised movement using nuclear magnetic resonance imaging
US20120268121A1 (en) * 2011-04-19 2012-10-25 Diego Hernando Method for r*2 quantification with magnetic resonance imaging
CN103218788A (en) * 2013-04-24 2013-07-24 南方医科大学 Method for measuring liver magnetic resonance crosswise relaxation rate R2* parameter
CN103714521A (en) * 2013-12-30 2014-04-09 南方医科大学 Liver R2* graph measuring method based on inquiry table
CN105608681A (en) * 2016-02-14 2016-05-25 电子科技大学 Liver magnetic resonance R2* parameter graph drafting method
CN108663644A (en) * 2018-03-14 2018-10-16 厦门大学 Single sweep Quantitative MRI Measurement T based on residual error network reconnection2* imaging method
CN110163812A (en) * 2019-04-10 2019-08-23 深圳大学 Muscle ultrasonic image denoising method, apparatus, storage medium and computer product
US20200345311A1 (en) * 2019-04-30 2020-11-05 Samsung Electronics Co., Ltd. Magnetic resonance imaging apparatus for generating parametric map from magnetic resonance signal data and method of operating the same
CN110782452A (en) * 2019-11-05 2020-02-11 厦门大学 T2 quantitative image imaging method and system
CN111915007A (en) * 2020-07-29 2020-11-10 厦门大学 Magnetic resonance spectrum noise reduction method based on neural network

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
CHANGQING WANG ET AL: "Improved Liver R*2 Mapping by Pixel-Wise Curve Fitting With Adaptive Neighborhood Regularization", MAGNETIC RESONANCE IN MEDICINE, vol. 80, pages 792 - 801 *
MEIYAN FENG ET AL: "Optimal region-of-interest MRI R2* measurements for the assessment of hepatic iron content in thalassaemia major", MAGNETIC RESONANCE IMAGING, pages 647 - 653 *
QIQI LU ET AL: "Cascade of Denoising and Mapping Neural Networks for MRI R2* Relaxometry of Iron-Loaded Liver", BIOENGINEERING, vol. 10, no. 2, pages 10 *
刘可文 等: "基于级联卷积神经网络的前列腺磁共振图像分类", 波谱学杂志, vol. 37, no. 2, pages 152 - 161 *

Also Published As

Publication number Publication date
CN113240078B (en) 2024-03-19

Similar Documents

Publication Publication Date Title
Jiang et al. Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network
Kwon et al. A parallel MR imaging method using multilayer perceptron
Pierre et al. Multiscale reconstruction for MR fingerprinting
US11080897B2 (en) Systems and methods for a PET image reconstruction device
Chung et al. MR image denoising and super-resolution using regularized reverse diffusion
Song et al. Coupled dictionary learning for multi-contrast MRI reconstruction
Luo et al. MRI reconstruction using deep Bayesian estimation
Shi et al. Parallel imaging and compressed sensing combined framework for accelerating high‐resolution diffusion tensor imaging using inter‐image correlation
Coupé et al. 3D wavelet subbands mixing for image denoising
Eun et al. Deep-learning-based image quality enhancement of compressed sensing magnetic resonance imaging of vessel wall: comparison of self-supervised and unsupervised approaches
You et al. Denoising of MR images with Rician noise using a wider neural network and noise range division
Pal et al. Rician noise removal in magnitude MRI images using efficient anisotropic diffusion filtering
Baselice et al. A 3D MRI denoising algorithm based on Bayesian theory
Wang et al. High‐field mr diffusion‐weighted image denoising using a joint denoising convolutional neural network
Pawar et al. A deep learning framework for transforming image reconstruction into pixel classification
Wang et al. Denoising auto-encoding priors in undecimated wavelet domain for MR image reconstruction
Tripathi et al. Denoising of magnetic resonance images using discriminative learning-based deep convolutional neural network
US11222406B2 (en) Method and system for training a machine learning-based image denoising system
CN113240078B (en) Magnetic resonance R2 based on deep learning network * Parameter quantization method, medium and device
Islam et al. Compressed sensing regularized calibrationless parallel magnetic resonance imaging via deep learning
Ryu et al. Accelerated multicontrast reconstruction for synthetic MRI using joint parallel imaging and variable splitting networks
US11941732B2 (en) Multi-slice MRI data processing using deep learning techniques
Kwon et al. Multi‐contrast MR image denoising for parallel imaging using multilayer perceptron
EP4024074A1 (en) Enforcement of data-consistency in deep-learning reconstruction of magnetic resonance images
CN114612656A (en) MRI image segmentation method and system based on improved ResU-Net neural network

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