Method for partial volume correction of pet images based on conditional deep residual compensation

Abstract

The application discloses a PET image partial volume correction method based on conditional deep residual compensation, which predicts blur kernel prior through a conditional neural blind deconvolution network, and combines a conditional deep residual compensation network to perform partial volume correction (PVC) on the partial volume effect (PVE) of a PET image. The method uses an anatomical MR prior image of a patient and a randomly generated Gaussian blur kernel as inputs of the conditional neural blind deconvolution network to estimate the blur kernel, and compensates for errors caused by inaccurate blur kernel estimation through the conditional deep residual compensation network. The application fully utilizes the potential complementary information of multi-modal data, considers the influence of inaccurate blur kernel prediction on the PVC result, and thus improves the effectiveness and robustness of neural network PVC. The method significantly improves the accuracy of quantitative analysis of PET images, especially the accurate analysis of brain PET images.

Description

Technical Field

[0001] The present invention belongs to the field of deep learning image processing, and in particular relates to a PET image partial volume correction method based on conditional depth residual compensation. Background Art

[0002] Positron emission tomography (PET) is an important molecular imaging technology widely used in clinical diagnosis and scientific research. It plays a vital role in medical diagnosis, especially in the early diagnosis of cancer.

[0003] However, due to the low spatial resolution of PET scanners, the partial volume effect (PVE) often occurs, whereby the radioactive uptake of specific voxels is affected by surrounding tissue, thereby reducing the accuracy and resolution of PET images. This effect not only affects the early diagnosis of diseases but also poses a serious challenge to the quantitative analysis of PET images. Although deep learning has made significant progress in PET image partial volume correction (PVC), most methods rely solely on large amounts of PET image data for training, fail to fully utilize additional anatomical information, and fail to consider the impact of inaccurate blur kernel estimation on PVC results. With the widespread use of PET / MR scanners, it has become easier to simultaneously acquire high-precision MR and PET images of patients, providing valuable anatomical information for PVC analysis of PET images. Therefore, effectively combining the complementary information between multimodal data to achieve PET image partial volume correction through software technology methods, thereby improving PET image quality and the accuracy of quantitative analysis, is an urgent problem in this field. Summary of the Invention

[0004] The purpose of the present invention is to address the problems existing in the prior art and provide a PET image partial volume correction method based on conditional depth residual compensation, which fully utilizes the potential complementary information of multimodal data and compensates for the errors caused by inaccurate blur kernel estimation, thereby significantly improving the quality of PVC-PET images.

[0005] According to a first aspect of an embodiment of the present application, a method for partial volume correction of a PET image based on conditional depth residual compensation is provided, comprising:

[0006] (1) Obtain PVE-PET images and corresponding anatomical MR images of the patient;

[0007] (2) Register the PVE-PET image and the anatomical MR image, and pre-process the registered anatomical MR image to obtain a registered PVE-PET image and an anatomical MR brain tissue image;

[0008] (3) Pre-train the PVC-PET image generation network and the blur kernel generation network respectively by using the registered PVE-PET image and the randomly generated Gaussian blur kernel, so as to initialize the initial weight parameters of the PVC-PET image generation network and the blur kernel generation network;

[0009] (4) Construct a conditional neural blind deconvolution network based on the pre-trained PVC-PET image generation network and the blur kernel generation network, input the randomly generated Gaussian blur kernel and the anatomical MR brain tissue image into the conditional neural blind deconvolution network, use the registered PVE-PET image as a training label, and train the conditional neural blind deconvolution network;

[0010] (5) Take the anatomical MR brain tissue image as an input of the conditional deep residual compensation network, combine the blur kernel prior estimated by the conditional neural blind deconvolution network, use the registered PVE-PET image as a training label, train the conditional deep residual compensation network, and obtain a PVC-PET image, so as to realize partial volume correction.

[0011] Further, in step (2), the registered anatomical MR image is pre-processed, specifically:

[0012] The skull part is removed from the registered anatomical MR image, and the brain tissue part is extracted to obtain an anatomical MR brain tissue image.

[0013] Further, step (3) includes:

[0014] (3.1) using a depth image prior network as the PVC-PET image generation network G x , and using a fully connected layer network as the blur kernel generation network G k ;

[0015] (3.2) pre-train the PVC-PET image generation network and the blur kernel generation network respectively by using the registered PVE-PET image and the randomly generated Gaussian blur kernel, wherein the loss functions of the PVC-PET image generation network and the blur kernel generation network are respectively defined as:

[0016]

[0017] wherein and are the loss functions of the PVC-PET image generation network and the blur kernel generation network respectively, y petand z k are the registered PVE-PET images and randomly generated Gaussian blur kernels, respectively.

[0018] Furthermore, in step (4), the conditional neural blind deconvolution network includes a parallel PVC-PET image generation network and a blur kernel generation network, wherein the PVC-PET image generation network is used to preliminarily predict the PVC-PET image based on the anatomical MR image, and the blur kernel generation network is used to estimate the blur kernel prior based on a randomly generated Gaussian blur kernel.

[0019] Furthermore, in step (4), the optimization process during training of the conditional neural blind deconvolution network is:

[0020]

[0021] in is the loss function of the conditional neural blind deconvolution network, z a For anatomical MR brain tissue images, y pet and z k are the registered PVE-PET images and the randomly generated Gaussian blur kernel, G x ,G k They are PVC-PET image generation network and blur kernel generation network respectively.

[0022] Furthermore, in step (5), the conditional depth residual compensation network includes a parallel PVC-PET image generation network and a depth residual generation network, wherein the depth residual generation network is used to obtain a depth residual map based on the anatomical MR brain tissue image, and the PVC-PET image generation network is used to combine the depth residual map and the blur kernel prior to generate a PVC-PET image based on the anatomical MR brain tissue image.

[0023] Furthermore, in step (5), the loss function during the training of the conditional depth residual compensation network is for:

[0024]

[0025] in and The loss functions are The fidelity term and regularization term in G x ,G r They are PVC-PET image generation network and deep residual generation network respectively. represents the blur kernel prior, z aFor anatomical MR brain tissue images, v and C represent the coefficient vector and DCT operator obtained after DCT transformation of the artifacts introduced by the blur kernel error, respectively. λ1, λ2, and λ3 are hyperparameters that control the weights of each item.

[0026] According to a second aspect of an embodiment of the present application, a computer program product is provided. When the computer program / instructions are executed by a processor, the method described in the first aspect is implemented.

[0027] According to a third aspect of the embodiments of the present application, there is provided an electronic device, including:

[0028] one or more processors;

[0029] a memory for storing one or more programs;

[0030] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in the first aspect.

[0031] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0032] The technical solutions provided by the embodiments of the present application may have the following beneficial effects:

[0033] It can be seen from the above embodiments that the partial volume correction method of PET images based on conditional depth residual compensation of the present application can effectively combine the potential complementary information in multimodal data and effectively compensate for the errors caused by inaccurate blur kernel prediction. The present method realizes the prediction of blur kernel prior through conditional neural blind deconvolution (CNBD) network, and compensates for the errors caused by inaccurate blur kernel prediction using conditional depth residual compensation (CDRC) network, thereby overcoming the dependence of most previous PVC methods on single modality data and the influence of inaccurate blur kernel estimation on PET image PVC results. In addition, the present method significantly improves the effectiveness and robustness of neural network PVC, especially when dealing with complex pathological changes and subtle structures, significantly improving the ability to restore PET image details and the accuracy of quantitative analysis.

[0034] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0036] Figure 1The present invention is a flow chart of a method for partial volume correction of PET images based on conditional depth residual compensation.

[0037] Figure 2 It is a schematic diagram of a model of the present invention.

[0038] Figure 3 are PET images affected by PVE, where (a) is a simulated PET image affected by PVE, and (b) is a real clinical PET image affected by PVE.

[0039] Figure 4 The output images of this method and the existing method on the simulated data set are shown, where (a) is the preliminary PVC-PET image obtained using only the CNBD network, (b) is the final PVC-PET image obtained using this method, (c) is the PVC-PET image obtained by processing using the existing method IY, and (d) is the PVC-PET image obtained by processing using the existing method RVC.

[0040] Figure 5 The output images of this method and the existing method on the real data set are shown, where (a) is the preliminary PVC-PET image obtained using only the CNBD network, (b) is the final PVC-PET image obtained using this method, (c) is the PVC-PET image obtained by processing using the existing method IY, and (d) is the PVC-PET image obtained by processing using the existing method RVC.

[0041] Figure 6 It is a block diagram of a PET image partial volume correction device based on conditional depth residual compensation of the present invention.

[0042] Figure 7 It is a schematic diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0043] Exemplary embodiments are described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different drawings represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with this application.

[0044] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0045] like Figure 1 As shown, the present invention is a PET image partial volume correction method based on conditional depth residual compensation, comprising the following steps:

[0046] (1) Obtain PVE-PET images and corresponding anatomical MR images of the patient;

[0047] Specifically, the PVE-PET image is a PET image affected by the partial volume effect.

[0048] (2) registering the PVE-PET image and the anatomical MR image, and preprocessing the registered anatomical MR image to obtain a registered PVE-PET image and an anatomical MR brain tissue image;

[0049] Specifically, the ANTs registration tool was used to register the PVE-PET images with the anatomical MR images, and ultimately both were registered to the MNI152 standard space to ensure accurate spatial alignment of the multimodal images. Simultaneously, the FSL BET tool was used to remove the skull from the anatomical MR images and extract the brain tissue to obtain the anatomical MR brain tissue images.

[0050] (3) using the registered PVE-PET images and the randomly generated Gaussian blur kernels, pre-training the PVC-PET image generation network and the blur kernel generation network, respectively, thereby initializing the initial weight parameters of the PVC-PET image generation network and the blur kernel generation network;

[0051] Specifically, this step may include the following sub-steps:

[0052] (3.1) Using the Deep Image Prior (DIP) network as the PET image generation network G x , using the fully connected network (FCN) as the fuzzy kernel generation network G k ;

[0053] Input the PVE-PET image into the network G x , we can get a PET image with potential internal information of the PVE-PET image. The randomly generated Gaussian blur kernel is input into the network G k , a roughly fitted Gaussian blur kernel can be obtained.

[0054] (3.2) Using the registered PVE-PET images and randomly generated Gaussian blur kernels, we can respectively x and G k Perform pre-training, where G x and G kThe loss function is set to mean square error (MSE) loss function, and each network is pre-trained separately by optimizing the loss function. x and G k The loss functions are defined as:

[0055]

[0056] in and G x and G k The loss function, y pet and z k are the registered PVE-PET images and randomly generated Gaussian blur kernels, respectively.

[0057] This pre-training method uses registered PVE-PET images and randomly generated Gaussian blur kernels as inputs to the DIP network and FCN, respectively, to autonomously optimize network parameters. In an unsupervised environment, the network trains itself by calculating the loss function between the input data and the network output data, without the need for additional labeled data. This pre-training method provides network initialization weight parameters with information related to PVE-PET images and random Gaussian blur kernels for subsequent CNBD network training, significantly improving the accuracy of the CNBD network in blur kernel prediction and preliminary PVC-PET image estimation. At the same time, it enhances the generalization ability of the neural network and reduces the unnecessary effects of random initialization parameters, enabling it to effectively adapt to the individual differences of different patients, thereby improving the fitting effect of subsequent neural network training.

[0058] (4) constructing a conditional neural blind deconvolution (CNBD) network based on the pre-trained PVC-PET image generation network and the blur kernel generation network, inputting the randomly generated Gaussian blur kernel and the anatomical MR brain tissue image into the conditional neural blind deconvolution network, and using the registered PVC-PET image as the training label to train the conditional neural blind deconvolution network;

[0059] Specifically, the conditional neural blind deconvolution (CNBD) network is used to perform blur kernel prior prediction and preliminary PVC-PET image estimation, and the pre-trained PVC-PET image generation network G x and the fuzzy kernel generation network G k The anatomical MR brain tissue image is input into the network G x Predict preliminary PVC-PET images and use randomly generated Gaussian blur kernels to input the network G k, which is used to estimate the blur kernel prior. The two work together through a joint optimization framework to gradually refine the preliminary PVC-PET image and the blur kernel prior estimation results. The objective function is set to the mean square error (MSE) loss function. The optimization process of the entire neural blind deconvolution network is:

[0060]

[0061] in is the loss function of the conditional neural blind deconvolution network, z a This is an anatomical MR image of brain tissue.

[0062] (5) The anatomical MR brain tissue image is used as the input of the conditional deep residual compensation (CDRC) network, and the blur kernel prior estimated by the CNBD network is combined with the registered PVE-PET image as the training label to train the conditional deep residual compensation network, thereby obtaining the PVC-PET image and realizing partial volume correction;

[0063] Specifically, the PVC-PET image generation network G x and deep residual generation network G r Combined with the Conditional Deep Residual Compensation (CDRC) network, the generated network G x and G r Both use anatomical MR brain tissue images as input, G r The output depth residual image effectively compensates for the PVC error caused by the inaccurate prior estimation of the blur kernel, significantly improving the fitting ability of the CDRC network to the PVE-PET image, thereby promoting the generation of the network G x Output the final high-quality PVC-PET image. Similarly, for the generation network G x and G r A joint optimization framework works together to gradually refine the depth residual compensation image and high-quality PVC-PET image. The CDRC network can be constrained and optimized through the mean square error (MSE) loss function, total variation (TV) regularization, and sparsity regularization, improving the ability to restore PVC-PET image details.

[0064] First, define the loss function and use the mean square error (MSE) loss function as the loss function of the fidelity term in the CDRC network loss function. Therefore, the fidelity term in the loss function is defined as:

[0065]

[0066] in represents the blur kernel prior; v and C represent the coefficient vector and DCT operator obtained by discrete cosine transform of the artifact introduced by the blur kernel error Δk, respectively. The blur kernel error Δk is the error between the estimated blur kernel prior and the actual blur kernel of the PVE-PET image.

[0067] Total variation (TV) regularization is applied to the generative network G x , sparsity regularization is applied to the generative network G r And the coefficient vector v obtained by DCT transformation, the regularization term in the CDRC network loss function is defined as:

[0068]

[0069] Where λ1, λ2, and λ3 are hyperparameters that control the weights of each regularization loss term, ||·|| TV and ||·||1 denote total variation regularization and sparsity regularization, respectively.

[0070] The total loss of the Conditional Deep Residual Compensation (CDRC) network is and The sum of the two:

[0071]

[0072] For the above CDRC network total loss function Optimization uses the alternating minimization optimization algorithm to decompose it into two sub-problems for iterative solution. The specific process is as follows:

[0073] 1. Fixed parameter v, generating network G x and G r The network parameters θ and ζ in are optimized and updated:

[0074]

[0075] Here, the superscript i represents the number of iterations.

[0076] 2. Fix the parameters θ and ζ and optimize v:

[0077]

[0078] Use the approximate gradient descent method to optimize and update v in each iteration process. The specific form is:

[0079]

[0080] in, represents the soft threshold operator, and L is the scaling factor used to control the degree of sparsity.

[0081] a total loss function of the CDRC network and an alternating minimization optimization algorithm, the CDRC network is trained by using an unsupervised learning method, and the training is stopped when a set of training epochs is reached or a high-quality PVC-PET image can be output, and whether a high-quality PVC-PET image is obtained can be judged by using related indexes such as PSNR, SSIM, and RMSE.

[0082] In this step, a conditional depth residual compensation (CDRC) network is introduced to compensate for the PVC error caused by the inaccurate estimation of the blur kernel of the CNBD network. The network combines a deep image prior (DIP) network and a deep residual prior (DRP) network, and uses total variation (TV) regularization and sparsity regularization to further constrain the optimization process of the neural network. By combining these prior information, the CDRC network can effectively improve the PVC performance of the neural network and obtain a high-quality PVC-PET image.

[0083] With the continuous progress of deep learning technology, the PVC technology of PET images gradually adopts an unsupervised learning method based on a deep learning network. Most PVC methods usually rely on single modality data and fail to fully exploit the potential of the complementary action of multi-modal data. In addition, the low resolution and noise problem of PET images poses a challenge to clinical quantitative analysis and diagnosis. The present method uses an unsupervised learning framework, avoids the dependence on a large amount of labeled data, and uses the anatomical MR brain tissue image of the patient as prior information to more effectively recover the subtle structures in the PET image through the potential complementary information between multi-modal data.

[0084] In the present application, the registered PVE-PET image and the randomly generated Gaussian blur kernel are used to pre-train the network weight parameters of the deep image prior (DIP) of the PVC-PET generation network and the fully connected layer network (FCN) of the blur kernel prior generation network, respectively. Subsequently, the network weight parameters with robustness and stability provided in the pre-training stage are used as the initialization weight parameters of the conditional neural blind deconvolution (CNBD) network, and the anatomical MR brain tissue image and the randomly generated Gaussian blur kernel are input into the DIP network and the FCN of the CNBD network, respectively, to generate the preliminary PVC-PET image and predict the blur kernel prior. Finally, the conditional depth residual compensation (CDRC) network is introduced to compensate for the PVC error caused by the inaccurate blur kernel prior generated by the CNBD network training, and the anatomical MR brain tissue image is used as the input of the deep residual prior (DRP) and the DIP network in the CDRC network. The residual image generated by the DRP network compensates for the inaccurate blur kernel error, so that the DIP network generates a final high-quality PVC-PET image.

[0085] Example

[0086] The embodiments of the present invention were implemented using Python 3.8 and PyTorch 2.3.1 on an NVIDIA 4090 graphics card. Simulation experiments were conducted using a simulated BrainWeb dataset, and experiments were conducted using real clinical data using an open-access dataset provided by OpenNeuro. Both simulated and real clinical data were ultimately registered to the standard MNI-152 space, with image dimensions of 109 × 91 × 91.

[0087] like Figure 3 、 Figure 4 As shown, compared with the CNBD method, the IY method (Kjell Erlandsson, Irene Buvat, PHendrik Pretorius, Benjamin A Thomas, and Brian F Hutton, “A review of partial volume correction techniques for emission tomography and their applications in neurology, cardiology and oncology,” Physics in Medicine & Biology, vol. 57, no. 21, pp. R119, 2012.) and the RVC method (Jussi Tohka and Anthonin Reilhac, “Deconvolution-based partial volume correction in raclopride-pet and montecarlo comparison to mr-based method,” Neuroimage, vol. 39, no. 4, pp. 1570–1584, 2008.), the present method can obtain more reliable PVC-PET images on simulated data, while more effectively preserving the local details of the PET images and more clearly displaying the brain structure areas. Similarly, as Figure 5 As shown in Figure 3, this method also obtains more accurate and reliable PVC-PET images on real clinical datasets.

[0088] Corresponding to the aforementioned embodiment of the method for partial volume correction of PET images based on conditional depth residual compensation, the present application also provides an embodiment of a network framework model device for partial volume correction of PET images based on conditional depth residual compensation.

[0089] Figure 2is a device block diagram of a PET image partial volume correction network framework model based on conditional deep residual compensation according to an exemplary embodiment. Referring to Figure 2 The device can include: an FCN and DIP network pre-training model, a conditional neural blind deconvolution model, a conditional deep residual compensation model, and finally generate a high-quality PVC-PET image.

[0090] An image acquisition module 21 is configured to acquire a PVE-PET image and a corresponding anatomical MR image of a patient.

[0091] A registration and preprocessing module 22 is configured to register the PVE-PET image and the anatomical MR image, and pre-process the registered anatomical MR image to obtain a registered PVE-PET image and an anatomical MR brain tissue image.

[0092] A pre-training module 23 is configured to pre-train a PVC-PET image generation network and a blur kernel generation network using the PVE-PET image processed by the registration and preprocessing module and a randomly generated Gaussian blur kernel, and initialize initial weight parameters of the PVC-PET image generation network and the blur kernel generation network.

[0093] A CNBD network training module 24 is configured to construct a conditional neural blind deconvolution network based on the pre-trained PVC-PET image generation network and the blur kernel generation network, input the randomly generated Gaussian blur kernel and the anatomical MR image processed by the registration and preprocessing module into the conditional neural blind deconvolution network, use the registered PVE-PET image as a training label, and train the conditional neural blind deconvolution network.

[0094] A CDRC network training module 25 is configured to use the anatomical MR image processed by the registration and preprocessing module as an input of a conditional deep residual compensation network, combine a blur kernel prior estimated by the conditional neural blind deconvolution network, use the registered PVE-PET image as a training label, train the conditional deep residual compensation network, and obtain a PVC-PET image to realize partial volume correction.

[0095] As to the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment related to the method, and will not be described in detail here.

[0096] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0097] Accordingly, the present application also provides a computer program product, comprising a computer program / instruction, which implements the method described in the first aspect when executed by a processor.

[0098] Accordingly, the present application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned method for partial volume correction of PET images based on conditional depth residual compensation. Figure 7 As shown in the figure, a hardware structure diagram of a deep learning dataset access system provided by an embodiment of the present invention is provided for any device with data processing capabilities, except Figure 7 In addition to the processor, memory, and network interface shown, any device with data processing capabilities in which the apparatus in the embodiment is located may also include other hardware, generally based on the actual functions of the device with data processing capabilities, which will not be described in detail.

[0099] Accordingly, the present application also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the above-mentioned method for partial volume correction of PET images based on conditional depth residual compensation. The computer-readable storage medium can be an internal storage unit of any device with data processing capabilities described in any of the aforementioned embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, a smart media card (SMC), an SD card, a flash card, etc. equipped on the device. Furthermore, the computer-readable storage medium can also include both an internal storage unit and an external storage device of any device with data processing capabilities. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capabilities, and can also be used to temporarily store data that has been output or is to be output.

[0100] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the contents disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed in this application.

Claims

1. A PET image partial volume correction method based on conditional depth residual compensation, characterized in that: include: (1) Obtain PVE-PET images and corresponding anatomical MR images of the patient; (2) registering the PVE-PET image and the anatomical MR image, and preprocessing the registered anatomical MR image to obtain a registered PVE-PET image and an anatomical MR brain tissue image; (3) using the registered PVE-PET images and the randomly generated Gaussian blur kernels, pre-training the PVC-PET image generation network and the blur kernel generation network, respectively, thereby initializing the initial weight parameters of the PVC-PET image generation network and the blur kernel generation network; (4) constructing a conditional neural blind deconvolution network based on the pre-trained PVC-PET image generation network and the blur kernel generation network, inputting the randomly generated Gaussian blur kernel and the anatomical MR brain tissue image into the conditional neural blind deconvolution network, and using the registered PVC-PET image as a training label to train the conditional neural blind deconvolution network; (5) The anatomical MR brain tissue image is used as the input of the conditional deep residual compensation network, and combined with the blur kernel prior estimated by the conditional neural blind deconvolution network, the registered PVE-PET image is used as the training label to train the conditional deep residual compensation network, thereby obtaining the PVC-PET image and realizing partial volume correction.

2. The method according to claim 1, characterized in that In step (2), the registered anatomical MR image is preprocessed, specifically: The skull part is removed from the registered anatomical MR image, and the brain tissue part is extracted to obtain the anatomical MR brain tissue image.

3. The method according to claim 1, characterized in that Step (3) includes: (3.1) Using the deep image prior network as the PVC-PET image generation network G x , using the fully connected layer network as the fuzzy kernel generation network G k ; (3.2) Using the registered PVE-PET images and the randomly generated Gaussian blur kernels, the PVC-PET image generation network and the blur kernel generation network are pre-trained, respectively, wherein the loss functions of the PVC-PET image generation network and the blur kernel generation network are defined as: in and are the loss functions of the PVC-PET image generation network and the blur kernel generation network, y pet and z k are the registered PVE-PET images and randomly generated Gaussian blur kernels, respectively.

4. The method according to claim 1, wherein In step (4), the conditional neural blind deconvolution network includes a parallel PVC-PET image generation network and a blur kernel generation network, wherein the PVC-PET image generation network is used to preliminarily predict the PVC-PET image based on the anatomical MR image, and the blur kernel generation network is used to estimate the blur kernel prior based on a randomly generated Gaussian blur kernel.

5. The method according to claim 4, characterized in that In step (4), the optimization process during the training of the conditional neural blind deconvolution network is: in is the loss function of the conditional neural blind deconvolution network, z a For anatomical MR brain tissue images, y pet and z k are the registered PVE-PET images and the randomly generated Gaussian blur kernel, G x ,G k They are PVC-PET image generation network and blur kernel generation network respectively.

6. The method according to claim 1, characterized in that In step (5), the conditional depth residual compensation network includes a parallel PVC-PET image generation network and a depth residual generation network, wherein the depth residual generation network is used to obtain a depth residual map based on the anatomical MR brain tissue image, and the PVC-PET image generation network is used to combine the depth residual map and the blur kernel prior to generate a PVC-PET image based on the anatomical MR brain tissue image.

7. The method according to claim 6, characterized in that In step (5), the loss function during the training of the conditional depth residual compensation network is for: in and The loss functions are The fidelity term and regularization term in G x ,G r They are PVC-PET image generation network and deep residual generation network respectively. represents the blur kernel prior, z a For anatomical MR brain tissue images, v and C represent the coefficient vector and DCT operator obtained after DCT transformation of the artifacts introduced by the blur kernel error, respectively. λ1, λ2, and λ3 are hyperparameters that control the weights of each item.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

9. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images