Dynamic magnetic resonance imaging method and apparatus, model training method, device and medium

Abstract

A dynamic magnetic resonance imaging method and apparatus, a model training method, a device and a medium. The dynamic magnetic resonance imaging method comprises: acquiring a dynamic magnetic resonance image to be reconstructed; and inputting said dynamic magnetic resonance image into a trained imaging model to obtain a reconstructed dynamic magnetic resonance image, wherein the reconstructed dynamic magnetic resonance image is an up-sampled image of said dynamic magnetic resonance image, the imaging model comprises a quantum convolutional neural network and a common convolutional neural network, the quantum convolutional neural network is used for performing feature extraction on the dynamic magnetic resonance image to be reconstructed to obtain a corresponding feature map, and the common convolutional neural network is used for converting the feature map into the reconstructed dynamic magnetic resonance image.

Description

Dynamic magnetic resonance imaging method, model training method, device, equipment and medium Technical Field

[0001] The present invention belongs to the field of medical imaging technology, and in particular relates to a dynamic magnetic resonance imaging method, a model training method, a device, equipment and a medium. Background Art

[0002] Magnetic resonance imaging (MRI) utilizes static and radiofrequency magnetic fields to image human tissue. It provides rich tissue contrast and is harmless to the human body, making it a powerful tool for clinical diagnosis. However, slow imaging speed has been a major bottleneck restricting its rapid development. Improving scanning speed and thus reducing scanning time while maintaining clinically acceptable imaging quality is crucial.

[0003] In the imaging field, deep learning methods are currently a common technique for MRI image reconstruction. Deep learning methods utilize neural networks to learn the optimal reconstruction parameters from large amounts of training data, or directly learn the mapping relationship between undersampled data and fully sampled images. This approach achieves better imaging quality and higher acceleration than traditional parallel imaging or compressed sensing methods. However, dynamic MRI images require a large amount of data, and traditional deep learning algorithms consume a significant amount of time to process this large amount of data, facing challenges such as insufficient computing resources and low computational efficiency.

[0004] Summary of the Invention

[0005] The present invention provides a dynamic magnetic resonance imaging method, model training method, device, equipment and medium, aiming to solve the problems of insufficient computing resources and low computing efficiency in existing deep learning imaging methods.

[0006] In a first aspect, an embodiment of the present invention provides a dynamic magnetic resonance imaging method, which comprises:

[0007] acquiring a dynamic magnetic resonance image to be reconstructed;

[0008] The dynamic magnetic resonance image to be reconstructed is input into a trained imaging model to obtain a reconstructed dynamic magnetic resonance image; wherein the reconstructed dynamic magnetic resonance image is an upsampled image of the dynamic magnetic resonance image to be reconstructed; the imaging model includes a quantum convolutional neural network and a conventional convolutional neural network, the quantum convolutional neural network is used to extract features from the dynamic magnetic resonance image to be reconstructed to obtain a corresponding feature map; the conventional convolutional neural network is used to convert the feature map into the reconstructed dynamic magnetic resonance image.

[0009] In a second aspect, an embodiment of the present invention provides a model training method, which includes

[0010] Acquire dynamic magnetic resonance image samples; wherein the dynamic magnetic resonance image samples include the dynamic magnetic resonance image to be reconstructed and the corresponding full-sampling image samples;

[0011] Performing feature extraction on the dynamic magnetic resonance image to be reconstructed by using a preset quantum convolutional neural network to obtain a corresponding feature map;

[0012] Inputting the feature map into a preset common convolutional neural network to output a reconstructed dynamic magnetic resonance image of the dynamic magnetic resonance image to be reconstructed;

[0013] Model parameters are optimized by minimizing the loss between the reconstructed dynamic magnetic resonance image and the fully sampled image samples.

[0014] In a third aspect, an embodiment of the present invention provides a dynamic magnetic resonance imaging device, which comprises

[0015] an acquisition module, used for acquiring a dynamic magnetic resonance image to be reconstructed;

[0016] An imaging module is configured to input the dynamic magnetic resonance image to be reconstructed into a trained imaging model to obtain a reconstructed dynamic magnetic resonance image; wherein the reconstructed dynamic magnetic resonance image is an upsampled image of the dynamic magnetic resonance image to be reconstructed; wherein the imaging model includes a quantum convolutional neural network and a conventional convolutional neural network, wherein the quantum convolutional neural network is configured to perform feature extraction on the dynamic magnetic resonance image to be reconstructed to obtain a corresponding feature map; and wherein the conventional convolutional neural network is configured to convert the feature map into the reconstructed dynamic magnetic resonance image.

[0017] In a fourth aspect, an embodiment of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned dynamic magnetic resonance imaging method when executing the computer program.

[0018] In a fifth aspect, an embodiment of the present invention provides a storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions are executed by one or more processors to implement the above-mentioned dynamic magnetic resonance imaging method.

[0019] Compared to existing technologies, this invention, based on a deep learning approach, incorporates quantum neural networks into traditional neural network models. By cascading a quantum convolutional neural network with a traditional convolutional neural network, it reconstructs magnetic resonance images. Leveraging quantum parallelism, it potentially alleviates the overfitting problem of convolutional neural networks. It also leverages quantum mechanical concepts such as entanglement, superposition, and interference to provide faster and more powerful image reconstruction capabilities for dynamic magnetic resonance imaging. Compared to classical computing networks, this approach not only reduces computation time but also produces higher-quality dynamic magnetic resonance reconstruction images. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] FIG1 is a schematic diagram of the main process of a dynamic magnetic resonance imaging method provided by an embodiment of the present invention;

[0022] FIG2 is a schematic diagram of a sub-process of the embodiment shown in FIG1 ;

[0023] FIG3 is a schematic diagram of a sub-process of the embodiment shown in FIG1 ;

[0024] FIG4 is a schematic diagram of a flow chart of a model training method according to the embodiment shown in FIG1 ;

[0025] FIG5 is a schematic diagram of the structure of the quantum convolutional neural network in the embodiment shown in FIG1 ;

[0026] FIG6 is a schematic diagram of the structure of the convolution module in the embodiment shown in FIG5 ;

[0027] FIG7 is a schematic diagram of the structure of a common convolutional neural network in the embodiment shown in FIG1 ;

[0028] FIG8 is a block diagram of the module structure of a dynamic magnetic resonance imaging device provided by an embodiment of the present invention;

[0029] FIG9 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0031] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0032] Please refer to FIG. 1 to FIG. 4 . FIG. 1 shows a schematic diagram of the main flow of a dynamic magnetic resonance imaging method provided by an embodiment of the present invention. An embodiment of the dynamic magnetic resonance imaging method of the present invention includes the following steps S100 to S200:

[0033] S100: Acquire a dynamic magnetic resonance image to be reconstructed.

[0034] S200, inputting the dynamic magnetic resonance image to be reconstructed into the trained imaging model to obtain a reconstructed dynamic magnetic resonance image;

[0035] Among them, the reconstructed dynamic magnetic resonance image is an upsampled image of the dynamic magnetic resonance image to be reconstructed; the imaging model includes a quantum convolutional neural network and a conventional convolutional neural network. The quantum convolutional neural network is used to extract features of the dynamic magnetic resonance image to be reconstructed to obtain the corresponding feature map; the conventional convolutional neural network is used to convert the feature map into the reconstructed dynamic magnetic resonance image.

[0036] In this embodiment, an imaging model is constructed based on a machine learning method, and by training the imaging model, the image can be reconstructed to obtain a reconstructed upsampled image to improve the image quality. Specifically, the method of the present invention is applied to the field of magnetic resonance and is used to reconstruct dynamic magnetic resonance images; and the constructed imaging model specifically includes a quantum convolutional neural network and an ordinary convolutional neural network; the quantum convolutional neural network is a convolutional neural network composed of quantum circuits under a quantum computer, which is used to extract features from dynamic magnetic resonance images, and the ordinary convolutional neural network is a neural network based on a traditional convolutional architecture, which is used to convert feature maps into reconstructed dynamic magnetic resonance images. The quantum convolutional neural network and the ordinary convolutional neural network are connected in series to construct an imaging model, and the output of the quantum convolutional neural network is used as the input of the ordinary convolutional neural network.

[0037] Deep learning methods often require extensive training to achieve good results, have high time and space complexity, and may face insufficient computing resources in dynamic magnetic resonance reconstruction. The method of the present invention is based on deep learning and incorporates quantum neural networks into traditional neural networks. Compared with traditional neural network training methods, the quantum computing in this method has higher computational efficiency. Compared with convolutional neural network methods based on classical computers, quantum convolutional neural networks can more efficiently search for optimal solutions or near-optimal solutions due to the characteristics of quantum, achieving higher processing efficiency.

[0038] In an optional embodiment, as shown in FIG2 , the process of extracting features from the dynamic magnetic resonance image to be reconstructed using a quantum convolutional neural network includes the following steps S210 to S230:

[0039] S210 , encoding the dynamic magnetic resonance image to be reconstructed, and converting it into a quantum state of a quantum bit.

[0040] S220. Perform a quantum convolution operation on the quantum state to obtain a changed quantum state.

[0041] S230. Measure the changed quantum state to obtain a characteristic graph.

[0042] In this embodiment, as shown in FIG5 , the quantum convolutional neural network includes an encoding module, a convolution module, and a measurement module; wherein the encoding module is used to encode the dynamic magnetic resonance image to be reconstructed and convert it into a quantum state of a quantum bit; the convolution module is used to perform a quantum convolution operation on the quantum state to obtain a changed quantum state; and the measurement module is used to measure the changed quantum state to obtain a feature map. It can be understood that the quantum convolutional neural network is implemented by a quantum circuit constructed based on a quantum computer. The quantum circuit includes quantum bits and quantum gates. The encoding module in the quantum circuit extracts the features of the dynamic magnetic resonance image to be reconstructed and encodes them into a quantum state. The convolution module performs a logical operation on the quantum state to obtain the changed quantum state. Finally, the measurement module observes the changed quantum state to obtain the final measurement result and complete the entire feature extraction process.

[0043] In an optional embodiment, as shown in Figure 6, the quantum circuit includes four qubits arranged in sequence from top to bottom, and the entire circuit runs in sequence from left to right. The quantum convolution module includes two entangled layers connected in series, each entangled layer is provided with eight rotational logic gates, and the rotation angle of the rotational logic gate is a trainable parameter. Specifically, the eight rotational logic gates include four RZ rotational gates and four RY rotational gates; wherein, each RZ gate and RY gate is located on a different qubit, the first RZ gate is located on the first qubit and is controlled by the first qubit, the second RZ gate is located on the third qubit and is controlled by the second qubit, the third RZ gate is located on the fourth qubit and is controlled by the third qubit, and the fourth RZ gate is located on the first qubit and is controlled by the fourth qubit; the first RY gate is located after the fourth RZ gate, the second RY gate is located after the first RZ gate, the third RY gate is located after the second RZ gate, and the fourth RY gate is located after the third RZ gate.

[0044] Quantum convolutional neural networks (CNNs) are built on quantum computers, utilizing quantum bits and quantum gates for computation. They employ properties such as quantum parallel processing and quantum superposition, which can accelerate computational processes in specific situations. In a CNN, each input sample is encoded as a quantum state, meaning the input data is quantized. Quantum gate operations are then used to transform and process the input data, allowing CNNs to extract quantum feature representations from images. Compared to traditional CNNs, quantum computing offers the advantages of parallelism and superposition, potentially alleviating the overfitting problem of CNNs. Quantum convolutional neural networks can handle more complex computational tasks and, in certain situations, achieve higher computational efficiency. Furthermore, CNNs incorporate the concept of quantum superposition, enabling the model to simultaneously consider multiple possibilities. This enhances the model's expressive power and generalization capabilities, contributing to improved image quality.

[0045] In an optional embodiment, as shown in FIG3 , a common convolutional neural network is constructed based on a U-net network. The process of converting the feature map into a reconstructed dynamic magnetic resonance image by the common convolutional neural network includes the following steps S240 to S250:

[0046] S240: Perform a downsampling operation on the feature map to obtain an intermediate feature map.

[0047] S250: Perform an upsampling operation on the intermediate feature map to obtain a reconstructed dynamic magnetic resonance image.

[0048] The convolutional neural network U-net is mainly composed of an encoder and a decoder. The encoder is used to extract image features and gradually reduce the resolution, while the decoder is responsible for gradually upsampling the low-resolution features and fusing them with the high-resolution features of the encoder, and finally outputting the segmentation results.

[0049] Specifically, as shown in Figure 7, the convolutional neural network includes an input module, a first downsampling module, a second downsampling module, a first upsampling module, a second upsampling module, and an output module; the input module, the first downsampling module, and the second downsampling module perform a downsampling operation on the feature map to obtain an intermediate feature map, and the first upsampling module, the second upsampling module, and the output module perform an upsampling operation on the intermediate feature map to obtain a reconstructed dynamic magnetic resonance image. More specifically, the input module includes two 3*3*3 convolutional layers, the first downsampling module and the second downsampling module each include a 2*2 global pooling layer and two 3*3*3 convolutional layers, the first upsampling module and the second upsampling module each include a one-hop link layer, a 3*3*3 upconvolutional layer, and two 3*3*3 convolutional layers, and the output module includes a 3*3*3 convolutional layer.

[0050] A 3D residual U-net was used to reduce undersampling artifacts in cardiac dynamic magnetic resonance imaging. The residual U-net consists of a contracting multiscale decomposition path and a symmetric expansion path with skip connections at each scale. As shown in Figure 7, 3D convolutions are trained on the entire image sequence to enforce temporal consistency between image frames. Images reconstructed from the undersampled data serve as input to the network, and the output is an anti-aliased reconstructed image. Each convolutional layer is equipped with a rectified linear unit (ReLU) as the nonlinear activation function. The residual U-net includes a skip connection at each scale between the encoder and decoder paths.

[0051] U-net has a compact network structure, resulting in relatively few network parameters and fast training speed, which can reduce the risk of overfitting and improve the generalization ability of the model. In addition, U-net also introduces the skip connection structure, which skips the feature map of the encoder part and the decoder part, thereby retaining more spatial and contextual information. This helps to improve the accuracy of the segmentation results and the ability to retain details.

[0052] As shown in FIG4 , the present invention further provides a model training method for obtaining the trained imaging model in the above method. The training process specifically includes the following steps S10 to S40:

[0053] S10, obtaining a dynamic magnetic resonance image sample;

[0054] The dynamic magnetic resonance image samples include the dynamic magnetic resonance image to be reconstructed and the corresponding full-sampling image samples.

[0055] S20. Perform feature extraction on the dynamic magnetic resonance image to be reconstructed through a preset quantum convolutional neural network to obtain a corresponding feature map.

[0056] S30, inputting the feature map into a preset common convolutional neural network to output a reconstructed dynamic magnetic resonance image of the dynamic magnetic resonance image to be reconstructed.

[0057] S40, optimizing the model parameters by minimizing the loss between the reconstructed dynamic magnetic resonance image and the fully sampled image samples.

[0058] In this embodiment, an imaging model constructed based on a quantum convolutional neural network and a conventional convolutional neural network is trained. The training method relies on inputting undersampled dynamic magnetic resonance image samples, comparing the reconstructed image generated by the model with the fully sampled image corresponding to the undersampled dynamic magnetic resonance image sample, and establishing a loss function. The model parameters are optimized by minimizing the value of the loss function, where the model parameters include the quantum gate parameters in the quantum convolutional neural network and the convolution kernel parameters of the conventional convolutional neural network. In an optional embodiment, the loss value of the reconstructed dynamic magnetic resonance image and the fully sampled image sample is calculated using a mean square error loss function; if the loss value is zero or the number of model training iterations reaches a preset number, the model training is stopped to obtain the optimized model parameters.

[0059] As shown in Figure 8, an embodiment of the present invention also provides a dynamic magnetic resonance imaging device 100, which includes an acquisition module 101 and an imaging module 102, wherein the acquisition module 101 is used to acquire a dynamic magnetic resonance image to be reconstructed; the imaging module 102 is used to input the dynamic magnetic resonance image to be reconstructed into a trained imaging model to obtain a reconstructed dynamic magnetic resonance image; wherein the reconstructed dynamic magnetic resonance image is an upsampled image of the dynamic magnetic resonance image to be reconstructed; wherein the imaging model includes a quantum convolutional neural network and a conventional convolutional neural network, wherein the quantum convolutional neural network is used to perform feature extraction on the dynamic magnetic resonance image to be reconstructed to obtain a corresponding feature map; and the conventional convolutional neural network is used to convert the feature map into a reconstructed dynamic magnetic resonance image.

[0060] In an optional embodiment, the imaging module 102 includes an encoding module, a convolution module, and a measurement module; wherein the encoding module is used to encode the dynamic magnetic resonance image to be reconstructed and convert it into a quantum state of a quantum bit; the convolution module is used to perform a quantum convolution operation on the quantum state to obtain a changed quantum state; and the measurement module is used to measure the changed quantum state to obtain a feature map.

[0061] In an optional embodiment, the imaging module 102 includes a downsampling module and an upsampling module; wherein the downsampling module is used to perform a downsampling operation on the feature map to obtain an intermediate feature map; and the upsampling module is used to perform an upsampling operation on the intermediate feature map to obtain a reconstructed dynamic magnetic resonance image.

[0062] In an optional embodiment, the apparatus further includes a model training module, which is configured to train the imaging module. Furthermore, the training module includes a sample acquisition module and a parameter optimization module. The acquisition module is configured to acquire dynamic magnetic resonance image samples, wherein the dynamic magnetic resonance image samples include the dynamic magnetic resonance image to be reconstructed and the corresponding fully sampled image samples. The parameter optimization module is configured to optimize the model parameters by minimizing the loss between the reconstructed dynamic magnetic resonance image and the fully sampled image samples.

[0063] As shown in FIG9 , an embodiment of the present invention further provides an electronic device 140, comprising a processor 141, a memory 142, a non-volatile memory 144, and a computer program 1441 stored in the non-volatile memory 144 and executable on the processor. When the processor 141 executes the computer program 1441, any of the above-described embodiments of the dynamic magnetic resonance imaging method are implemented. Specifically, the electronic device 140 further comprises an input / output interface 145 and an input / output device 146 connected thereto. The processor 141, the memory 142, the non-volatile memory 144, and the input / output interface 145 are connected via an internal bus 143.

[0064] It should be understood that in the embodiments of the present invention, the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0065] The present invention also proposes a storage medium. In an exemplary embodiment, the storage medium stores at least one instruction, at least one program, code set or instruction set. When the at least one instruction, at least one program, code set or instruction set is executed by a processor of a computer device, it implements the dynamic magnetic resonance imaging method of any of the above embodiments.

[0066] Those skilled in the art will appreciate that all or part of the steps in the method of the above-described embodiment can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the steps in the method of the above-described embodiment.

[0067] It will be understood that the present invention is described by way of some embodiments, and it will be appreciated by those skilled in the art that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of the present invention are intended to be protected by the present invention.

Claims

1. A dynamic magnetic resonance imaging method, characterized in that: The method includes: acquiring a dynamic magnetic resonance image to be reconstructed; The dynamic magnetic resonance image to be reconstructed is input into a trained imaging model to obtain a reconstructed dynamic magnetic resonance image; wherein the reconstructed dynamic magnetic resonance image is an upsampled image of the dynamic magnetic resonance image to be reconstructed; the imaging model includes a quantum convolutional neural network and a conventional convolutional neural network, the quantum convolutional neural network is used to extract features from the dynamic magnetic resonance image to be reconstructed to obtain a corresponding feature map; the conventional convolutional neural network is used to convert the feature map into the reconstructed dynamic magnetic resonance image.

2. The method according to claim 1, characterized in that The process of extracting features of the dynamic magnetic resonance image to be reconstructed by the quantum convolutional neural network includes: Encoding the dynamic magnetic resonance image to be reconstructed and converting it into a quantum state of a quantum bit; performing a quantum convolution operation on the quantum state to obtain a changed quantum state; The changed quantum state is measured to obtain the characteristic graph.

3. The method according to claim 2, characterized in that The quantum convolutional neural network includes a quantum convolution module, which is implemented by a quantum circuit. The quantum circuit includes four qubits. The quantum convolution module includes two entangled layers connected in series. The entangled layers include four RZ gates and four RY gates. The first RZ gate is located on the first qubit and is controlled by the first qubit, the second RZ gate is located on the third qubit and is controlled by the second qubit, the third RZ gate is located on the fourth qubit and is controlled by the third qubit, and the fourth RZ gate is located on the first qubit and is controlled by the fourth qubit. The four RY gates are respectively located at different qubits, and the RY gate is located after the RZ gate.

4. The method according to claim 1, wherein The common convolutional neural network is constructed based on the U-net network, and the process of converting the feature map into the reconstructed dynamic magnetic resonance image by the common convolutional neural network includes: Performing a downsampling operation on the feature map to obtain an intermediate feature map; An upsampling operation is performed on the intermediate feature map to obtain the reconstructed dynamic magnetic resonance image.

5. The method according to claim 4, characterized in that The ordinary convolutional neural network includes an input module, a first downsampling module, a second downsampling module, a first upsampling module, a second upsampling module and an output module; the input module includes two convolutional layers, the first downsampling module and the second downsampling module each include a global pooling layer and two convolutional layers, the first upsampling module and the second upsampling module each include a jump connection layer, an upconvolution layer and two convolutional layers, and the output module includes a convolutional layer.

6. A model training method, characterized in that: include: Acquire dynamic magnetic resonance image samples; wherein the dynamic magnetic resonance image samples include the dynamic magnetic resonance image to be reconstructed and the corresponding full-sampling image samples; Performing feature extraction on the dynamic magnetic resonance image to be reconstructed by using a preset quantum convolutional neural network to obtain a corresponding feature map; Inputting the feature map into a preset common convolutional neural network to output a reconstructed dynamic magnetic resonance image of the dynamic magnetic resonance image to be reconstructed; Model parameters are optimized by minimizing the loss between the reconstructed dynamic magnetic resonance image and the fully sampled image samples.

7. The model training method according to claim 6, characterized in that Optimizing the model parameters by minimizing the loss between the reconstructed dynamic magnetic resonance image and the fully sampled image samples, comprising: Calculating the loss value of the reconstructed dynamic magnetic resonance image and the full sampling image sample by using a mean square error loss function; If the loss value is zero or the number of model training iterations reaches a preset number, the model training is stopped to obtain the optimized model parameters.

8. A dynamic magnetic resonance imaging device, characterized in that: The device comprises: an acquisition module, used for acquiring a dynamic magnetic resonance image to be reconstructed; An imaging module is configured to input the dynamic magnetic resonance image to be reconstructed into a trained imaging model to obtain a reconstructed dynamic magnetic resonance image; wherein the reconstructed dynamic magnetic resonance image is an upsampled image of the dynamic magnetic resonance image to be reconstructed; wherein the imaging model includes a quantum convolutional neural network and a conventional convolutional neural network, wherein the quantum convolutional neural network is configured to perform feature extraction on the dynamic magnetic resonance image to be reconstructed to obtain a corresponding feature map; and wherein the conventional convolutional neural network is configured to convert the feature map into the reconstructed dynamic magnetic resonance image.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 5 when executing the computer program.

10. A storage medium having computer-readable instructions stored thereon, characterized in that: The computer-readable instructions are executed by one or more processors to implement the method according to any one of claims 1 to 5.

Images