Fmri generation method and system based on generative adversarial network model

Abstract

Disclosed in the present invention are an fMRI generation method and system based on a generative adversarial network model. The method comprises: collecting MRI and fMRI pairing data of a plurality of target collection objects, and establishing a training data set; using the training data set to train a generator and a discriminator in a generative adversarial network model, and optimizing network parameters of the generator and network parameters of the discriminator; and acquiring an MRI image of a target object to be collected, inputting the MRI image of said target object into the trained generative adversarial network model, so as to directly generate an fMRI image of said target object. In the present invention, MRI data of collection objects is used to generate corresponding fMRI data, and the MRI data of each collection object can be converted into the fMRI data, such that each collection object has the MRI data and the fMRI data, accurate and reliable information can be provided for downstream tasks, and the existing single-modal data can also be used to the maximum extent, thereby avoiding data waste; and the dependence on the collection of the fMRI data, thereby reducing the complexity and cost of clinical operations.

Description

A method and system for generating fMRI based on a generative adversarial network model Technical Field

[0001] This invention relates to the field of magnetic resonance imaging technology, and in particular to an fMRI generation method, system, terminal, and computer-readable storage medium based on a generative adversarial network model. Background Technology

[0002] Magnetic resonance imaging (MRI) provides high-resolution anatomical images, while functional magnetic resonance imaging (fMRI) reveals the brain's functional activity. However, in clinical practice, fMRI data is often difficult to obtain due to time and resource limitations associated with MRI acquisition. This results in a situation where only MRI or fMRI data may be available for the same patient, and very few patients possess both types of data simultaneously. Furthermore, fMRI acquisition is costly, time-consuming, and requires specific patient expertise, making it generally not feasible for every patient.

[0003] This situation presents two main problems: First, using only unimodal data to inform diagnosis, while avoiding the problem of insufficient data, significantly reduces diagnostic accuracy. Second, considering only multimodal data to inform diagnosis necessitates discarding patient information with only unimodal data, which not only wastes valuable medical data but also reduces the usable sample size, further limiting the practical application of multimodal data.

[0004] Therefore, existing technologies still need to be improved and developed.

[0005] Summary of the Invention

[0006] The main objective of this invention is to provide an fMRI generation method, system, terminal, and computer-readable storage medium based on a generative adversarial network model, aiming to solve the problems of high cost, long time, and high requirements for the acquisition objects in the prior art for acquiring fMRI images.

[0007] To achieve the above objectives, this invention provides an fMRI generation method based on a generative adversarial network (GAN) model, which includes the following steps:

[0008] Collect paired MRI and fMRI data of multiple target acquisition objects, and build a training dataset based on the paired MRI and fMRI data;

[0009] The generator and discriminator in the generative adversarial network model are trained using the training dataset, and the network parameters of the generator and the discriminator are optimized to obtain a trained generative adversarial network model.

[0010] The MRI image of the target object is acquired, and then the MRI image of the target object is input into the trained generative adversarial network model to directly generate the fMRI image of the target object.

[0011] Optionally, the fMRI generation method based on a generative adversarial network model, wherein collecting paired MRI and fMRI data of multiple target acquisition objects and establishing a training dataset based on the paired MRI and fMRI data specifically includes:

[0012] Collect paired MRI and fMRI data from multiple target acquisition objects, wherein the paired MRI and fMRI data includes MRI images and real fMRI images;

[0013] The paired MRI and fMRI data are preprocessed, including denoising, standardization, and registration.

[0014] A training dataset was created based on preprocessed paired MRI and fMRI data.

[0015] Optionally, the fMRI generation method based on a generative adversarial network model includes a generator and a discriminator.

[0016] The generator is used to generate fMRI images based on MRI images;

[0017] The discriminator is used to determine the difference between the fMRI image generated by the generator and the real fMRI image;

[0018] The generator uses the ResNet architecture to capture multi-scale features;

[0019] The discriminator uses a CNN architecture to improve the fine-grainedness of discrimination.

[0020] Optionally, the fMRI generation method based on a generative adversarial network (GAN) model, wherein training the generator and discriminator in the GAN model using the training dataset, and optimizing the network parameters of the generator and the discriminator to obtain a trained GAN model, specifically includes:

[0021] MRI images and random Gaussian noise are input into the network structure of the generator for training to generate fMRI images;

[0022] The fMRI image generated by the generator is input into the network structure of the discriminator along with the real fMRI image;

[0023] The discriminator distinguishes between generated fMRI images and real fMRI images, and outputs a true / false classification result.

[0024] Based on the true / false classification results of the discriminator, backpropagation optimizes the network parameters of the generator and the discriminator, so that the fMRI image generated by the generator is as close as possible to the real fMRI image, and the discriminator can distinguish between the real fMRI image and the generated fMRI image as accurately as possible.

[0025] Optionally, the fMRI generation method based on a generative adversarial network model further includes:

[0026] The generator and the discriminator are optimized by using the loss function of the generative adversarial network model, so that the fMRI images generated by the generator are as similar as possible to the real fMRI data, while at the same time enhancing the discrimination ability of the discriminator.

[0027] Optionally, in the fMRI generation method based on a generative adversarial network model, the loss function of the generative adversarial network model includes adversarial loss and generation loss;

[0028] The adversarial loss is used to optimize the adversarial learning between the generator and the discriminator, so that the fMRI images generated by the generator gradually approximate the distribution of the real data.

[0029] The generation loss is used to reduce the pixel difference between the generated fMRI image and the real fMRI image, thereby improving the quality of the generated image.

[0030] Optionally, in the fMRI generation method based on a generative adversarial network (GAN) model, the loss function of the GAN model is:

[0031] in, This represents the loss function of the generative adversarial network model. Indicating resistance to loss, Indicates the generation loss;

[0032] The resistance loss for:

[0033] Where G represents the generator, D represents the discriminator, x represents the MRI image, y represents the real fMRI image, z represents random Gaussian noise, and D(x,y) represents the true / false classification result obtained by the discriminator between the MRI image and the real fMRI image. Let G(x,z) represent the expectation of logD(x,y), G(x,z) represent the result obtained by the generator after the MRI image and random Gaussian noise are fed into it, and D(x,G(x,z)) represent the result obtained by the discriminator after the MRI image and the fMRI image generated by the generator are passed through it. This represents the expectation of log(1-D(x,G(x,z))).

[0034] The generation loss for:

[0035] Where λ represents a given parameter, This represents the expectation of ||yG(x,z)||1.

[0036] Furthermore, to achieve the above objectives, the present invention also provides an fMRI generation system based on a generative adversarial network (GAN) model, wherein the fMRI generation system based on the GAN model comprises:

[0037] The data acquisition module is used to collect paired MRI and fMRI data from multiple target acquisition objects and to build a training dataset based on the paired MRI and fMRI data.

[0038] The model training module is used to train the generator and discriminator in the generative adversarial network model using the training dataset, optimize the network parameters of the generator and the discriminator, and obtain the trained generative adversarial network model.

[0039] The image generation module is used to acquire MRI images of the target object, input the MRI images of the target object into the trained generative adversarial network model, and directly generate fMRI images of the target object.

[0040] Furthermore, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and an fMRI generation program based on a generative adversarial network model stored in the memory and executable on the processor, wherein when the fMRI generation program based on the generative adversarial network model is executed by the processor, it implements the steps of the fMRI generation method based on the generative adversarial network model as described above.

[0041] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an fMRI generation program based on a generative adversarial network model, and the fMRI generation program based on the generative adversarial network model, when executed by a processor, implements the steps of the fMRI generation method based on the generative adversarial network model as described above.

[0042] In this invention, paired MRI and fMRI data of multiple target subjects are collected, and a training dataset is established based on the paired MRI and fMRI data. The generator and discriminator in a generative adversarial network (GAN) model are trained using the training dataset, and the network parameters of the generator and discriminator are optimized to obtain a trained GAN model. MRI images of the target subjects are acquired and input into the trained GAN model to directly generate fMRI images of the target subjects. This invention utilizes the MRI data of the acquired subjects to generate corresponding fMRI data. The MRI data of each acquired subject can be converted into fMRI data, thus providing each acquired subject with both MRI and fMRI data. This not only provides accurate and reliable information for downstream tasks but also maximizes the use of existing single-modal data, avoiding data waste, reducing reliance on fMRI data acquisition, and lowering the complexity and cost of clinical procedures. Attached Figure Description

[0043] Figure 1 is a flowchart of a preferred embodiment of the fMRI generation method based on a generative adversarial network model of the present invention;

[0044] Figure 2 is a schematic diagram of the training of the generative adversarial network model in a preferred embodiment of the fMRI generation method based on the generative adversarial network model of the present invention.

[0045] Figure 3 is a schematic diagram of a preferred embodiment of the fMRI generation system based on a generative adversarial network model of the present invention;

[0046] Figure 4 is a schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0048] Currently, research using GANs (Generative Adversarial Networks) to generate medical images has made some progress. For example, SRGAN has been used to improve the resolution of medical images. Although this method is not directly used for modality transfer, it demonstrates the potential of GANs in improving image quality. CycleGAN is a generative adversarial network that does not require paired training data and is widely used for the conversion between different modalities of medical images. CycleGAN can perform modality transfer without paired images, but the quality and consistency of the generated images still need improvement. For example, the pix2pix model has been used for various image-to-image conversion tasks, including CT to MRI conversion. This method relies on paired training data and achieves high-quality image conversion through conditional generative adversarial networks.

[0049] While existing GAN-based methods have made some progress in medical image generation and translation, they still have some significant drawbacks in practical applications. First, existing methods, such as CycleGAN, still suffer from insufficient image quality and consistency when performing modality transformation without paired training data. The generated images may exhibit artifacts or missing details, affecting their practical clinical application. Second, methods like GAN models require a large amount of paired training data, but obtaining a sufficient number of paired MRI and fMRI datasets is very difficult in actual clinical practice. Insufficient data affects the model's generalization ability and the quality of the generated images. Third, methods like GAN models require a large amount of paired training data, but obtaining a sufficient number of paired MRI and fMRI datasets is very difficult in actual clinical practice. Insufficient data affects the model's generalization ability and the quality of the generated images.

[0050] The preferred embodiment of the fMRI generation method based on a generative adversarial network model of the present invention, as shown in Figure 1, includes the following steps:

[0051] Step S10: Collect paired MRI and fMRI data of multiple target acquisition objects, and establish a training dataset based on the paired MRI and fMRI data.

[0052] Specifically, paired MRI and fMRI data (MRI and fMRI data of the same patient, spatially aligned) are collected from multiple target subjects (e.g., Parkinson's disease patients). This paired MRI and fMRI data includes MRI images and actual fMRI images (i.e., MRI data and fMRI data). The paired MRI and fMRI data undergo preprocessing, including denoising, normalization, and registration operations, to ensure image quality and alignment. For example, 3Dslicer software is used to register the MRI and fMRI data to ensure the accuracy and consistency of the training data. The registration process involves aligning the MRI and fMRI images to ensure they have the same spatial resolution and geometry. A training dataset is then built based on the preprocessed paired MRI and fMRI data.

[0053] Step S20: Use the training dataset to train the generator and discriminator in the generative adversarial network model, optimize the network parameters of the generator and the discriminator, and obtain the trained generative adversarial network model.

[0054] Specifically, the generative adversarial network model includes a generator G and a discriminator D. The generator G is used to generate fMRI images based on MRI images. The discriminator D is used to distinguish between the fMRI images generated by the generator and real fMRI images. The generator G uses the ResNet architecture (residual network), which is known for its powerful performance in image generation tasks. ResNet effectively solves the gradient vanishing problem in deep networks through residual blocks, improving the quality of generated images. The generator G mainly learns the mapping between MRI and fMRI to capture multi-scale features. The discriminator D uses the CNN architecture (convolutional neural network), which is known for its excellent performance in image classification tasks. CNN can extract high-level features of images and accurately distinguish between generated fMRI and real fMRI, thereby improving the fine-grainedness of discrimination.

[0055] As shown in Figure 2, the process of training the generator and discriminator in the Generative Adversarial Network (GAN) model using the training dataset specifically includes:

[0056] MRI images and random Gaussian noise are input into the network structure of the generator G for training to generate fMRI images. The fMRI images generated by the generator G are then input together with real fMRI images into the network structure of the discriminator D. The discriminator D distinguishes between the generated fMRI images and the real fMRI images, outputting a true / false classification result. Based on the true / false classification result of the discriminator D, backpropagation is used to optimize the network parameters of the generator G and the discriminator D, so that the fMRI images generated by the generator G approximate the real fMRI images as closely as possible, and the discriminator D distinguishes between the real fMRI images and the generated fMRI images as accurately as possible. The entire training process is adversarial training.

[0057] The goal of the generator G is to minimize the difference between the generated fMRI image and the real fMRI image, making the generated fMRI image as close to the real fMRI image as possible. The goal of the discriminator is to maximize the accuracy of distinguishing between the generated fMRI image and the real fMRI image.

[0058] Furthermore, the generator and the discriminator are optimized using the loss function of the generative adversarial network model, so that the fMRI images generated by the generator are as similar as possible to the real fMRI data, while simultaneously enhancing the discrimination ability of the discriminator.

[0059] The loss function of the generative adversarial network model includes adversarial loss and generation loss. The adversarial loss optimizes the adversarial learning between the generator and the discriminator, enabling the generated fMRI images to gradually approximate the distribution of real data. The generation loss reduces the pixel differences between the generated fMRI images and real fMRI images, further improving the quality of the generated images. By combining adversarial loss and generation loss (i.e., L1 loss), the detail and consistency of the generated images are improved.

[0060] The loss function of the generative adversarial network model is:

[0061] in, This represents the loss function of the generative adversarial network model. Indicating resistance to loss, Indicates the generation loss;

[0062] The resistance loss for:

[0063] Where G represents the generator, D represents the discriminator, x represents the MRI image, y represents the real fMRI image, z represents random Gaussian noise, and D(x,y) represents the true / false classification result obtained by the discriminator between the MRI image and the real fMRI image. Let G(x,z) represent the expectation of logD(x,y), G(x,z) represent the result obtained by the generator after the MRI image and random Gaussian noise are fed into it, and D(x,G(x,z)) represent the result obtained by the discriminator after the MRI image and the fMRI image generated by the generator are passed through it. This represents the expectation of log(1-D(x,G(x,z))).

[0064] The generation loss for:

[0065] Where λ represents a given parameter, This represents the expectation of ||yG(x,z)||1.

[0066] Step S30: Obtain the MRI image of the target object to be acquired. Input the MRI image of the target object to be acquired into the trained generative adversarial network model to directly generate the fMRI image of the target object to be acquired.

[0067] Specifically, after training the generator and discriminator in the generative adversarial network (GAN) model using the aforementioned training dataset, a well-trained GAN model (which has learned the mapping relationship between MRI and fMRI images) can be obtained. Then, for a new target object (e.g., a new Parkinson's patient), the MRI image of the target object can be directly input into the well-trained GAN model. The well-trained GAN model can then directly generate a high-resolution fMRI image (high fidelity and realism) of the target object based on the MRI image. This allows for the simultaneous acquisition of both MRI and fMRI images for the target object, compensating for the missing fMRI data of patients (e.g., Parkinson's patients) and providing comprehensive multimodal data support. This further provides more evidence (information) to improve the accuracy of diagnosis and treatment, such as generating high-resolution functional MRI images for Parkinson's patients, thereby supplementing and enhancing the original fMRI data.

[0068] The beneficial effects of this invention are:

[0069] (1) fMRI images generated by GAN models have higher resolution and clarity, and can more accurately reflect the details of brain functional activities, which helps to provide more reliable evidence for improving the diagnostic accuracy of Parkinson's disease.

[0070] (2) The method of the present invention reduces reliance on expensive and time-consuming fMRI data acquisition, thereby reducing the complexity and cost of clinical procedures. By generating high-quality functional MRI images, each patient can obtain complete multimodal data.

[0071] (3) High-quality functional MRI images provide clinicians with more valuable information, helping to diagnose Parkinson's disease more accurately and develop more effective treatment plans. This not only improves the accuracy of diagnosis but also allows for better monitoring of disease progression and treatment effectiveness.

[0072] (4) The method of the present invention can be widely applied to different clinical scenarios, not limited to the diagnosis and research of Parkinson's disease, but can also be extended to the research of other neurodegenerative diseases, thereby improving the application value of multimodal data in the medical field.

[0073] In summary, this invention effectively solves the problems of difficult fMRI data acquisition and low image resolution by utilizing GAN models to generate high-quality functional MRI images, providing strong support for the diagnosis and treatment of Parkinson's disease. This innovative method not only improves diagnostic accuracy but also reduces the complexity and cost of clinical procedures, demonstrating broad application prospects and significant clinical value.

[0074] This invention alleviates the problem of insufficient paired data through data augmentation techniques and transfer learning. Simultaneously, it explores semi-supervised learning methods to further reduce reliance on paired data. During training, this invention employs various techniques, such as spectral normalization and experience replay, to improve training stability and reduce the occurrence of mode collapse and gradient vanishing.

[0075] Furthermore, as shown in Figure 3, based on the above-mentioned fMRI generation method based on a generative adversarial network (GAN) model, this invention also provides an fMRI generation system based on a GAN model, wherein the fMRI generation system based on a GAN model includes:

[0076] Data acquisition module 51 is used to collect paired MRI and fMRI data of multiple target acquisition objects and to build a training dataset based on the paired MRI and fMRI data;

[0077] The model training module 52 is used to train the generator and discriminator in the generative adversarial network model using the training dataset, optimize the network parameters of the generator and the discriminator, and obtain a trained generative adversarial network model.

[0078] The image generation module 53 is used to acquire the MRI image of the target object to be acquired, input the MRI image of the target object to be acquired into the trained generative adversarial network model, and directly generate the fMRI image of the target object to be acquired.

[0079] Furthermore, as shown in Figure 4, based on the above-described fMRI generation method and system based on a generative adversarial network model, the present invention also provides a terminal, which includes a processor 10, a memory 20, and a display 30. Figure 4 only shows some components of the terminal; however, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0080] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal. Further, the memory 20 may include both internal and external storage units of the terminal. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores an fMRI generation program 40 based on a generative adversarial network (GAN) model, which can be executed by the processor 10 to implement the fMRI generation method based on a GAN model in this application.

[0081] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the fMRI generation method based on the generative adversarial network model.

[0082] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The components 10-30 of the terminal communicate with each other via a system bus.

[0083] In one embodiment, when the processor 10 executes the fMRI generation program 40 based on the generative adversarial network model in the memory 20, the following steps are performed:

[0084] Collect paired MRI and fMRI data of multiple target acquisition objects, and build a training dataset based on the paired MRI and fMRI data;

[0085] The generator and discriminator in the generative adversarial network model are trained using the training dataset, and the network parameters of the generator and the discriminator are optimized to obtain a trained generative adversarial network model.

[0086] The MRI image of the target object is acquired, and then the MRI image of the target object is input into the trained generative adversarial network model to directly generate the fMRI image of the target object.

[0087] The process of collecting paired MRI and fMRI data from multiple target acquisition objects and establishing a training dataset based on the paired MRI and fMRI data specifically includes:

[0088] Collect paired MRI and fMRI data from multiple target acquisition objects, wherein the paired MRI and fMRI data includes MRI images and real fMRI images;

[0089] The paired MRI and fMRI data are preprocessed, including denoising, standardization, and registration.

[0090] A training dataset was created based on preprocessed paired MRI and fMRI data.

[0091] The generative adversarial network model includes a generator and a discriminator;

[0092] The generator is used to generate fMRI images based on MRI images;

[0093] The discriminator is used to determine the difference between the fMRI image generated by the generator and the real fMRI image;

[0094] The generator uses the ResNet architecture to capture multi-scale features;

[0095] The discriminator uses a CNN architecture to improve the fine-grainedness of discrimination.

[0096] Specifically, the step of training the generator and discriminator in the generative adversarial network model using the training dataset, optimizing the network parameters of the generator and the discriminator, and obtaining the trained generative adversarial network model includes:

[0097] MRI images and random Gaussian noise are input into the network structure of the generator for training to generate fMRI images;

[0098] The fMRI image generated by the generator is input into the network structure of the discriminator along with the real fMRI image;

[0099] The discriminator distinguishes between generated fMRI images and real fMRI images, and outputs a true / false classification result.

[0100] Based on the true / false classification results of the discriminator, backpropagation optimizes the network parameters of the generator and the discriminator, so that the fMRI image generated by the generator is as close as possible to the real fMRI image, and the discriminator can distinguish between the real fMRI image and the generated fMRI image as accurately as possible.

[0101] The fMRI generation method based on the generative adversarial network model further includes:

[0102] The generator and the discriminator are optimized by using the loss function of the generative adversarial network model, so that the fMRI images generated by the generator are as similar as possible to the real fMRI data, while at the same time enhancing the discrimination ability of the discriminator.

[0103] The loss function of the generative adversarial network model includes adversarial loss and generative loss;

[0104] The adversarial loss is used to optimize the adversarial learning between the generator and the discriminator, so that the fMRI images generated by the generator gradually approximate the distribution of the real data.

[0105] The generation loss is used to reduce the pixel difference between the generated fMRI image and the real fMRI image, thereby improving the quality of the generated image.

[0106] The loss function of the generative adversarial network model is:

[0107] in, This represents the loss function of the generative adversarial network model. Indicating resistance to loss, Indicates the generation loss;

[0108] The resistance loss for:

[0109] Where G represents the generator, D represents the discriminator, x represents the MRI image, y represents the real fMRI image, z represents random Gaussian noise, and D(x,y) represents the true / false classification result obtained by the discriminator between the MRI image and the real fMRI image. Let G(x,z) represent the expectation of logD(x,y), G(x,z) represent the result obtained by the generator after the MRI image and random Gaussian noise are fed into it, and D(x,G(x,z)) represent the result obtained by the discriminator after the MRI image and the fMRI image generated by the generator are passed through it. This represents the expectation of log(1-D(x,G(x,z))).

[0110] The generation loss for:

[0111] Where λ represents a given parameter, This represents the expectation of ||yG(x,z)||1.

[0112] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores an fMRI generation program based on a generative adversarial network model, and the fMRI generation program based on the generative adversarial network model, when executed by a processor, implements the steps of the fMRI generation method based on the generative adversarial network model as described above.

[0113] In summary, this invention provides an fMRI generation method, system, terminal, and computer-readable storage medium based on a generative adversarial network (GAN) model. The method includes: collecting paired MRI and fMRI data from multiple target subjects; establishing a training dataset based on the paired MRI and fMRI data; training the generator and discriminator in the GAN model using the training dataset; optimizing the network parameters of the generator and discriminator to obtain a trained GAN model; acquiring MRI images of the target subjects; inputting the MRI images of the target subjects into the trained GAN model to directly generate fMRI images of the target subjects. This invention utilizes the MRI data of the target subjects to generate corresponding fMRI data. The MRI data of each target subject can be converted into fMRI data, thus providing each target subject with both MRI and fMRI data. This not only provides accurate and reliable information for downstream tasks but also maximizes the use of existing single-modal data, avoiding data waste, reducing reliance on fMRI data acquisition, and lowering the complexity and cost of clinical procedures.

[0114] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal that includes that element.

[0115] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The computer-readable storage medium can be a memory, magnetic disk, optical disk, etc.

[0116] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. An fMRI generation method based on a generative adversarial network model, characterized in that, The fMRI generation method based on the generative adversarial network model comprises: Collecting MRI and fMRI paired data of a plurality of target acquisition objects, and establishing a training data set according to the MRI and fMRI paired data; Training a generator and a discriminator in the generative adversarial network model using the training data set, optimizing network parameters of the generator and the discriminator, and obtaining a trained generative adversarial network model; Obtaining an MRI image of a target object to be acquired, inputting the MRI image of the target object to be acquired into the trained generative adversarial network model, and directly generating an fMRI image of the target object to be acquired. 2.The fMRI generation method based on a generative adversarial network model according to claim 1, wherein, The collecting of the MRI and fMRI paired data of the plurality of target acquisition objects and the establishing of the training data set according to the MRI and fMRI paired data specifically comprise: Collecting MRI and fMRI paired data of a plurality of target acquisition objects, wherein the MRI and fMRI paired data comprises an MRI image and a real fMRI image; Preprocessing the MRI and fMRI paired data, wherein the preprocessing comprises denoising, standardization and registration; Establishing a training data set according to the preprocessed MRI and fMRI paired data. 3.The fMRI generation method based on a generative adversarial network model according to claim 2, characterized in that, The generative adversarial network model comprises a generator and a discriminator; The generator is used to generate an fMRI image according to an MRI image; The discriminator is used to distinguish the difference between the fMRI image generated by the generator and a real fMRI image; The generator uses a ResNet architecture to capture multi-scale features; The discriminator uses a CNN architecture to improve the granularity of the discrimination. 4.The fMRI generation method based on a generative adversarial network model according to claim 3, characterized in that, The training of the generator and the discriminator in the generative adversarial network model using the training data set, the optimization of the network parameters of the generator and the discriminator, and the obtaining of the trained generative adversarial network model specifically comprise: Inputting an MRI image and random Gaussian noise into a network structure of the generator for training to generate an fMRI image; Inputting the fMRI image generated by the generator and a real fMRI image into a network structure of the discriminator; The discriminator distinguishes between the generated fMRI image and the real fMRI image, and outputs a true or false classification result; According to the true or false classification result of the discriminator, the network parameters of the generator and the discriminator are optimized through back propagation, so that the fMRI image generated by the generator approximates the real fMRI image as much as possible, and the discriminator accurately distinguishes between the real fMRI image and the generated fMRI image as much as possible.

5. The fMRI generation method based on a generative adversarial network model according to claim 4, characterized in that, The fMRI generation method based on the generative adversarial network model further comprises: Optimizing the generator and the discriminator through a loss function of the generative adversarial network model, so that the fMRI image generated by the generator is as similar as possible to the real fMRI data, and the discrimination ability of the discriminator is enhanced.

6. The fMRI generation method based on a generative adversarial network model according to claim 5, characterized in that, The loss function of the generative adversarial network model comprises an adversarial loss and a generation loss; The adversarial loss is used to optimize the adversarial learning between the generator and the discriminator, so that the fMRI image generated by the generator gradually approximates the distribution of the real data. The generation loss is used to reduce pixel differences between the generated fMRI image and the real fMRI image, so as to improve the quality of the generated image.

7. The fMRI generation method based on a generative adversarial network model according to claim 6, characterized in that, The loss function of the generative adversarial network model is: wherein a loss function representing a generative adversarial network model, denotes the adversarial loss, represents the generation loss; the adversarial loss For: wherein G represents a generator, D represents a discriminator, x represents an MRI image, y represents a real fMRI image, z represents random Gaussian noise, and D(x, y) represents a true or false classification result of the MRI image and the real fMRI image through the discriminator, represents the expectation of logD(x, y), G(x, z) represents the result obtained by inputting the MRI image and random Gaussian noise into the generator, and d(x, G(x, z)) represents the result obtained by inputting the MRI image and the fMRI image generated by the generator into the discriminator Results, represents the expectation of log(1-D(x, G(x, z))), the generation loss For: where λ represents a given parameter, represents the expectation of ||y-G(x, z)||1.

8. An fMRI generation system based on a generative adversarial network model, characterized by, The fMRI generation system based on the generative adversarial network model comprises: a data acquisition module configured to collect MRI and fMRI paired data of a plurality of target acquisition objects, and establish a training data set according to the MRI and fMRI paired data; a model training module configured to train a generator and a discriminator in the generative adversarial network model using the training data set, optimize network parameters of the generator and the discriminator, and obtain a trained generative adversarial network model; an image generation module configured to acquire an MRI image of a target object to be acquired, input the MRI image of the target object to be acquired into the trained generative adversarial network model, and directly generate an fMRI image of the target object to be acquired.

9. A terminal, characterized by comprising: The terminal comprises a memory, a processor, and an fMRI generation program based on a generative adversarial network model stored on the memory and executable on the processor, and the fMRI generation program based on the generative adversarial network model, when executed by the processor, implements the steps of the fMRI generation method based on the generative adversarial network model according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores an fMRI generation program based on a generative adversarial network model, and the fMRI generation program based on the generative adversarial network model, when executed by the processor, implements the steps of the fMRI generation method based on the generative adversarial network model according to any one of claims 1-7.

Images