Human 5.0T multi-nuclear 31 Self-supervised reconstruction method for magnetic resonance spectroscopy imaging

Abstract

The present invention discloses a 5.0T multi-core 31 The self-supervised reconstruction method of P magnetic resonance spectroscopy imaging, the self-supervised reconstruction network of the present invention includes a position encoding module, n dense convolution modules, and n data consistency modules, through which the position encoding module fully learns the position information of the chemical shift of the metabolite, and assists 31 The P-MRSI spectral image is reconstructed, and then a dense convolutional neural network structure is constructed to effectively promote the flow of information, strengthen feature reuse, and enhance the ability to remove pseudo-peaks and reconstruct high-quality images. Compared with existing 31 The P-MRSI reconstruction method and the self-supervised reconstruction network of the present invention can be effectively trained without fully sampled spectral images, shortening the data acquisition time while obtaining reconstructed high-quality spectral images, so that the trained network has stronger generalization ability.

Description

Technical Field

[0001] The present invention belongs to the field of magnetic resonance imaging technology, and specifically relates to a 5.0T multi-core human body. 31 A self-supervised reconstruction method for P magnetic resonance spectroscopy imaging, suitable for undersampling 31 High-quality spectral images were reconstructed from P-MRSI data. Background Art

[0002] Magnetic Resonance Spectroscopic Imaging (MRSI) is a magnetic resonance imaging technique. 31 P-MRSI can provide biochemical information about tissues by measuring high-energy phosphates (i.e., ATP, creatine phosphate PCr, and inorganic phosphate).

[0003] The inherently low signal-to-noise ratio (SNR) 31 The main limiting factor of P-MRSI is the low spatial resolution and extremely long acquisition time. The emergence of ultra-high field 5.0T magnetic resonance systems has improved the performance of low-field magnetic resonance experimental equipment. 31 The problem of low spatial resolution of P-MRSI can better study the relationship between tissue structure and function. Compared with other ultra-high field magnetic resonance systems (such as 7.0T magnetic resonance systems), the 5.0T magnetic resonance system avoids the B1 + The problem of spectral imaging quality degradation caused by field RF inhomogeneity is B1 + Field uniformity helps in 31 P-MRSI spectroscopy enables more precise chemical shift selection and metabolite concentration measurement, supporting more reliable metabolite quantification and biochemical analysis. Furthermore, the 5.0T MRI system has lower material costs, making it more suitable for clinical application.

[0004] In addition, various acceleration methods commonly used in MRI have been introduced to reduce acquisition time while maintaining sufficient SNR for spectral analysis. 31 P-MRSI and P-MRSI have shown potential in obtaining high-quality spectra. 31 The P-MRSI method is Compressed Sensing (CS), which uses 31 The spectrum of P-MRSI has sparseness in the transform domain and the incoherence of undersampling is used for nonlinear reconstruction, which can better restore the full sampling 31P-MRSI spectral images, but the CS optimization process takes a long time and is greatly affected by parameters. At present, deep learning methods have shown great potential in the field of undersampling MRSI reconstruction. Some researchers have used convolutional neural networks (CNN) for the human B cell receptor CD79b protein. 1 H- 15 The reconstruction of N HSQC spectral images can reconstruct MRSI quickly, reliably and with high quality. However, due to the difficulty in acquiring MRSI spectral images, existing deep learning MRSI reconstruction methods are difficult to use a large amount of actual acquired data as training data for supervised learning. Self-supervised learning can automatically extract feature information related to imaging quality from the original MRSI spectral image data to assist in reconstruction, without the need to acquire a large amount of fully sampled MRSI data, thus solving the problem of long acquisition time. Therefore, the use of self-supervised learning methods is a good choice. 31 PMRSI reconstruction and improvement 31 P MRSI spatial resolution and shortened acquisition time can obtain high-quality reconstructed spectral images when data is scarce. Summary of the Invention

[0005] The purpose of the present invention is to provide a 5.0T multi-core human body to solve the above problems in the prior art. 31 A self-supervised reconstruction method for P magnetic resonance spectroscopy.

[0006] The above-mentioned purpose of the present invention is achieved by the following technical means:

[0007] Human body 5.0T multi-core 31 The self-supervised reconstruction method of P magnetic resonance spectroscopy imaging is characterized by comprising the following steps:

[0008] Step 1: Acquire multiple undersampled k-space data, take each undersampled k-space data as a sample data, and then randomly divide all the sample data into a training set, a validation set, and a test set according to proportion;

[0009] Step 2: Each sample data in the training set is randomly divided into two parts, which are used as the first undersampled k-space data and the second undersampled k-space data, and a first undersampled spectral image and a first undersampled matrix corresponding to the first undersampled k-space data are obtained; a second undersampled spectral image and a second undersampled matrix corresponding to the second undersampled k-space data are obtained; and the first undersampled spectral image is used as the input sample;

[0010] Step 3: construct a self-supervised reconstruction network, the input of the self-supervised reconstruction network is the input sample, and the output of the self-supervised reconstruction network is the reconstructed full-sampled spectrum image;

[0011] Step 4: Perform Fourier transform on the reconstructed fully sampled spectral image to obtain corresponding reconstructed fully sampled k-space data, then multiply the reconstructed fully sampled k-space data by the second undersampling matrix to obtain reconstructed undersampled k-space data, and then perform inverse Fourier transform on the reconstructed undersampled k-space data to obtain a reconstructed undersampled spectral image;

[0012] Step 5: Set the total loss function;

[0013] Step 6: Input the input samples of the training set into the self-supervised reconstruction network to train the self-supervised reconstruction network. After the training is completed, save the model parameters to obtain the trained self-supervised reconstruction network.

[0014] Step 7: Input the input samples corresponding to the test set obtained after executing step 2 on the test set into the trained self-supervised reconstruction network to obtain the reconstructed full-sampled spectrum image corresponding to the test set;

[0015] Step 8: Obtain the actual undersampled spectral image and input it into the trained self-supervised reconstruction network to obtain the reconstructed full-sampled spectral image corresponding to the actual undersampled spectral image.

[0016] As described above, the self-supervised reconstruction network in step 3 includes a position encoding module, n dense convolution modules, and n data consistency modules. The position encoding module includes an encoder. The input sample is input into the encoder. The output of the encoder and the input are input into the first dense convolution module after channel splicing operation. The output of the bth data consistency module is input into the b+1th dense convolution module, and b is 1 to n-1; the output of the ath dense convolution module and the first undersampled k-space data are added and input into the ath data consistency module, and a is 1 to n; the output of the nth data consistency module is the output of the self-supervised reconstruction network, and the output of the self-supervised reconstruction network reconstructs the fully sampled spectral image.

[0017] As mentioned above, the dense convolution module includes multiple densely connected convolution modules. The input of the first convolution module is the input of the dense convolution module, and the inputs of the remaining convolution modules are the results of the outputs of all previous convolution modules after channel splicing operations. The outputs of all convolution modules are added together as the output of the corresponding dense convolution module.

[0018] As mentioned above, in each dense convolution module, except for the last convolution module which only includes a convolution layer, the remaining convolution modules all include convolution layers and activation layers. The input of the convolution layer is the input of the corresponding convolution module, the output of the last convolution layer is the output of the corresponding convolution module, and the output of the remaining convolution layers is input into the activation layer of the corresponding convolution module, and the output of the activation layer is the output of the corresponding convolution module.

[0019] The total loss function of step 5 as described above is the sum of the first loss function and the second loss function, wherein the first loss function calculates the error between the second undersampled k-space data and the reconstructed undersampled k-space data; the second loss function calculates the error between the second undersampled spectral image and the reconstructed undersampled spectral image.

[0020] As mentioned above, the first loss function and the second loss function in step 5 are both mean square error loss functions.

[0021] As described above, step 6 specifically includes the following process: inputting the input samples in the training set into the self-supervised reconstruction network to obtain the reconstructed fully sampled spectral image corresponding to each input sample, then executing step 4 on the reconstructed fully sampled spectral image to obtain the reconstructed undersampled k-space data, setting the learning rate, batch size, and total number of iterations, and then performing end-to-end training on the self-supervised reconstruction network through the ADAM optimizer and the set total loss function. After the number of iterations reaches the total number of iterations, the training is stopped, and the parameters of the self-supervised reconstruction network are saved to obtain a trained self-supervised reconstruction network.

[0022] A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any one of the above-mentioned human body 5.0T multi-core 31 Steps in a self-supervised reconstruction method for P magnetic resonance spectroscopy imaging.

[0023] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any of the above-mentioned human body 5.0T multi-core 31 Steps in a self-supervised reconstruction method for P magnetic resonance spectroscopy imaging.

[0024] A computer program product comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any one of the above-mentioned human 5.0T multi-core 31 Steps in a self-supervised reconstruction method for P magnetic resonance spectroscopy imaging.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] (1) The self-supervised reconstruction network of the present invention can utilize the magnetic resonance system B1 + The uniformity of the field is characterized by fully learning the position information of the chemical shift of metabolites through position encoding, assisting 31 The P-MRSI spectral image is reconstructed, and then a dense convolutional neural network structure is constructed. The advantages of residual connections and dense connections are utilized to effectively promote the flow of information, strengthen feature reuse, and enhance the ability to remove pseudo-peaks and reconstruct high-quality images.

[0027] (2) Compared with the existing31 The P-MRSI reconstruction method no longer relies on a large number of full sampling 31 P-MRSI spectrum image, the present invention effectively utilizes 31 The inherent laws and characteristics of P-MRSI data are learned using self-supervised methods 31 The inherent characteristics of P-MRSI can be used for training without full-sampled spectral images, reducing the need for high-quality full-sampled images. 31 The demand for P-MRSI spectral images is to obtain reconstructed high-quality spectral images while shortening the data acquisition time, so that the trained network has stronger generalization ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a flow chart of the method of the present invention;

[0029] FIG2( a ) is a schematic diagram of a sampling matrix for Cartesian undersampling in Example 1 of the present invention;

[0030] FIG2( b ) is a first undersampling matrix according to embodiment 1 of the present invention;

[0031] FIG2( c ) is a second undersampling matrix according to embodiment 1 of the present invention;

[0032] Figure 3 Schematic diagram of the structure of the self-supervised reconstruction network of Example 1 of the present invention;

[0033] Figure 4 This is a schematic diagram of the structure of the dense convolution module of Example 1 of the present invention, wherein Represents channel splicing operation;

[0034] FIG5(a) is a 2D full sampling 5.0T in the test set in Example 1 of the present invention. 31 P-MRSI spectrum image (where ppm is the unit of chemical shift on the abscissa and amplitude is the signal amplitude);

[0035] Figure 5(b) shows the 2D undersampling 5.0T obtained by using the zero-filling method. 31 P-MRSI spectral images;

[0036] FIG5(c) shows the 2D undersampling 5.0T in FIG5(b) using the self-supervised reconstruction network trained in Example 1 of the present invention. 31 P-MRSI spectral images were reconstructed to obtain the reconstructed 5.0T 31 P-MRSI spectral image. DETAILED DESCRIPTION

[0037] In order to facilitate those skilled in the art to understand and implement the present invention, the present invention is further described in detail below with reference to the embodiments. The embodiments described herein are only used to illustrate and explain the present invention and are not intended to limit the present invention.

[0038] Example 1:

[0039] Human body 5.0T multi-core 31 The self-supervised reconstruction method of P magnetic resonance spectroscopy imaging comprises the following steps:

[0040] Step 1: Acquire multiple undersampled k-space data, take each undersampled k-space data as a sample data, and then randomly divide all the sample data into a training set, a validation set, and a test set according to proportion;

[0041] In this embodiment, LCModel spectrum quantitative analysis software is used to simulate and obtain 1024 5.0T 31 P-MRSI spectrum data (5.0T is the magnetic field strength), and then 1024 5.0T 31 The P-MRSI spectral data were Fourier transformed to obtain multiple 2D full-sampling 5.0T 31 P-MRSI k-space data, and then each 2D full sampling 5.0T according to the Cartesian undersampling sampling matrix 31 The P-MRSI k-space data were undersampled to obtain the corresponding 2D undersampled 5.0T 31 P-MRSI k-space data (corresponding to the undersampled k-space data in step 1); in this embodiment, each 2D undersampled 5.0T 31 The P-MRSI k-space data was used as a sample data, and then all sample data were randomly divided into a training set, a validation set, and a test set in a ratio of 3:1:1;

[0042] Step 2: Each sample data in the training set is randomly divided into two parts, respectively as the first under-sampled k-space data and the second under-sampled k-space data. The first under-sampled k-space data is subjected to inverse Fourier transform to obtain the corresponding spectral image as the first under-sampled spectral image, and the under-sampled sampling matrix corresponding to the first under-sampled k-space data is obtained as the first under-sampling matrix; the second under-sampled k-space data is subjected to inverse Fourier transform to obtain the corresponding spectral image as the second under-sampled spectral image, and the under-sampled sampling matrix corresponding to the second under-sampled k-space data is obtained as the second under-sampling matrix; the first under-sampled spectral image is the input sample.

[0043] The input samples are used to input into the self-supervised reconstruction network, and the second undersampled k-space data and the corresponding second undersampled spectral image are used to perform loss calculation to train the self-supervised reconstruction network.

[0044] In this embodiment, step 2 is performed on each sample data in the training set to obtain the first undersampling 5.0T 31 P-MRSI k-space data (corresponding to the first under-sampled k-space data in step 2), the first under-sampled 5.0T 31 P-MRSI spectrum image (corresponding to the first under-sampled spectrum image in step 2), and the first under-sampled matrix; the second under-sampled 5.0T 31 P-MRSI k-space data (corresponding to the second undersampled k-space data in step 2), the second undersampled 5.0T 31 The P-MRSI spectrum image (corresponding to the second under-sampled spectrum image in step 2) and the second under-sampling matrix are converted from the first under-sampled 5.0T 31 P-MRSI spectrum image is used as input sample.

[0045] Step 3. Construct a self-supervised reconstruction network. The self-supervised reconstruction network includes a position encoding module, n dense convolution modules, and n data consistency modules. The position encoding module includes an encoder. The input sample is input into the encoder of the position encoding module. The output and input of the encoder of the position encoding module are input into the first dense convolution module after channel splicing operation. The output of the bth data consistency module is input into the b+1th dense convolution module, and b is 1 to n-1; the output of the ath dense convolution module and the first undersampled k-space data are added and input into the ath data consistency module, and a is 1 to n; the output of the nth data consistency module is the output of the self-supervised reconstruction network, and the output of the self-supervised reconstruction network reconstructs the full-sampled spectral image.

[0046] The dense convolution module includes multiple densely connected convolution modules. The input of the first convolution module is the input of the dense convolution module. The input of the remaining convolution modules is the output of all convolution modules before the current convolution module in the corresponding dense convolution module after channel splicing operation. The output of all convolution modules is added together as the output of the corresponding dense convolution module.

[0047] In each dense convolution module, except for the last convolution module which only includes a convolution layer, the remaining convolution modules all include convolution layers and activation layers. The input of the convolution layer is the input of the corresponding convolution module, the output of the last convolution layer is the output of the corresponding convolution module, and the output of the remaining convolution layers is input into the activation layer of the corresponding convolution module, and the output of the activation layer is the output of the corresponding convolution module.

[0048] The positional encoding module learns uniform B1 by encoding a vector with the same length as the input content + Field (this example is a uniform B1 under a 5.0T system +field) reflects more accurate position information of metabolite chemical shifts, improving 31 Efficiency and accuracy of P-MRSI spectral image reconstruction.

[0049] Multiple densely connected convolutional modules enable the self-supervised reconstruction network to learn complex mapping relationships, so that each convolutional layer can receive rich information from the entire front of the network, helping the network to consider both global and local features during the reconstruction process;

[0050] The data consistency module is used to combine the reconstructed k-space data with the first undersampled k-space data to ensure data consistency.

[0051] In this embodiment, the structural diagram of the self-supervised reconstruction network is as follows: Figure 3 As shown, the self-supervised reconstruction network includes a position encoding module, three dense convolution modules, and three data consistency modules, each of which includes four densely connected convolution modules.

[0052] Step 4: Perform Fourier transform on the reconstructed fully sampled spectral image to obtain corresponding reconstructed fully sampled k-space data, then multiply the reconstructed fully sampled k-space data by the second undersampling matrix to obtain reconstructed undersampled k-space data, and then perform inverse Fourier transform on the reconstructed undersampled k-space data to obtain a reconstructed undersampled spectral image;

[0053] Step 5: Set a total loss function. The total loss function is the sum of the first loss function and the second loss function, where the first loss function calculates the error between the second undersampled k-space data and the reconstructed undersampled k-space data; and the second loss function calculates the error between the second undersampled spectral image and the reconstructed undersampled spectral image.

[0054] In this embodiment, the first loss function and the second loss function are both mean square error (L2) loss functions.

[0055] Step 6: Input the input samples of the training set into the self-supervised reconstruction network to train the self-supervised reconstruction network. After the training is completed, save the model parameters to obtain the trained self-supervised reconstruction network.

[0056] Specifically, the input samples in the training set are input into the self-supervised reconstruction network to obtain the reconstructed fully sampled spectral images corresponding to each input sample. Then, step 4 is performed on the reconstructed fully sampled spectral images to obtain the reconstructed undersampled k-space data. The learning rate, batch size, and total number of iterations are set. Then, the self-supervised reconstruction network is trained end-to-end using the ADAM optimizer and the set total loss function. The training is stopped when the number of iterations reaches the total number of iterations, and the parameters of the self-supervised reconstruction network are saved to obtain a trained self-supervised reconstruction network.

[0057] In this embodiment, the first undersampling is 5.0T 31 The P-MRSI spectral image is input into the self-supervised reconstruction network to perform step 6 to obtain the reconstructed full sampling 5.0T 31 P-MRSI spectral image (corresponding to the reconstructed full-sample spectral image in step 6), reconstructed full-sample 5.0T 31 P-MRSI k-space data (corresponding to the reconstructed full-sample k-space data in step 4), reconstructed undersampled 5.0T 31 P-MRSI k-space data (corresponding to the reconstructed undersampled k-space data in step 4), reconstructed undersampled 5.0T 31 P-MRSI spectrum image (corresponding to the reconstructed undersampled spectrum image in step 4), the learning rate is initialized to 0.0001, the batch size is set to 10, and the total number of iterations is set to 200.

[0058] Step 7: Execute step 2 on the test set to obtain the input samples corresponding to the test set, input the input samples corresponding to the test set into the trained self-supervised reconstruction network in step 6 to obtain the reconstructed full-sampled spectrum image corresponding to the test set.

[0059] In this embodiment, the test set is executed in step 7 to obtain the reconstructed full sampling 5.0T corresponding to the test set. 31 P-MRSI spectral images and computational reconstruction of full sampling 5.0T 31 Signal-to-noise ratio (SNR) of P-MRSI spectral images, calculated and reconstructed at full sampling 5.0T 31 P-MRSI spectral images and 2D full sampling 5.0T 31 The peak intensity correlation (R 2 ), and obtained by using the 2D undersampling 5.0T method using the zero-filling method 31 P-MRSI spectral images are analyzed and compared to measure the performance of the trained self-supervised reconstruction network;

[0060] Comparing Figure 5(b) and Figure 5(a), it can be seen that the reconstructed 5.0T image obtained by the self-supervised reconstruction network of the present invention is 31 P-MRSI spectral images and 2D full sampling 5.0T 31 The peak correlation of P-MRSI spectral images is higher and the reconstruction of 5.0T 31 The signal-to-noise ratio of P-MRSI spectral images is also better.

[0061] In the actual application process, the undersampled k-space data collected can be directly used in step 1. In this embodiment, the 2D full sampling 5.0T 31 The P-MRSI spectral image is used to measure the performance of the trained self-supervised reconstruction network and does not participate in the training of the self-supervised reconstruction network.

[0062] The self-supervised reconstruction network of the present invention can utilize the magnetic resonance system B1 + The uniformity of the field is characterized by fully learning the position information of the chemical shift of metabolites through position encoding, assisting 31 The P-MRSI spectral image is reconstructed, and then a dense convolutional neural network structure is constructed. The advantages of residual connections and dense connections are utilized to effectively promote the flow of information, strengthen feature reuse, and enhance the ability to remove pseudo-peaks and reconstruct high-quality images.

[0063] Compared with the existing 31 The P-MRSI reconstruction method no longer relies on a large number of full sampling 31 P-MRSI spectrum image, the present invention effectively utilizes 31 The inherent laws and characteristics of P-MRSI data are learned using self-supervised methods 31 The inherent characteristics of P-MRSI can be used for training without full-sampled spectral images, reducing the need for high-quality full-sampled images. 31 The demand for P-MRSI spectral images is to obtain reconstructed high-quality spectral images while shortening the data acquisition time, so that the trained network has stronger generalization ability.

[0064] Step 8: Input the actual undersampled spectral image into the trained self-supervised reconstruction network to obtain the reconstructed full-sampled spectral image corresponding to the actual undersampled spectral image.

[0065] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0066] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements steps 1 to 8 of the above method embodiments when executing the computer program.

[0067] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, steps 1 to 8 of the above method embodiments are implemented.

[0068] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, steps 1 to 8 of the above method embodiments are implemented.

[0069] It should be noted that the embodiments described herein are merely illustrative of the spirit of the present invention. Persons skilled in the art may make various modifications, additions, or substitutions to the described embodiments without departing from the spirit of the present invention or exceeding the scope of the appended claims.

Claims

1. Human body 5.0T multi-core 31 A self-supervised reconstruction method for P magnetic resonance spectroscopy imaging, characterized in that The following steps are involved: Step 1: Acquire multiple undersampled k-space data, take each undersampled k-space data as a sample data, and then randomly divide all the sample data into a training set, a validation set, and a test set according to proportion; Step 2: Each sample data in the training set is randomly divided into two parts, which are used as the first undersampled k-space data and the second undersampled k-space data, and a first undersampled spectral image and a first undersampled matrix corresponding to the first undersampled k-space data are obtained; a second undersampled spectral image and a second undersampled matrix corresponding to the second undersampled k-space data are obtained; and the first undersampled spectral image is used as the input sample; Step 3: construct a self-supervised reconstruction network, the input of the self-supervised reconstruction network is the input sample, and the output of the self-supervised reconstruction network is the reconstructed full-sampled spectrum image; Step 4: Perform Fourier transform on the reconstructed fully sampled spectral image to obtain corresponding reconstructed fully sampled k-space data, then multiply the reconstructed fully sampled k-space data by the second undersampling matrix to obtain reconstructed undersampled k-space data, and then perform inverse Fourier transform on the reconstructed undersampled k-space data to obtain a reconstructed undersampled spectral image; Step 5: Set the total loss function; Step 6: Input the input samples of the training set into the self-supervised reconstruction network to train the self-supervised reconstruction network. After the training is completed, save the model parameters to obtain the trained self-supervised reconstruction network. Step 7: Input the input samples corresponding to the test set obtained after executing step 2 on the test set into the trained self-supervised reconstruction network to obtain the reconstructed full-sampled spectrum image corresponding to the test set; Step 8: Obtain the actual undersampled spectrum image and input it into the trained self-supervised reconstruction network to obtain the reconstructed full-sampled spectrum image corresponding to the actual undersampled spectrum image; The self-supervised reconstruction network in step 3 includes a position encoding module, n dense convolution modules, and n data consistency modules. The position encoding module includes an encoder. The input sample is input into the encoder. The output of the encoder and the input are input into the first dense convolution module after a channel splicing operation. The output of the bth data consistency module is input into the b+1th dense convolution module, where b is 1 to n-1; the output of the ath dense convolution module and the first undersampled k-space data are added and input into the ath data consistency module, where a is 1 to n; the output of the nth data consistency module is the output of the self-supervised reconstruction network, and the self-supervised reconstruction network output reconstructs the fully sampled spectral image; The positional encoding module learns uniform B1 by encoding a vector with the same length as the input content + The field reflects the position information of the metabolite chemical shift.

2. The human 5.0T multi-core according to claim 1 31 A self-supervised reconstruction method for P magnetic resonance spectroscopy imaging, characterized in that The dense convolution module includes multiple densely connected convolution modules. The input of the first convolution module is the input of the dense convolution module, and the inputs of the remaining convolution modules are the results of the outputs of all previous convolution modules after channel splicing operations. The outputs of all convolution modules are added together as the output of the corresponding dense convolution module.

3. The human 5.0T multi-core according to claim 2 31 A self-supervised reconstruction method for P magnetic resonance spectroscopy imaging, characterized in that In each dense convolution module, except for the last convolution module which only includes a convolution layer, the remaining convolution modules all include convolution layers and activation layers. The input of the convolution layer is the input of the corresponding convolution module, the output of the last convolution layer is the output of the corresponding convolution module, and the output of the remaining convolution layers is input into the activation layer of the corresponding convolution module, and the output of the activation layer is the output of the corresponding convolution module.

4. The human 5.0T multi-core 31 A self-supervised reconstruction method for P magnetic resonance spectroscopy imaging, characterized in that The total loss function of step 5 is the sum of a first loss function and a second loss function, wherein the first loss function calculates the error between the second undersampled k-space data and the reconstructed undersampled k-space data; and the second loss function calculates the error between the second undersampled spectral image and the reconstructed undersampled spectral image.

5. The human 5.0T multi-core according to claim 4 31 A self-supervised reconstruction method for P magnetic resonance spectroscopy imaging, characterized in that In step 5, the first loss function and the second loss function are both mean square error loss functions.

6. The human 5.0T multi-core 31 A self-supervised reconstruction method for P magnetic resonance spectroscopy imaging, characterized in that The step 6 specifically includes the following process: inputting the input samples in the training set into the self-supervised reconstruction network to obtain the reconstructed fully sampled spectral image corresponding to each input sample, then executing step 4 on the reconstructed fully sampled spectral image to obtain the reconstructed undersampled k-space data, setting the learning rate, batch size, and total number of iterations, and then performing end-to-end training on the self-supervised reconstruction network using the ADAM optimizer and the set total loss function. After the number of iterations reaches the total number of iterations, the training is stopped, and the parameters of the self-supervised reconstruction network are saved to obtain a trained self-supervised reconstruction network.

7. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the human body 5.0T multi-core according to any one of claims 1 to 6 is implemented 31 Steps in a self-supervised reconstruction method for P magnetic resonance spectroscopy imaging.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the human body 5.0T multi-core processor according to any one of claims 1 to 6 is implemented. 31 Steps in a self-supervised reconstruction method for P magnetic resonance spectroscopy imaging.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the human body 5.0T multi-core processor according to any one of claims 1 to 6 is implemented. 31 Steps in a self-supervised reconstruction method for P magnetic resonance spectroscopy imaging.

Images