Magnetic resonance high-resolution multi-parameter quantification method and system based on multi-scanning overlapping echoes

Abstract

The invention discloses a magnetic resonance high-resolution multi-parameter quantification method and system based on multi-scanning overlapping echoes, and relates to a magnetic resonance imaging method. Comprising the following steps: designing a high-resolution multi-parameter simultaneous quantitative imaging sequence based on multi-scanning overlapping echoes and determining sampling parameters of the high-resolution multi-parameter simultaneous quantitative imaging sequence; performing data acquisition on an imaging object by using the designed sequence and sampling parameters in a magnetic resonance instrument meeting the sequence and sampling parameters to obtain a magnetic resonance signal; after the magnetic resonance signal is processed, an image acquired by the sequence is obtained; designing a high-fidelity quantitative reconstruction method; the acquired magnetic resonance image is subjected to quantitative reconstruction by using the method, and a high-resolution multi-parameter magnetic resonance quantitative image is obtained. Magnetic resonance high-resolution multi-parameter simultaneous quantitative imaging can be realized, and the problem that reconstruction details are lost under the condition of low signal-to-noise ratio is solved. Experimental results show that the magnetic resonance quantitative parameter image generated through reconstruction is highly consistent with the result of a reference method, the imaging precision is high, and the method has wide application prospects.

Description

Technical Field

[0001] The invention relates to a magnetic resonance imaging method, in particular to a magnetic resonance high-resolution multi-parameter quantitative method and system based on multi-scanning overlapping echoes. Background Art

[0002] Quantitative magnetic resonance imaging can quantitatively measure physiological parameters. Compared with qualitative parameter-weighted imaging, it can provide more objective evaluation criteria, which is of great significance for the evaluation of therapeutic effects and the graded diagnosis of diseases. High-resolution quantitative images can provide better anatomical details and enhance the ability to evaluate tissue structure and identify early pathology. However, traditional quantitative magnetic resonance imaging methods have a long acquisition time and can only quantify one parameter at a time, which greatly limits the application of quantitative magnetic resonance imaging. Based on this, a series of single-scan overlapping echo fast imaging methods have been developed (CN108010100B, CN108663644B, CN110807492B). After one excitation, multiple echoes with single or multiple parameters of different contrast are simultaneously acquired to achieve a single T2 or T2 * Parameters or both are quickly quantified simultaneously. However, since the echo chain length of a single scan is limited by the lateral relaxation attenuation during signal readout, the imaging resolution of the above invention is low and some detailed structures may be lost. In addition, the above invention uses a reconstruction method based on a convolutional neural network (CNN) to learn the mapping relationship from overlapping echo images to quantitative parameters by minimizing the mean square error (MMSE) between the network output and the quantitative parameters. Therefore, in high-resolution imaging, the smaller the voxel, the lower the signal-to-noise ratio. Due to the small receptive field of CNN, it is difficult for it to capture global features and complex spatial relationships, and the reconstruction result is relatively smooth when the signal-to-noise ratio is low. In addition, training using the MMSE method will also reduce the perceptual quality (such as visual blur), especially under low signal-to-noise ratio conditions (Blau Y, Michaeli T. The perception-distortion tradeoff. Proc Cvpr Ieee . 2018;6228-6237). The use of multi-scan technology can shorten the readout time of a single scan and improve the imaging resolution. Other imaging methods based on multi-scan overlapping echoes (CN113030813B, CN118549870A) can only quantify the T2 parameter and do not consider the impact of changes in the signal-to-noise ratio on the reconstruction results when the acquisition resolution changes. Therefore, the above invention is not suitable for high-resolution multi-parameter quantitative imaging.

[0003] The Swin Transformer structure is a technology transplanted from the field of natural language processing to the field of computer vision. Thanks to its global self-attention mechanism, it can better model global features and better restore texture details (LiuZ, Lin YT, Cao Yet al. Swin transformer: Hierarchical vision transformerusing shifted windows. 2021 Ieee / Cvf International Conference on Computer Vision (Iccv 2021). 2021;9992-10002). Summary of the invention

[0004] The purpose of the present invention is to provide a high-resolution multi-parameter quantitative method and system for magnetic resonance based on multi-scan overlapping echoes to address the problems of loss of reconstruction details, reconstruction quality and noise robustness under low signal-to-noise ratio conditions in the prior art. The method and system use multi-scan technology to improve single-scan multi-parameter overlapping echo separation imaging to achieve fast high-resolution multi-parameter quantitative imaging. At the same time, a high-fidelity quantitative reconstruction method is designed based on the Swin Transformer structure, and the MMSE is improved by combining the auxiliary task of noise learning, so that high-quality quantitative results can still be obtained under low signal-to-noise ratios.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] A magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlap echo acquisition comprises the following steps:

[0007] S1: Design a high-resolution multi-parameter quantitative method sequence of magnetic resonance based on overlapping echoes, called multi-scan multi-parameter multiple overlapping echo separation imaging sequence;

[0008] S2: Determine the sampling parameters of the multi-scan multi-parameter multiple overlap echo separation imaging sequence;

[0009] S3: using the designed sequence and sampling parameters in a magnetic resonance instrument that meets the sequence and sampling parameters, collecting data on the imaging object and obtaining a magnetic resonance signal;

[0010] S4: After rearranging, splicing, zero-filling, and parallel reconstruction of the acquired magnetic resonance signals, a multi-scanning, multi-parameter, and multi-overlapping echo image is obtained;

[0011] S5: Design a high-fidelity quantitative reconstruction method based on the Swin Transformer structure;

[0012] S6: using the high-fidelity quantitative reconstruction method to obtain a trained neural network;

[0013] S7: Using the trained neural network to quantitatively reconstruct the acquired magnetic resonance image to obtain a high-resolution multi-parameter magnetic resonance quantitative image.

[0014] Optionally, the designing of a magnetic resonance imaging sequence specifically includes:

[0015] S11: Design a signal excitation module for generating magnetic resonance signals;

[0016] S12: Design a shift gradient module to refocus the generated signals into the same k-space;

[0017] S13: design a data acquisition module for acquiring magnetic resonance signals;

[0018] Optionally, determining the imaging sequence sampling parameters mainly includes:

[0019] S21: Determine the parameters such as the RF pulse angle, shape and application time;

[0020] S22: Determine parameters such as the displacement gradient area, direction, and application time;

[0021] S23: determining the number of scans to balance readout time and imaging resolution;

[0022] S24: determining a parallel imaging acceleration factor to speed up acquisition;

[0023] S25: confirm other acquisition parameters;

[0024] Optionally, the design is a high-fidelity quantitative reconstruction method based on a Swin Transformer structure, specifically comprising:

[0025] S51: Determine the quantitative reconstruction neural network based on Swin Transformer;

[0026] S52: Design noise learning auxiliary tasks to improve the robustness of neural networks to noise;

[0027] S53: Use the Pytorch deep learning framework to build a neural network training framework based on S51 and S52, and determine hyperparameters such as learning rate, batch size, number of iterations, etc.

[0028] S54: Generate neural network training samples; including simulated data or actually collected data and their corresponding quantitative parameters.

[0029] A magnetic resonance high-resolution multi-parameter quantitative system based on multi-scanning overlapping echo acquisition, comprising:

[0030] The sequence design module is responsible for designing the multi-scan multi-parameter multiple overlap echo separation imaging sequence, including the specific implementation of signal excitation, shift gradient and data acquisition modules, and passing the design parameters to the sampling parameter determination module;

[0031] The sampling parameter determination module further determines specific sampling parameters such as the RF pulse angle, shape, application time, shift gradient area, direction, application time, number of scans, parallel imaging acceleration factor, etc. according to the design parameters, and provides these parameters to the data acquisition module;

[0032] The data acquisition module collects data on the imaging object in the magnetic resonance instrument according to the given sequence and sampling parameters, obtains magnetic resonance signals, and transmits these signals to the image preprocessing module;

[0033] The image preprocessing module performs preprocessing operations such as rearrangement, splicing, zero filling, and parallel reconstruction on the collected magnetic resonance signals to generate multi-scan, multi-parameter, and multi-overlap echo images, and transmits them to the neural network reconstruction module;

[0034] The neural network reconstruction module uses a high-fidelity quantitative reconstruction neural network based on the Swin Transformer structure to quantitatively reconstruct the preprocessed image to obtain a high-resolution multi-parameter magnetic resonance quantitative image. This module also needs to interact with the neural network training module to obtain a trained neural network model.

[0035] The neural network training module is responsible for designing the training framework of the neural network, using the magnetic resonance images with different characteristics and parameters provided by the simulation data generation module as training samples (these training samples also simulate the unstable factors in the real experiment to improve the robustness of the model), training the neural network, and providing the trained model to the neural network reconstruction module;

[0036] The simulation data generation module is specifically used to generate simulation data required for training;

[0037] The result display module receives the reconstructed image output by the neural network reconstruction module and displays it for users to view and analyze. These modules work together to realize the complete process from sequence design to data acquisition, preprocessing, quantitative reconstruction and result display.

[0038] Compared with the prior art, the advantages of the present invention are:

[0039] 1. The present invention adopts multi-scanning overlapping echo technology to obtain magnetic resonance signals through multiple scans, effectively shortening the readout time of a single scan, thereby improving imaging resolution. Compared with the traditional single-scan method, this method can capture detailed structures more clearly and avoid information loss.

[0040] 2. The present invention introduces the Swin Transformer structure, which is an advanced technology transplanted from the field of natural language processing to the field of computer vision. Swin Transformer has a global self-attention mechanism, which can better model global features and restore texture details. Compared with traditional convolutional neural networks (CNNs), Swin Transformer can still obtain high-quality quantitative results under low signal-to-noise ratio conditions.

[0041] 3. The present invention realizes fast magnetic resonance high-resolution parameters T2 and T2 * , B1, PD, and ΔB0. Compared with the limitation of traditional methods that can only quantify one parameter at a time, this method greatly improves imaging efficiency and information volume, providing doctors with a more comprehensive diagnosis basis.

[0042] 4. Due to the use of multi-scanning technology and Swin Transformer structure, the quantitative magnetic resonance images obtained by the present invention are highly accurate and have good detail effects. This is of great significance for evaluating tissue structure and identifying early pathology, and helps to improve the accuracy of disease diagnosis.

[0043] 5. The present invention adds a noise learning auxiliary task when designing a high-fidelity quantitative reconstruction method based on the Swin Transformer structure. This design enables the neural network to better learn the noise characteristics during the training process, so that the reconstruction quality can still be maintained stable under low signal-to-noise ratio conditions.

[0044] 6. The present invention is robust to reconstruction quality under low signal-to-noise ratio conditions. Even under poor imaging conditions, the present invention can still provide high-quality magnetic resonance quantitative images, providing doctors with reliable diagnostic basis. It has broad application prospects and important clinical value in the field of medical imaging. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flow chart of the magnetic resonance high-resolution multi-parameter simultaneous quantitative imaging method of the present invention.

[0046] Figure 2 A flow chart of a high-fidelity quantitative reconstruction method based on the Swin Transformer structure is designed for the present invention.

[0047] Figure 3 It is a multi-scanning, multi-parameter, multiple overlapping echo separation imaging sequence diagram and k-space filling trajectory in an embodiment of the present invention.

[0048] Figure 4 It is a neural network model used in the high-fidelity quantitative reconstruction method in an embodiment of the present invention.

[0049] Figure 5This is a high-resolution multi-parameter quantitative image of the human brain obtained by the method of the present invention.

[0050] Figure 6 T2 and T2 obtained by the method of the present invention under different signal-to-noise ratio conditions * Quantitative graph. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention, including but not limited to: adding common preparation modules such as reversal, saturation, and fat compression before using the sequence and in the intermediate process of cyclic use of the sequence, which should be regarded as the scope of no obvious creative work on the basis of the present invention, that is, within the scope of protection of the present invention.

[0052] like Figure 1 The magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlapping echoes described in the embodiment of the present invention comprises the following steps:

[0053] S1: Design a high-resolution multi-parameter quantitative method sequence of magnetic resonance based on overlapping echoes, called multi-scan multi-parameter multiple overlapping echo separation imaging sequence;

[0054] S11: Designing a signal excitation module; Designing a signal excitation module is the first step in the imaging sequence. In this embodiment, multiple RF pulses are used to generate echo signals with different contrasts. These echo signals provide the required parameter weighting information for subsequent quantitative imaging. In order to optimize signal excitation, an appropriate flip angle, pulse shape, and application time are selected to ensure the signal strength and maximize the signal sensitivity to the parameters.

[0055] S12: Design a shift gradient module; the shift gradient module is used to refocus each echo signal into the same k-space. By designing specific shift gradients, each echo signal can be accurately moved to a specified position in the k-space. This design not only improves the signal acquisition efficiency, but also enhances the quality and accuracy of quantitative imaging.

[0056] S13: Design a data acquisition module; the data acquisition module is used to collect magnetic resonance signals during the imaging process. In order to obtain quantitative information of multiple parameters at the same time, different readout modules (such as SE-EPI and GRE-EPI) are used to obtain T2 and T2 respectively. *k-space data with equal parameters weighting. In addition, combined with multi-scan technology, the sampling echo chain length in the pulse sequence is shortened by multiple scans to reduce the relaxation attenuation of the signal. At the same time, the parallel imaging method is used to reduce the scanning time and achieve a balance between the minimum signal-to-noise ratio and scanning time required for high-resolution multi-parameter quantitative imaging.

[0057] S2: Determine the sampling parameters of the multi-scan multi-parameter multiple overlap echo separation imaging sequence; after determining the imaging sequence, it is necessary to further determine the sampling parameters to ensure the quality and accuracy of the imaging. These parameters include the flip angle, shape and application time of the RF pulse, the area, direction and application time of the shift gradient, the number of scans, the parallel imaging acceleration factor, and other acquisition parameters (such as imaging field of view, imaging matrix, acquisition layer thickness and repeated acquisition time, etc.). The optimization of these parameters is crucial to improving the imaging quality and quantitative accuracy of parameters, including:

[0058] S21: Determine the parameters such as the RF pulse angle, shape and application time;

[0059] S22: Determine parameters such as the displacement gradient area, direction, and application time;

[0060] S23: Determine the number of scans;

[0061] S24: determining a parallel imaging acceleration factor;

[0062] S25: confirm other acquisition parameters;

[0063] S3: Use the designed sequence and sampling parameters in a magnetic resonance instrument that meets the sequence and sampling parameters to collect data on the imaging object and obtain magnetic resonance signals; by precisely controlling the excitation pulse, shift gradient and data acquisition process, high-quality magnetic resonance signals can be obtained, providing a reliable data basis for subsequent processing.

[0064] S4: After rearranging, splicing, zero-filling, and parallel reconstruction of the acquired magnetic resonance signals, a multi-scanning, multi-parameter, and multi-overlapping echo image is obtained; specifically, accurate alignment and separation of the signals must be ensured, and data loss or confusion must be avoided. Subsequently, the data are further processed using a parallel reconstruction method to obtain a high-resolution image.

[0065] S5: Design a high-fidelity quantitative reconstruction method based on the Swin Transformer structure; this method is the core part of the present invention. This method uses deep learning technology and the self-attention mechanism of Swin Transformer to extract deep features and improve the quality of image reconstruction. At the same time, by designing noise learning auxiliary tasks, the noise characteristics are explicitly understood and separated, and the main task's ability to effectively extract signals is enhanced. This design not only improves the accuracy of reconstruction and the generalization performance of the model, but also significantly improves the performance under low signal-to-noise ratio conditions. Figure 2 , specifically including:

[0066] S51: Determine the quantitative reconstruction neural network based on Swin Transformer; the structure of the neural network includes four modules: shallow feature extraction, deep feature extraction, main task and auxiliary task. The shallow feature extraction module maps the input image to the shallow feature space through the convolution layer; the deep feature extraction module uses the Swin Transformer block to extract deep features; the main task module obtains quantitative reconstruction parameters through the deconvolution layer; and the auxiliary task module is used to predict noise.

[0067] S52: Design auxiliary tasks for noise learning; the auxiliary tasks for noise learning are implemented by sharing the previous feature extraction layer and adding a noise prediction output at the end. This design enables the model to explicitly understand and separate noise characteristics while learning signal features, thereby improving the accuracy and robustness of reconstruction.

[0068] S53: According to steps S51 and S52, a neural network training framework is built using the Pytorch deep learning framework, and hyperparameters are determined; a neural network training framework is built using the Pytorch deep learning framework, and hyperparameters (such as the number of input and output channels, the number of Swin Transformer blocks, the embedding dimension, the number of attention heads, and the sliding window size) are determined. The optimization of these hyperparameters is crucial to improving the performance and accuracy of the neural network.

[0069] S54: Generate neural network training samples; use simulation methods to generate the training samples required for deep neural networks. By inputting the pulse sequence into the magnetic resonance imaging simulation software and adding corresponding non-ideal terms to simulate the actual situation, a series of magnetic resonance images with different characteristics and parameters are generated as training samples. These samples not only contain all the characteristics of the object to be tested, but also simulate the unstable factors in the real experiment (such as excitation pulse angle deviation, shift gradient deviation and inhomogeneous field, etc.) to improve the robustness of the model to non-ideal experimental environments.

[0070] S6: Using the high-fidelity quantitative reconstruction method to obtain a trained neural network; specifically, inputting the generated training samples into the constructed neural network for training. By iterative training and adjusting the parameters of the neural network, the value of the loss function is minimized, thereby preserving the deep neural network parameters and ensuring the stability and accuracy of the training process.

[0071] S7: Use the trained neural network to quantitatively reconstruct the collected magnetic resonance images, input the multi-scan multi-parameter multi-overlap echo images into the neural network, and after a series of processing and calculations, obtain high-resolution multi-parameter magnetic resonance quantitative images. These images not only have clear texture structures and high resolution, but also accurately reflect multiple parameter information of the object to be tested (such as T2, T2 * , B1, PD, ΔB0, etc.).

[0072] Specifically, in step S1, designing a multi-scan multi-parameter multiple overlapping echo separation imaging sequence specifically includes:

[0073] S11: Design signal excitation module;

[0074] Figure 3 (a) is a multi-scanning, multi-parameter, multiple overlapping echo separation imaging sequence diagram proposed by the present invention, wherein α represents the flip angle of the radio frequency pulse, and four main echoes are generated by applying four excitation pulses continuously, which are used to generate signals with different contrast weightings.

[0075] S12: Design the shift gradient module;

[0076] G roi (i = 1, 2, 3, 4) represents the shift gradient of the i-th RF pulse in the frequency encoding direction, G pei (i = 1, 2, 3, 4) represents the shift gradient of the i-th RF pulse in the phase encoding direction, which refocuses the four main echoes to the specified position in k-space.

[0077] S13: Design data acquisition module;

[0078] In order to obtain quantitative information of multiple parameters simultaneously, SE-EPI and GRE-EPI readout modules were used to obtain k-space weighted by different parameters of interest, respectively. The former was mainly weighted by T2 signal, while the latter was mainly weighted by T2 signal. *Signal weighting is the main method. Considering that single-scan multi-parameter multi-overlap echo imaging is limited by lateral relaxation attenuation and cannot obtain high-resolution images, the present invention combines a multi-scan method to shorten the sampling echo chain length in the pulse sequence through multiple scans, reduce signal relaxation attenuation, and combine a parallel imaging method to reduce the scanning time increase caused by the multi-scan method, so as to achieve a balance between the minimum signal-to-noise ratio and scanning time required for high-resolution multi-parameter quantitative imaging. The entire sequence is repeated N times to cover the entire k-space. Figure 3 (b) shows the arrangement method of N scans in k-space, and R is the parallel imaging acceleration factor. Figure 3 (c) shows the k-space and weighted images acquired by a multi-scan, multi-parameter, multiple overlap echo separation imaging sequence.

[0079] Specifically, in step S2, determining the sampling parameters of the multi-scan multi-parameter multiple overlap echo separation imaging sequence specifically includes:

[0080] S21: Determine the size of each RF pulse flip angle α, the pulse shape, and the interval Δ between each RF excitation pulse i (i = 1, 2, 3, 4);

[0081] S22: Determine each shift gradient G roi , G pei the area, direction and application time of the

[0082] S23: Determine the number of repeated scans N shot ;

[0083] S24: determining a parallel imaging acceleration factor R;

[0084] After the above parameters are determined, the position and weighting degree of each overlapping echo in k-space are determined;

[0085] S25: Determine other acquisition parameters such as imaging field of view, imaging matrix, acquisition layer thickness, repeated acquisition time, etc.;

[0086] Specifically, in S4, the magnetic resonance signal collected is processed according to Figure 3 After rearrangement, splicing, zero filling and parallel reconstruction in the manner of (b), a multi-scanning, multi-parameter and multi-overlapping echo image is obtained;

[0087] Specifically, in S5, the high-fidelity quantitative reconstruction method based on the Swin Transformer structure is as follows:

[0088] S51: Determine the quantitative reconstruction neural network based on Swin Transformer;

[0089] The quantitative reconstruction neural network includes four modules: shallow feature extraction, deep feature extraction, main task and auxiliary task. The shallow feature extraction is completed by two cascaded convolution layers. The first convolution layer maps the input image to the shallow feature space. The second convolution further extracts the shallow features and implements downsampling, which improves the efficiency of deep feature extraction and relieves the calculation pressure. The deep feature extraction is composed of multiple Swin Transformer blocks. The high-performance self-attention mechanism of Transformer is used to realize deep feature extraction and improve the image reconstruction quality. The Swin Transformer block is composed of multiple Swin Transformer layers, and the head and tail are connected using residuals. The Swin Transformer layer first passes the input features through a normalization layer LayerNorm, then through a multi-head self-attention module, introduces residuals at the end of the multi-head self-attention, then passes through a normalization layer LayerNorm, and finally passes through a multi-layer perceptron MLP. The main task module is upsampled through a deconvolution layer to obtain quantitative reconstruction parameters; the auxiliary task obtains the added noise through another deconvolution layer.

[0090] S52: Design auxiliary tasks for noise learning;

[0091] The auxiliary task of noise learning is implemented by sharing the previous feature extraction layer and adding a noise prediction output at the end. Specifically, the main task network and the auxiliary task network share the same feature extraction structure to extract common features from the input data. After the feature extraction is completed, an output module for predicting noise is attached to estimate the noise component in the input data. Through this design, the model explicitly understands and separates the noise characteristics while learning the signal features, thereby enhancing the main task's ability to effectively extract the signal, significantly improving the accuracy of reconstruction and the generalization performance of the model, especially under low signal-to-noise ratio conditions. Such a design can be expressed as:

[0092]

[0093] Among them, L total Represents the loss of the entire model, L main represents the loss of the main task, L noise represents the noise estimation loss, and λ is the weight coefficient used to balance the learning of the main task and the auxiliary task.

[0094] S53: Building a neural network training framework using the Pytorch deep learning framework according to steps S51 and S52, and determining hyperparameters;

[0095] Determine the number of input and output channels of the neural network and the number of Swin Transformer blocks; determine the embedding dimension of the Swin Transformer structure, the number of attention heads and the sliding window size; determine the auxiliary task weight λ; determine the optimizer and learning rate for training the deep neural network;

[0096] S54: Generate neural network training samples;

[0097] According to the determined sequence and parameters, a training sample of a deep neural network is generated. The present invention takes into account that a neural network requires a large number of training samples, and real training samples are difficult to obtain. Therefore, the present invention uses a simulation method to generate the training samples required for the deep neural network. The specific steps are as follows:

[0098] The pulse sequence is input into the magnetic resonance imaging simulation software, and corresponding non-ideal items are added according to the non-ideality of the actual experiment to simulate the actual situation as much as possible;

[0099] A set amount of random templates are generated according to the characteristics of the object to be tested (or templates are generated using an MRI data set with the characteristics of the object to be tested); the complexity of the templates matches the object to be tested and should be able to contain all the characteristics of the experimental samples; the number of templates needs to be sufficient to ensure good reconstruction quality.

[0100] The template is simulated sampled using simulation software to obtain the magnetic resonance signal of the template; during the simulation sampling process, unstable factors are added in consideration of changes in the actual experimental environment to improve the robustness of the network model to an undesirable experimental environment; the unstable factors include excitation pulse angle deviation, shift gradient deviation, inhomogeneous field, etc.

[0101] The magnetic resonance signals of the templates are rearranged into two-dimensional k-space signals, and then two-dimensional Fourier transform is performed to obtain magnetic resonance images of each template, and the magnetic resonance images are normalized and random Gaussian noise is added to the real part and the imaginary part respectively;

[0102] The corresponding quantitative parameters in the template and the added noise are used as the corresponding labels for network training;

[0103] The normalized magnetic resonance images of each template and the corresponding labels constitute a training sample, and all simulation training samples are divided according to proportion to form a simulation sample training set and a verification set.

[0104] Specifically, in step S6, the training samples are used to train the neural network, as follows:

[0105] The training sample set is input into the deep neural network in batches for iterative training. Each time the network is trained, the value of the loss function is calculated. The parameters of the neural network are adjusted by the gradient descent method based on the value and the loss function to minimize the value of the loss function and save the parameters of the deep neural network. During training, the deep neural network achieves accurate quantitative reconstruction of the parameters by minimizing the error between the output and the quantitative parameters, while minimizing the error with the added noise, reducing the interference of the noise, improving the gradient update direction, and improving the performance under low signal-to-noise ratio conditions and the overall performance and robustness.

[0106] Specifically, in step S7, the trained neural network is used to quantitatively reconstruct the acquired magnetic resonance image to obtain a high-resolution multi-parameter magnetic resonance quantitative image, as follows:

[0107] The multi-scan multi-parameter multi-overlap echo image obtained in step S4 is input into the trained neural network obtained in step S6 to reconstruct a high-resolution multi-parameter magnetic resonance quantitative image.

[0108] A specific embodiment is given below.

[0109] Step 1: Design a multi-scan, multi-parameter, multiple overlapping echo separation imaging sequence and determine the sequence sampling parameters.

[0110] The design of magnetic resonance imaging sequences is as follows Figure 3 As shown in (a) in the figure, the excitation pulses α are all Sinc pulses with a flip angle of 30°, and the refocusing pulses β are Sinc pulses with a flip angle of 180°.

[0111] The time between each excitation pulse is Δ1 = Δ2 = Δ3 = 8.61ms, Δ4 = 7.78ms;

[0112] Repeat scan times N shot = 4;

[0113] Parallel imaging acceleration factor R = 2;

[0114] Assume that the readout module has a readout gradient area A in the frequency encoding direction during sampling ro ; Assume that the area of ​​the phase encoding direction of the readout module during sampling is A pe . A roi and A pei represent the shift gradient G applied after the i-th excitation pulse. roi and G pei The relative areas of each shift gradient are: A roi / A ro = 1 / 4, 1 / 4, 1 / 4, 1 / 8, G roi / G ro= -44 / 256, 22 / 256, -44 / 256, -88 / 256.

[0115] The imaging field of view FOV is 22 cm × 22 cm;

[0116] The imaging matrix size is 256×248;

[0117] The collection layer thickness is 3 mm;

[0118] The repeated acquisition time was 5 s.

[0119] Step 2: Use the designed sequence and sampling parameters in the magnetic resonance instrument that meets the sequence and sampling parameters to collect data on the imaging object and obtain the magnetic resonance signal. Figure 3 After parallel reconstruction, we obtain Figure 3 The multi-scan, multi-parameter, multiple overlapping echo image shown in (c) contains multiple overlapping echoes in its k-space and exhibits strip-like interference fringes in the image domain.

[0120] Step 3: Design a high-fidelity quantitative reconstruction method based on the Swin Transformer structure.

[0121] Determine the number of input and output channels of the neural network and the number of Swin Transformer blocks. Figure 4 As shown, the sequence described in this embodiment collects 2 k-space data, corresponding to 2 magnetic resonance images, and uses the real part and imaginary part of each magnetic resonance image as the input of the deep neural network, so the number of input channels of the deep neural network is 4. This embodiment reconstructs T2, T2 * , PD, B1, ΔB0, these five magnetic resonance quantitative parameter maps, so the number of output channels of the main task module of the neural network is 5. The auxiliary task module outputs the estimated noise, so the number of output channels of the auxiliary task module is 1. The number of Swin Transformer blocks is 6, the embedding dimension is 96, the number of attention heads is 4, and the sliding window size is 8. An improved L1 norm is used as the loss function of the main task, and the mean square error is used as the loss function of the auxiliary task, as follows:

[0122]

[0123] Among them, P n Indicates the target parameter map (such as T2 and T2 * ), S n is the image acquired by the magnetic resonance sequence, F(S n ;θ) represents the output of the network, n represents the nth sample in the batch size N, N p(Sn;θ) is the noise predicted by the auxiliary task, N in represents the actual noise added, ϵ is a small constant to improve the L1 norm to ensure numerical stability, and θ is the neural network parameter. The weighting coefficient of the auxiliary task is λ = 0.15.

[0124] The Adam optimizer is used to adjust the learning rate in an exponential decay manner: the initial learning rate is set to 0.0001, the number of iterations is set to decay once every 20,000 times, and the decay rate is 0.8.

[0125] To generate neural network training samples, the pulse sequence is imported into the magnetic resonance imaging simulation software, and corresponding correction items are added according to the non-ideal factors in the real experiment to be as close to the actual experimental conditions as possible. A series of random templates are generated according to the characteristics of the object to be tested. The complexity of the template should match the characteristics of the object to be tested and contain all the characteristics of the experimental samples; the number of templates should be sufficient to ensure good reconstruction quality. Subsequently, the templates are sampled using the simulation software to obtain the corresponding magnetic resonance signals. During the sampling process, combined with the changing factors of the real experimental environment, unstable factors such as excitation pulse angle deviation, gradient deviation and noise are added to improve the robustness of the model in non-ideal experimental environments. The magnetic resonance echo signals of the templates are rearranged into two-dimensional k-space signals, and the magnetic resonance images of each template are generated after two-dimensional Fourier transformation, and the images are normalized and noise is added. According to the characteristics of different parameters, the corresponding quantitative parameters in the templates are normalized to a range suitable for network learning to form corresponding label data. Finally, the normalized magnetic resonance images of each template and the corresponding labels are combined as training samples, and all simulated samples are divided into training sets and validation sets in proportion.

[0126] The training sample set is randomly divided into two parts: 80% for training and 20% for validation.

[0127] When training a deep neural network, the training sample set is input into the deep neural network in batches for iterative training. Each time the network is trained, the value of the loss function is calculated, and the parameter value of the neural network is automatically adjusted according to the value to reduce the value of the loss function. The above training is repeated until the value of the loss function tends to be stable, and the deep neural network parameter θ is saved.

[0128] Step 4: Use the trained neural network to quantitatively reconstruct the acquired magnetic resonance image to obtain a high-resolution multi-parameter magnetic resonance quantitative image.

[0129] The real human brain image collected in step 2 is input into the neural network trained in step 3 for reconstruction, generating Figure 4 The magnetic resonance multi-parameter quantitative image is shown. Figure 5 T2 and T2 showing real human brains *, PD, B1, ΔB0, where the left image is a quantitative reference image acquired using the reference method, and the right image is a quantitative parameter image generated by the high-fidelity reconstruction method of the present invention. It can be seen that the magnetic resonance quantitative parameter image generated by the reconstruction method of the present invention is highly consistent with the result of the reference method, has high imaging accuracy, and has a clear texture structure.

[0130] Figure 6 The results of reconstructing the simulated human brain samples in the validation set by inputting them into the neural network trained in step 3 are shown, where different degrees of Gaussian noise are added to simulate various signal-to-noise ratio conditions. The leftmost image in the first row is the real image of T2, and the right side is the T2 image generated by the reconstruction method of the present invention under different signal-to-noise ratio conditions; the second row is the absolute error image between the reconstruction result and the corresponding label image, which is magnified 10 times for easy observation. The third and fourth rows are T2, respectively. * The reconstruction and error images show that the high-fidelity reconstruction method based on Swin Transformer shows high accuracy and detail preservation ability under various signal-to-noise ratio conditions, especially under low signal-to-noise ratio conditions.

[0131] By comparing the imaging results of the reference method and the method of the present invention, it is found that the magnetic resonance quantitative parameter image generated by the reconstruction method of the present invention is highly consistent with the results of the reference method, has high imaging accuracy, and has a clear texture structure. In addition, the results of reconstruction under different signal-to-noise ratio conditions also show that the method of the present invention exhibits high accuracy and detail retention capabilities under various conditions. The present invention combines multi-scanning technology, multi-parameter imaging and a high-fidelity quantitative reconstruction method based on Swin Transformer to achieve high-resolution, multi-parameter, low-noise MRI imaging. Experimental results show that the present invention is superior to traditional methods in terms of imaging quality and parameter quantitative accuracy.

[0132] The present invention uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A high-resolution multi-parameter quantitative method for magnetic resonance based on multi-scanning overlapping echoes, characterized in that The following steps are involved: S1: Design a high-resolution multi-parameter quantitative method sequence of magnetic resonance based on overlapping echoes, called a multi-scan multi-parameter multiple overlapping echo separation imaging sequence, including designing a signal excitation module, a shift gradient module and a data acquisition module; S2: Determine the sampling parameters of the multi-scan multi-parameter multiple overlap echo separation imaging sequence; S3: using the designed sequence and sampling parameters in a magnetic resonance instrument that meets the sequence and sampling parameters, collecting data on the imaging object and obtaining a magnetic resonance signal; S4: After rearranging, splicing, zero-filling, and parallel reconstruction of the acquired magnetic resonance signals, a multi-scanning, multi-parameter, and multi-overlapping echo image is obtained; S5: Design a high-fidelity quantitative reconstruction method based on the Swin Transformer structure, which includes determining a quantitative reconstruction neural network based on the Swin Transformer, designing noise learning auxiliary tasks, using the Pytorch deep learning framework to build a neural network training framework and determine hyperparameters, and generating neural network training samples; S6: training the neural network using the high-fidelity quantitative reconstruction method designed in step S5 to obtain a trained neural network; S7: Use the neural network trained in step S6 to quantitatively reconstruct the acquired magnetic resonance image, input the multi-scan multi-parameter multi-overlap echo image into the neural network, and obtain a high-resolution multi-parameter magnetic resonance quantitative image.

2. A magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlap echoes as claimed in claim 1, characterized in that In step S1 , the design of the signal excitation module includes using a plurality of radio frequency pulses to generate echo signals with different contrasts.

3. A magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlap echoes as claimed in claim 1, characterized in that In step S1 , the design of the shift gradient module includes designing a specific shift gradient so that each echo signal is refocused into the same k-space and accurately moved to a specified position.

4. A magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlap echoes as claimed in claim 1, characterized in that In step S1, the design of the data acquisition module includes using different readout modules to acquire k-space data weighted by different parameters, and combining multi-scanning technology and parallel imaging methods to shorten the sampling echo chain length in the pulse sequence and reduce the scanning time.

5. A magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlap echoes as claimed in claim 1, characterized in that In step S2, the determining of sampling parameters of a multi-scan multi-parameter multiple overlap echo separation imaging sequence includes: S21: determining the RF pulse angle, shape and application time; S22: determining the displacement gradient area, direction and application time; S23: determining the number of scans to balance readout time and imaging resolution; S24: determining a parallel imaging acceleration factor to speed up acquisition; S25: Confirm other acquisition parameters.

6. A magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlap echoes as claimed in claim 1, characterized in that In step S5, the quantitative reconstruction neural network includes a shallow feature extraction module, a deep feature extraction module, a main task module and an auxiliary task module, wherein the deep feature extraction module uses a Swin Transformer block to extract deep features; the noise learning auxiliary task is achieved by sharing the previous feature extraction layer and adding a noise prediction output at the end to improve the reconstruction accuracy and the generalization performance of the model.

7. A magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlap echoes as claimed in claim 1, characterized in that In step S5, generating neural network training samples includes using a simulation method to generate magnetic resonance images with different features and parameters as training samples, and simulating unstable factors in real experiments to improve the robustness of the model to non-ideal experimental environments.

8. A magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlap echoes as claimed in claim 1, characterized in that In step S6, the neural network training includes inputting the training sample set into the deep neural network in batches for iterative training, and adjusting the parameters of the neural network to minimize the value of the loss function.

9. A magnetic resonance high-resolution multi-parameter quantitative method based on multi-scanning overlap echoes as claimed in claim 1, characterized in that In step S7, the high-resolution multi-parameter magnetic resonance quantitative image includes parameters T2, T2 * , B1, PD, and ΔB0 images, these quantitative parameter maps can be acquired simultaneously and have clear texture structure and noise robustness.

10. A high-resolution multi-parameter quantitative magnetic resonance system based on multi-scanning overlapping echo acquisition, characterized in that include: The sequence design module is responsible for designing the multi-scan multi-parameter multiple overlap echo separation imaging sequence, including the specific implementation of signal excitation, shift gradient and data acquisition modules, and passing the design parameters to the sampling parameter determination module; The sampling parameter determination module further determines the specific sampling parameters of the RF pulse angle, shape, application time, shift gradient area, direction, application time, number of scans, and parallel imaging acceleration factor according to the design parameters, and provides these parameters to the data acquisition module; The data acquisition module collects data on the imaging object in the magnetic resonance instrument according to the given sequence and sampling parameters, obtains magnetic resonance signals, and transmits these signals to the image preprocessing module; The image preprocessing module performs rearrangement, splicing, zero filling, and parallel reconstruction preprocessing operations on the acquired magnetic resonance signals to generate multi-scanning, multi-parameter, and multi-overlap echo images, and transmits them to the neural network reconstruction module; The neural network reconstruction module uses a high-fidelity quantitative reconstruction neural network based on the Swin Transformer structure to quantitatively reconstruct the preprocessed image to obtain a high-resolution multi-parameter magnetic resonance quantitative image. This module also needs to interact with the neural network training module to obtain a trained neural network model. The neural network training module is responsible for designing the training framework of the neural network, using the magnetic resonance images with different characteristics and parameters provided by the simulation data generation module as training samples, training the neural network, and providing the trained model to the neural network reconstruction module; The simulation data generation module is specifically used to generate simulation data required for training; The result display module receives the reconstructed image output by the neural network reconstruction module and displays it for users to view and analyze; These modules work together to realize the complete process from sequence design to data acquisition, preprocessing, quantitative reconstruction and result presentation.

Images