Physical base model multi-part high-definition diffusion magnetic resonance imaging method

Abstract

The invention discloses a physical basis model multi-part high-definition diffusion magnetic resonance imaging method, and relates to a multi-excitation plane echo diffusion magnetic resonance imaging method. Comprising the following steps: 1) acquiring k space data of diffusion magnetic resonance imaging to be reconstructed acquired by a multi-excitation plane echo sequence; 2) designing a bidirectional one-dimensional low-rank reconstruction model based on a local smooth phase; 3) generating data by using a physical diffusion model; 4) training the base model neural network by using the physical generation data; 5) solving a bidirectional one-dimensional low-rank reconstruction model; and 6) in combination with reconstruction parameters prompted by the basis model neural network, generalization reconstruction is carried out to obtain high-definition diffusion magnetic resonance images of various parts without motion artifacts. According to the method, robust high-definition magnetic resonance diffusion imaging of a plurality of challenge parts without parameter adjustment is realized through a bidirectional one-dimensional low-rank optimization reconstruction method and neural network adaptive optimization reconstruction parameters.

Description

Technical Field

[0001] The present invention relates to a method for reconstructing multi-body high-definition diffusion magnetic resonance images, and in particular to a physical-based model multi-body high-definition diffusion magnetic resonance imaging method for multi-excitation echo-planar diffusion magnetic resonance images of phase-complex parts such as the abdomen and pelvis. Background Art

[0002] Diffusion magnetic resonance imaging is a non-ionizing, non-invasive technology for detecting the diffusion of water molecules in living biological tissues. It plays an important role in studying and detecting diseases in multiple parts of the body, such as brain function, tumors, and arthritis.

[0003] Conventional single-shot echo-planar imaging (ss-EPI) is a diffusion imaging method commonly used in clinical diagnosis. While fast, it is sensitive to field inhomogeneities, resulting in severe image distortion. Furthermore, image resolution is limited by the length of the echo train. To reduce distortion and improve resolution, multi-shot EPI uses multiple excitations to fill k-space, shortening the echo train to reduce distortion and improve resolution and signal-to-noise ratio. However, subject motion can introduce phase errors between excitations, leading to image artifacts.

[0004] Multi-shot diffusion imaging (MUSE) has been developed in recent years, but areas with complex motion remain understudied. Methods such as MUSE (N. Chen et al., "A robust multi-shot scan strategy for high-resolution diffusion weighted MRI enabled by multiplexed sensitivity-encoding (MUSE)" published in Neuroimage, Vol. 72, pp. 41-47, May 15, 2013) and MUSSELS (M. Mani et al., "Multi-shot sensitivity-encoded diffusion data recovery using structured low-rank matrix completion (MUSSELS)" published in Magnetic Resonance in Medicine, Vol. 78, No. 2, pp. 494-507, August 23, 2016) have demonstrated good reconstruction results in the brain, but struggle to reconstruct high-quality images in the abdomen. DONATE ("Fast and ultra-high shot diffusion MRI image reconstruction with self-adaptive Hankel subspace" by C. Qian, et al., published in Medical Image Analysis, Vol. 102, p. 103546, May 2025) achieves high-definition reconstruction of the brain with ultra-high shot counts. However, reconstructions of complex phase-determined regions (such as the eyes, skull, abdomen, and pelvis) can result in artifact correction in some layers and diffusion directions. Existing methods are not robust to complex phase data and require adjustment of reconstruction parameters for specific layers or directions.

[0005] To improve reconstruction robustness, a single reconstruction parameter is used to achieve high-quality, robust reconstruction across all planes and directions. This robustness is enhanced by an artificial intelligence network based on generated data. PIDD (C. Qian et al., "Physics-informed deep diffusion MRI reconstruction: Breaking the bottleneck of training data in artificial intelligence," presented at the 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Cartagena, Colombia, pp. 1-5, 2023)) utilizes a high-order phase model to generate data with complex phases, enabling robust, high-quality brain image reconstruction. However, in complex phase regions, such as the abdomen, where different organs have significant phase differences, PIDD can cause signal loss, making robust reconstruction of challenging areas like the abdomen impossible. Summary of the Invention

[0006] The purpose of the present invention is to address the problems existing in the prior art of multi-excitation diffusion magnetic resonance imaging, such as incomplete correction of motion artifacts in phase-complex areas (such as the abdomen and pelvis), insufficient image reconstruction robustness, the need to manually adjust reconstruction parameters for different areas or levels, and the susceptibility of existing methods to signal loss. The present invention provides a physical-based model multi-area high-definition diffusion magnetic resonance imaging method that combines a physical-based model with a neural network to achieve adaptive optimization of parameters and robustly reconstruct high-definition, artifact-free images of multiple areas without manual adjustment, thereby achieving robust, high-quality multi-body high-definition diffusion magnetic resonance imaging.

[0007] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions.

[0008] The present invention provides a physical-based model multi-site high-definition diffusion magnetic resonance imaging method, comprising the following steps:

[0009] 1) Acquire k-space data of diffusion MRI to be reconstructed using a multi-shot echo-planar sequence for high-definition diffusion imaging reconstruction of multiple sites;

[0010] 2) Designing a bidirectional one-dimensional low-rank reconstruction model based on local smooth phase; the model includes a two-dimensional Fourier transform operator, a channel sensitivity operator, a structured low-rank matrix extraction operator, and a nuclear norm constraint term to characterize the low-rank characteristics of multi-shot data;

[0011] 3) Data generation using physical diffusion models, including: acquiring amplitude images using multi-organ phantoms, generating complex phase data of corresponding orders for different organs, and combining amplitude and phase to generate noisy and noise-free fully sampled multi-shot k-space data;

[0012] 4) Using physically generated data to train the base model neural network; by converting the noisy k-space data into a structured low-rank matrix and performing singular value decomposition, the neural network learns the optimal singular value cutoff parameters;

[0013] 5) Solve the bidirectional one-dimensional low-rank reconstruction model and achieve signal recovery by preserving the key singular values and corresponding subspaces of the structured low-rank matrix;

[0014] 6) Combined with the reconstruction parameters suggested by the base model neural network, multi-excitation k-space data are generalized to reconstruct high-definition diffusion magnetic resonance images of various parts without motion artifacts.

[0015] In step 1), the k-space data of the diffusion magnetic resonance imaging to be reconstructed acquired by the multi-excitation echo-planar sequence is acquired, specifically: the k-space data of the diffusion magnetic resonance imaging to be reconstructed is acquired by the multi-excitation echo-planar sequence ,in represents the k-space data collected by the c-th coil during the j-th excitation, , ; represents a complex set; represents multiplication; M, N, J, and C represent the frequency encoding number, phase encoding number, total number of excitations, and total number of coil channels, respectively.

[0016] In step 2), the bidirectional one-dimensional low-rank reconstruction model is:

[0017]

[0018] in, is the k-space data of diffusion magnetic resonance imaging to be reconstructed; is the sampling template of the multi-excitation sequence; and They are the two-dimensional Fourier transform and its inverse transform; It is the channel sensitivity operator, which saves the sensitivity information of multiple channels; is the multi-shot data to be reconstructed, and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; and The phase coding line and the frequency coding line are respectively subjected to one-dimensional inverse Fourier transform operations, represents the Frobenius norm of the matrix; represents the nuclear norm of the matrix; 、 and is the weight coefficient; M represents the frequency encoding number, and N represents the phase encoding number.

[0019] In step 3), the data is generated using a physical diffusion model, specifically by acquiring amplitude images using a phantom comprising gray matter, white matter, spine, spinal cord, adrenal glands, liver, gallbladder, stomach, pancreas, spleen, colon, kidneys, ureters, arteries, veins, muscles, bones, joints, fat, and skin.

[0020]

[0021] Among them, m o They represent the amplitude of the oth part, and there are O parts in total; Represents the mask of the o-th part; m is the amplitude map of a layer composed of various parts;

[0022] Generate complex phases of all excitations of multiple organs based on high-order phase models , where the phase of the j-th excitation is:

[0023]

[0024] Where m, n are image coordinates; L o is the order of the generated phase of the o-th position (o=1,2,…,O); The mask representing the oth part; is the parameter of the generation phase of the oth part;

[0025] The generated phase is used to further generate full-sampled multi-shot k-space data, including generating noise-free multi-shot k-space data X GT and generate the noisy multi-shot k-space data X Inp :

[0026]

[0027]

[0028] in, is the generated multi-excitation motion phase; is the amplitude image; and are two-dimensional Fourier transform and its inverse transform respectively; N is noise.

[0029] In step 4), the base model neural network is trained using physically generated data; the generated noisy multi-shot k-space data X Inp Convert to a structured low-rank matrix and perform singular value decomposition:

[0030]

[0031]

[0032] in, and These are the operations of performing one-dimensional inverse Fourier transform on the phase-encoded lines and the frequency-encoded lines; and Extract the frequency-coded lines and Phase encoding rows and converting them into structured low-rank matrices; SVD is the singular value decomposition; 、 、 are the left singular matrix, singular values, and right singular matrix of the structured matrix constructed from frequency-encoded data; 、 、 are the left singular matrix, singular values, and right singular matrix of the structured matrix constructed by phase encoding data; X Inp is the generated noisy multi-shot k-space data;

[0033] The base model neural network learns the singular value truncation parameters of the structured low-rank matrix based on the generated data, that is, the number of singular values optimally retained in the frequency encoding direction and phase encoding structured low-rank matrix and , so that the noisy signal has the highest peak signal-to-noise ratio after being restored by singular value truncation:

[0034]

[0035]

[0036] in, and These are the operations of performing one-dimensional inverse Fourier transform on the phase-encoded lines and the frequency-encoded lines; and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; 、 、 are the left singular matrix, singular values, and right singular matrix of the structured matrix constructed from frequency-encoded data; 、 、 are the left singular matrix, singular value, and right singular matrix of the structured matrix constructed by phase encoding data; M and N are the frequency encoding number and phase encoding number respectively; X GT It is noise-free multi-shot k-space data; Represents matrix multiplication; represents the Frobenius norm of the matrix;

[0037] Physically based neural network models It is a data-driven supervised artificial intelligence neural network based on gradient back propagation, and its loss function is:

[0038]

[0039] Among them, the input of the neural network is a paired one-dimensional input signal and ; The network's labels are frequency-encoded direction and phase-encoded structured low-rank matrix. The optimal number of retained singular values and ; and They represent the operators for selecting the mth frequency coding row and the nth phase coding row respectively; and are the one-dimensional inverse Fourier transform operations on the phase encoding line and the frequency encoding line respectively; T is the total number of training samples; is the optimal weight parameter; M represents the frequency encoding number, and N represents the phase encoding number; represents the Frobenius norm of the matrix; X Inp is the generated noisy multi-shot k-space data.

[0040] In step 5), the bidirectional one-dimensional low-rank reconstruction model uses singular value truncation to solve the nuclear norm; the low-rank matrix is constrained using singular value truncation and for and ,in Represents a low-rank matrix Perform singular value truncation and retain the first r largest singular values and the corresponding subspace to recover the signal; and These are the operations of performing one-dimensional inverse Fourier transform on the phase-encoded lines and the frequency-encoded lines; and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; is the multi-shot data to be reconstructed.

[0041] In step 6), the optimal parameters are truncated using the low-rank matrix singular values suggested by the base model neural network and Perform singular value truncation to achieve robust high-definition reconstruction.

[0042] Compared with the prior art, the present invention has the following outstanding technical effects and advantages:

[0043] 1. The present invention designs a bidirectional one-dimensional low-rank reconstruction model and combines it with local smooth phase constraints to perform targeted correction of phase errors and artifacts caused by inter-excitation motion in multi-excitation sequences. In particular, the reconstruction effect of complex phase areas such as the abdomen and pelvis is significantly better than that of existing low-rank algorithms (such as MUSE and MUSSELS), and can eliminate residual artifacts.

[0044] 2. The present invention generates phases of different orders for different organs and phase data for multiple organs. It constructs a physical-based model neural network based on the physical diffusion model and learns adaptive optimization of reconstruction parameters by training the neural network to achieve stable reconstruction in all levels and directions under a single parameter setting. This eliminates the need to manually adjust parameters for different parts or levels, and addresses the problem of insufficient robustness of existing methods (such as DONATE).

[0045] 3. The present invention uses a physical-based model neural network to accurately learn the signal characteristics of complex phase areas, maintaining signal integrity in multiple organ locations with large phase differences (such as the junction of the liver and intestine in the abdomen), overcoming the defect of existing methods such as PIDD that are prone to signal loss in complex phase scenarios.

[0046] 4. The present invention adopts a bidirectional one-dimensional low-rank model to strengthen local low-rank constraints, and combines the optimal singular value truncation parameters suggested by the neural network to achieve generalized reconstruction of multiple parts such as the brain, neck, and joints while improving image resolution, taking into account high-definition quality and applicability to multiple parts. Through the bidirectional one-dimensional low-rank optimization reconstruction method and the neural network adaptive optimization parameters, robust high-definition magnetic resonance diffusion imaging of multiple challenging parts is achieved without adjusting parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 The image shows the multi-excitation merged data of the kidney (left) and the reconstruction result (right) achieved with 2-times equally spaced undersampling based on a physical-based model multi-site high-definition diffusion magnetic resonance imaging method.

[0048] Figure 2 This is the liver multi-excitation merged data (left) and reconstruction results (right) of 2-excitation 2-fold equally spaced undersampling based on a physical-based model multi-site high-definition diffusion magnetic resonance imaging method.

[0049] Figure 3 Figure 2 shows the prostate multi-excitation merged data (left) and reconstruction results (right) achieved using a physical-based model multi-site high-definition diffusion MRI method.

[0050] Figure 4 This is the four-shot sacroiliac joint multi-excitation merged data (left) and reconstruction results (right) achieved based on a physical-based model multi-site high-definition diffusion MRI method.

[0051] Figure 5 This is the four-shot neck multi-excitation merged data (left) and the reconstruction result (right) achieved based on a physical-based model multi-site high-definition diffusion MRI method.

[0052] Figure 6 This is the four-shot brain multi-excitation merged data (left) and reconstruction results (right) achieved based on a physical-based model multi-site high-definition diffusion magnetic resonance imaging method.

[0053] Figure 7 This is the double-excitation knee joint multi-excitation merged data (left) and reconstruction results (right) achieved based on a physical-based model multi-site high-definition diffusion magnetic resonance imaging method. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the following embodiments will be further described in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0055] The embodiment of the present invention uses a physical-based model multi-site high-definition diffusion magnetic resonance imaging method proposed by the present invention to reconstruct the data of multiple body parts with 2 excitations (abdomen, pelvis, knee joint) and 4 excitations (brain, spinal cord, sacroiliac joint). Figures 1 to 7 , the method of the present invention is described in detail.

[0056] This embodiment includes the following steps:

[0057] 1) Acquire k-space data for diffusion MRI to be reconstructed using a multi-shot echo-planar sequence ,in represents the k-space data collected by the c-th coil during the j-th excitation, , ; represents a complex set; represents multiplication; M, N, J, and C represent the frequency encoding number, phase encoding number, total number of excitations, and total number of coil channels, respectively.

[0058] 2) The bidirectional one-dimensional low-rank reconstruction model is:

[0059]

[0060] in is the sampling template of the multi-excitation sequence; and They are the two-dimensional Fourier transform and its inverse transform; It is the channel sensitivity operator, which saves the sensitivity information of multiple channels; is the multi-shot data to be reconstructed; and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; and These are the operations of performing one-dimensional inverse Fourier transform on the phase-encoded lines and the frequency-encoded lines; represents the Frobenius norm of the matrix; Represents the nuclear norm of the matrix; weight coefficient , , .

[0061] 3) Use generated data based on diffusion physics models.

[0062] 3.1) Obtaining Magnitude Images: Magnitude images are obtained using a phantom containing various parts of the brain, including gray matter, white matter, spine, spinal cord, adrenal glands, liver, gallbladder, stomach, pancreas, spleen, colon, kidneys, ureters, arteries, veins, muscles, bones, joints, fat, and skin.

[0063]

[0064] Among them, m o They represent the amplitude of the oth part, and the number of parts is O=20; Represents the mask of the o-th part; m is the amplitude map of a layer composed of various parts.

[0065] 3.2) Complex phase generation: Generate complex phases of all excitations of multiple organs based on high-order phase models , where the phase of the j-th excitation is:

[0066]

[0067] Where m and n are image coordinates; the order of the generated phase of the oth part is ; The mask representing the oth part; the parameters of the generated phase of the oth part .

[0068] 3.3) Generate k-space data: Use the generated phase to further generate full-sample multi-shot k-space data, including generating noise-free multi-shot k-space data X GT and generate the noisy multi-shot k-space data X Inp :

[0069]

[0070]

[0071] in is the generated multi-excitation motion phase; is the amplitude image; and They are two-dimensional Fourier transform and its inverse transform respectively; N is noise, and the signal-to-noise ratio is set to 0~20dB.

[0072] 4) The base model neural network is trained using physically generated data.

[0073] 4.1) Data preprocessing: The generated noisy multi-shot k-space data X Inp Convert to a structured low-rank matrix and perform singular value decomposition:

[0074]

[0075]

[0076] in, and They are the operations of performing one-dimensional inverse Fourier transform on the phase encoding line and the frequency encoding line; SVD is the singular value decomposition; and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; 、 、 are the left singular matrix, singular values, and right singular matrix of the structured matrix constructed from frequency-encoded data; 、 、 They are the left singular matrix, singular values, and right singular matrix of the structured matrix constructed by phase encoding data.

[0077] 4.2) Learning singular value truncation parameters: The base model neural network learns the singular value truncation parameters of the structured low-rank matrix based on the generated data, and the number of singular values optimally retained by the frequency encoding direction and phase encoding structured low-rank matrix and , so that the noisy signal has the highest peak signal-to-noise ratio after being restored by singular value truncation:

[0078]

[0079]

[0080] in and These are the operations of performing one-dimensional inverse Fourier transform on the phase-encoded lines and the frequency-encoded lines; and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; 、 、 are the left singular matrix, singular values, and right singular matrix of the structured matrix constructed from frequency-encoded data; 、 、 are the left singular matrix, singular value, and right singular matrix of the structured matrix constructed by phase encoding data; M and N are the frequency encoding number and phase encoding number respectively; X GT It is noise-free multi-shot k-space data; Represents matrix multiplication; represents the Frobenius norm of the matrix.

[0081] Physically based neural network models The network structure is ResNet18 (K. He et al., "Deepresidual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778, 2016).

[0082] Its loss function is:

[0083]

[0084] Among them, the input of the neural network is a paired one-dimensional input signal and ; The network's labels are frequency-encoded direction and phase-encoded structured low-rank matrix. The optimal number of retained singular values and ; and They represent the operators for selecting the mth frequency coding row and the nth phase coding row respectively; and are the one-dimensional inverse Fourier transform operations on the phase encoding line and the frequency encoding line respectively; T is the total number of training samples; is the optimal weight parameter; M represents the frequency encoding number, and N represents the phase encoding number; represents the Frobenius norm of the matrix; X Inp is the generated noisy multi-shot k-space data.

[0085] 5) The bidirectional one-dimensional low-rank reconstruction model uses singular value truncation to solve the nuclear norm. Use singular value truncation to constrain the low-rank matrix and for and ,in Represents a low-rank matrix Perform singular value truncation and retain the first r largest singular values and the corresponding subspace to recover the signal; and These are the operations of performing one-dimensional inverse Fourier transform on the phase-encoded lines and the frequency-encoded lines; and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; is the multi-shot data to be reconstructed.

[0086] 6) Use the low-rank matrix singular values suggested by the base model neural network to truncate the optimal parameters and Perform singular value truncation to achieve robust high-definition reconstruction.

[0087] To verify the technical effect of the present invention, the multi-excitation diffusion data of the kidney, liver, prostate, sacroiliac joint, neck, brain, and knee joint were reconstructed. The results are as follows: Figures 1 to 7 , with the kidneys, liver, prostate, and knee joints receiving two excitations, and the sacroiliac joints, neck, and brain receiving four excitations. The left side of each figure shows the artifact-bearing image after merging the original data with multiple excitations, while the right side shows the image reconstructed using this method. Experiments demonstrate that the method of the present invention effectively suppresses artifacts in multiple locations.

[0088] The present invention generates phases of different orders for different organs, generates phase data for different organs, constructs a physical-based model neural network, and trains the neural network to adaptively obtain optimized reconstruction parameters. This method uses a bidirectional one-dimensional low-rank optimization reconstruction method and a neural network to adaptively optimize reconstruction parameters, achieving robust high-definition magnetic resonance diffusion imaging of multiple challenging areas without adjusting parameters. Compared to existing low-rank reconstruction algorithms, the present invention strengthens local low-rank constraints through a bidirectional one-dimensional low-rank model and a neural network. Phase data for multiple areas is generated, and a neural network is trained to adaptively obtain optimized reconstruction parameters. High-definition, artifact-free images can be robustly reconstructed for areas with complex phases.

[0089] The above embodiments are only preferred embodiments of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent of the present invention.

Claims

1. A physical-based model multi-site high-definition diffusion magnetic resonance imaging method, characterized in that The following steps are involved: 1) Acquire k-space data of diffusion MRI to be reconstructed using a multi-shot echo-planar sequence for high-definition diffusion imaging reconstruction of multiple sites; 2) Designing a bidirectional one-dimensional low-rank reconstruction model based on local smooth phase; the model includes a two-dimensional Fourier transform operator, a channel sensitivity operator, a structured low-rank matrix extraction operator, and a nuclear norm constraint term to characterize the low-rank characteristics of multi-shot data; 3) Data generation using physical diffusion models, including: acquiring amplitude images using multi-organ phantoms, generating complex phase data of corresponding orders for different organs, and combining amplitude and phase to generate noisy and noise-free fully sampled multi-shot k-space data; 4) Using physically generated data to train the base model neural network; by converting the noisy k-space data into a structured low-rank matrix and performing singular value decomposition, the neural network learns the optimal singular value cutoff parameters; 5) Solve the bidirectional one-dimensional low-rank reconstruction model and achieve signal recovery by preserving the key singular values and corresponding subspaces of the structured low-rank matrix; 6) Combined with the reconstruction parameters suggested by the base model neural network, multi-excitation k-space data are generalized to reconstruct high-definition diffusion magnetic resonance images of various parts without motion artifacts.

2. A physical-based model multi-site high-definition diffusion magnetic resonance imaging method as claimed in claim 1, characterized in that In step 1), the k-space data of the diffusion magnetic resonance imaging to be reconstructed acquired by the multi-excitation echo-planar sequence is acquired, specifically: the k-space data of the diffusion magnetic resonance imaging to be reconstructed is acquired by the multi-excitation echo-planar sequence ,in represents the k-space data collected by the c-th coil during the j-th excitation, , ; represents a complex set; represents multiplication; M, N, J, and C represent the frequency encoding number, phase encoding number, total number of excitations, and total number of coil channels, respectively.

3. A physical-based model multi-site high-definition diffusion magnetic resonance imaging method as claimed in claim 1, characterized in that In step 2), the bidirectional one-dimensional low-rank reconstruction model is: in, is the k-space data of diffusion magnetic resonance imaging to be reconstructed; is the sampling template of the multi-excitation sequence; and They are the two-dimensional Fourier transform and its inverse transform; It is the channel sensitivity operator, which saves the sensitivity information of multiple channels; is the multi-shot data to be reconstructed, and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; and The phase coding line and the frequency coding line are respectively subjected to one-dimensional inverse Fourier transform operations, represents the Frobenius norm of the matrix; represents the nuclear norm of the matrix; 、 and is the weight coefficient; M represents the frequency encoding number, and N represents the phase encoding number.

4. A physical-based model multi-site high-definition diffusion magnetic resonance imaging method as claimed in claim 1, characterized in that In step 3), the data is generated using a physical diffusion model, specifically by acquiring amplitude images using a phantom comprising gray matter, white matter, spine, spinal cord, adrenal glands, liver, gallbladder, stomach, pancreas, spleen, colon, kidneys, ureters, arteries, veins, muscles, bones, joints, fat, and skin. Among them, m o They represent the amplitude of the oth part, and there are O parts in total; Represents the mask of the o-th part; m is the amplitude map of a layer composed of various parts; Generate complex phases of all excitations of multiple organs based on high-order phase models , where the phase of the j-th excitation is: Where m, n are image coordinates; L o is the order of the generated phase of the o-th position (o=1,2,…,O); The mask representing the oth part; is the parameter of the generation phase of the oth part; The generated phase is used to further generate full-sampled multi-shot k-space data, including generating noise-free multi-shot k-space data X GT and generate the noisy multi-shot k-space data X Inp : in, is the generated multi-excitation motion phase; is the amplitude image; and are two-dimensional Fourier transform and its inverse transform respectively; N is noise.

5. A physical-based model multi-site high-definition diffusion magnetic resonance imaging method as claimed in claim 1, characterized in that In step 4), the base model neural network is trained using the physically generated data. Specifically, the generated noisy multi-shot k-space data X Inp Convert to a structured low-rank matrix and perform singular value decomposition: in, and These are the operations of performing one-dimensional inverse Fourier transform on the phase-encoded lines and the frequency-encoded lines; and Extract the frequency-coded lines and Phase encoding rows and converting them into structured low-rank matrices; SVD is the singular value decomposition; 、 、 are the left singular matrix, singular values, and right singular matrix of the structured matrix constructed from frequency-encoded data; 、 、 are the left singular matrix, singular values, and right singular matrix of the structured matrix constructed by phase encoding data; X Inp is the generated noisy multi-shot k-space data; The base model neural network learns the singular value truncation parameters of the structured low-rank matrix based on the generated data, that is, the number of singular values optimally retained in the frequency encoding direction and phase encoding structured low-rank matrix and , so that the noisy signal has the highest peak signal-to-noise ratio after being restored by singular value truncation: in, and These are the operations of performing one-dimensional inverse Fourier transform on the phase-encoded lines and the frequency-encoded lines; and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; 、 、 are the left singular matrix, singular values, and right singular matrix of the structured matrix constructed from frequency-encoded data; 、 、 are the left singular matrix, singular value, and right singular matrix of the structured matrix constructed by phase encoding data; M and N are the frequency encoding number and phase encoding number respectively; X GT It is noise-free multi-shot k-space data; Represents matrix multiplication; represents the Frobenius norm of the matrix; Physically based neural network models It is a data-driven supervised artificial intelligence neural network based on gradient back propagation, and its loss function is: Among them, the input of the neural network is a paired one-dimensional input signal and ; The network's labels are frequency-encoded direction and phase-encoded structured low-rank matrix. The optimal number of retained singular values and ; and They represent the operators for selecting the mth frequency coding row and the nth phase coding row respectively; and are the one-dimensional inverse Fourier transform operations on the phase encoding line and the frequency encoding line respectively; T is the total number of training samples; is the optimal weight parameter; M represents the frequency encoding number, and N represents the phase encoding number; represents the Frobenius norm of the matrix; X Inp is the generated noisy multi-shot k-space data.

6. A physical-based model multi-site high-definition diffusion magnetic resonance imaging method as claimed in claim 1, characterized in that In step 5), the bidirectional one-dimensional low-rank reconstruction model uses singular value truncation to solve the nuclear norm; the singular value truncation is used to constrain the low-rank matrix and for and ,in Represents a low-rank matrix Perform singular value truncation and retain the first r largest singular values and the corresponding subspace to recover the signal; and These are the operations of performing one-dimensional inverse Fourier transform on the phase-encoded lines and the frequency-encoded lines; and Extract the frequency-coded lines and An operator that converts phase-encoded rows into a structured low-rank matrix; is the multi-shot data to be reconstructed.

7. A physical-based model multi-site high-definition diffusion magnetic resonance imaging method as claimed in claim 1, characterized in that In step 6), the reconstruction parameters suggested by the base model neural network adopt the low rank matrix singular value truncation optimal parameters suggested by the base model neural network and .

Images