Computed tomography reconstruction method and related device

Abstract

The invention discloses a computed tomography reconstruction method and a related device, and relates to the technical field of image reconstruction, and the method comprises the steps: obtaining original projection domain data; de-noising processing is carried out on the original projection domain data to obtain projection domain data after de-noising processing; inputting the denoised projection domain data into a computed tomography reconstruction model to obtain computed tomography of an image domain output by the computed tomography reconstruction model; and enhancing the computed tomography of the image domain output by the computed tomography reconstruction model to obtain the final computed tomography. According to the method and the device, the improvement of the efficiency and the effect of computed tomography reconstruction is realized based on projection domain data denoising, computed tomography reconstruction model and enhancement of a model result.

Description

Technical Field

[0001] The present application relates to the field of image reconstruction technology, and in particular to a computer tomography reconstruction method and related devices. Background Art

[0002] CT (Computed Tomography) is a medical imaging technology, among which SPECT (Single-Photon Emission Computed Tomography) and PET (Positron Emission Tomography) are two CT technologies in nuclear medicine. Since they both image gamma rays emitted from the patient's body, they are collectively called ECT (Emission Computed Tomography). Taking SPECT as an example, SPECT equipment is a commonly used clinical imaging equipment in the field of nuclear medicine. It can be used for functional evaluation of organs such as thyroid, kidney, heart, brain, lung and other organs and diagnosis of related diseases. It also plays a major role in the clinical diagnosis and staging of various malignant tumors. Compared with traditional gamma cameras, SPECT equipment can not only reflect the function and morphology of organs and tissues, observe the changes of organs and diseases in three dimensions, but also display the above information in tomographic images in different directions.

[0003] Traditional computed tomography reconstruction techniques include methods based on iterative reconstruction and methods based on traditional filtered back projection reconstruction. However, the reconstruction efficiency and reconstruction effect of traditional computed tomography reconstruction techniques need to be improved.

[0004] Therefore, how to provide a computer tomography reconstruction method to improve the efficiency and effect of computer tomography reconstruction has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0005] In view of the above problems, the present application provides a computer tomography reconstruction method and related devices to achieve the purpose of improving the efficiency and effect of computer tomography reconstruction. The specific scheme is as follows:

[0006] The first aspect of the present application provides a computer tomography reconstruction method, comprising:

[0007] Get the original projection domain data;

[0008] Performing denoising on the original projection domain data to obtain denoised projection domain data;

[0009] Inputting the projection domain data after denoising into a computer tomography reconstruction model to obtain computer tomography in the image domain output by the computer tomography reconstruction model; the computer tomography reconstruction model is trained based on the projection domain training data and the image domain computer tomography training data;

[0010] The computed tomography in the image domain output by the computed tomography reconstruction model is enhanced to obtain a final computed tomography.

[0011] In a possible implementation, the performing denoising on the original projection domain data to obtain denoised projection domain data includes:

[0012] The original projection domain data is input into a trained denoising model to obtain denoised projection domain data output by the denoising model; the denoising model is trained using noisy projection domain data as training samples, denoised projection domain data as sample labels, and the projection domain data output by the model approaching the denoised projection domain data as a training target.

[0013] In a possible implementation, the computer tomography reconstruction model is trained as follows:

[0014] Determining training data, wherein the training data includes computed tomography training data in the image domain and projection domain training data corresponding to the computed tomography training data in the image domain;

[0015] Get pre-built generators and discriminators;

[0016] Based on the projection domain training data and the computed tomography training data in the image domain, the generator and the discriminator are iteratively trained multiple times to obtain a trained generator and a trained discriminator; the trained generator is the computed tomography reconstruction model.

[0017] In a possible implementation, during each iterative training process, the generator and the discriminator are trained based on the projection domain training data and the computed tomography training data in the image domain, including:

[0018] Using the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels, only training the generator;

[0019] Using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels, only training the discriminator;

[0020] The parameters of the discriminator are fixed, and the generator is trained again using the projection domain training data as training samples and sample labels.

[0021] In a possible implementation, during each iterative training process, the loss function for training the generator and the discriminator based on the projection domain training data and the computed tomography training data in the image domain includes:

[0022] Generator loss, discriminator loss, supervision loss of corresponding network layers and cascade network loss;

[0023] The generator loss is used to characterize the similarity between the output of the generator and the computed tomography training data in the image domain when only the generator is trained with the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels;

[0024] The discriminator loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when only the discriminator is trained using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels;

[0025] The cascade network loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when the parameters of the discriminator are fixed and the projection domain training data is used as training samples and sample labels and the generator is retrained;

[0026] The supervision loss of the corresponding network layer is used to characterize the similarity of the feature maps of the corresponding layer structures in the generator and the discriminator during each iterative training process.

[0027] In a possible implementation, the step of enhancing the computed tomography in the image domain output by the computed tomography reconstruction model to obtain a final computed tomography includes:

[0028] The computed tomography in the image domain output by the computed tomography reconstruction model is input into a trained enhancement model to obtain an enhanced computed tomography output by the enhancement model as the final computed tomography; the enhancement model is obtained by training with unenhanced computed tomography as training samples, enhanced computed tomography as sample labels, and the computed tomography output by the model approaching the enhanced computed tomography as a training target.

[0029] A second aspect of the present application provides a computer tomography reconstruction device, comprising:

[0030] An acquisition unit, used for acquiring original projection domain data;

[0031] A denoising processing unit, used for performing denoising processing on the original projection domain data to obtain denoised projection domain data;

[0032] A reconstruction unit, used for inputting the projection domain data after the denoising process into a computer tomography reconstruction model to obtain a computer tomography image in the image domain output by the computer tomography reconstruction model;

[0033] The enhancement unit is used to enhance the computed tomography in the image domain output by the computed tomography reconstruction model to obtain a final computed tomography.

[0034] In a possible implementation, the denoising processing unit is specifically used to:

[0035] The original projection domain data is input into a trained denoising model to obtain denoised projection domain data output by the denoising model; the denoising model is trained using noisy projection domain data as training samples, denoised projection domain data as sample labels, and the projection domain data output by the model approaching the denoised projection domain data as a training target.

[0036] In a possible implementation, the device further includes: a computed tomography reconstruction model training unit, the computed tomography reconstruction model training unit including:

[0037] A training data determination unit, configured to determine training data, wherein the training data includes computed tomography training data in the image domain and projection domain training data corresponding to the computed tomography training data in the image domain;

[0038] Generator and discriminator acquisition units, used to acquire pre-built generators and discriminators;

[0039] A training unit is used to perform multiple iterative training on the generator and the discriminator based on the projection domain training data and the computed tomography training data in the image domain to obtain a trained generator and a trained discriminator; the trained generator is the computed tomography reconstruction model.

[0040] In a possible implementation, during each iterative training process, the training unit is specifically used to:

[0041] Using the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels, only training the generator;

[0042] Using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels, only training the discriminator;

[0043] The parameters of the discriminator are fixed, and the generator is trained again using the projection domain training data as training samples and sample labels.

[0044] In a possible implementation, during each iterative training process, the loss function includes:

[0045] Generator loss, discriminator loss, supervision loss of corresponding network layers and cascade network loss;

[0046] The generator loss is used to characterize the similarity between the output of the generator and the computed tomography training data in the image domain when only the generator is trained with the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels;

[0047] The discriminator loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when only the discriminator is trained using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels;

[0048] The cascade network loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when the parameters of the discriminator are fixed and the projection domain training data is used as training samples and sample labels and the generator is retrained;

[0049] The supervision loss of the corresponding network layer is used to characterize the similarity of the feature maps of the corresponding layer structures in the generator and the discriminator during each iterative training process.

[0050] In a possible implementation, the enhancement unit includes:

[0051] The computed tomography in the image domain output by the computed tomography reconstruction model is input into a trained enhancement model to obtain an enhanced computed tomography output by the enhancement model as the final computed tomography; the enhancement model is obtained by training with unenhanced computed tomography as training samples, enhanced computed tomography as sample labels, and the computed tomography output by the model approaching the enhanced computed tomography as a training target.

[0052] A third aspect of the present application provides a computer program product, comprising computer-readable instructions, which, when executed on an electronic device, enables the electronic device to implement the computer tomography reconstruction method of the first aspect or any implementation of the first aspect.

[0053] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0054] The memory is used to store computer programs;

[0055] The processor is used to execute the computer program so that the electronic device can implement the computer tomography reconstruction method of the above-mentioned first aspect or any implementation manner of the first aspect.

[0056] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can perform the computer tomography reconstruction method of the above-mentioned first aspect or any implementation method of the first aspect.

[0057] By means of the above technical scheme, the present application provides a method and related device for computer tomography reconstruction, including: obtaining original projection domain data; denoising the original projection domain data to obtain denoised projection domain data; inputting the denoised projection domain data into a computer tomography reconstruction model to obtain computer tomography in the image domain output by the computer tomography reconstruction model; enhancing the computer tomography in the image domain output by the computer tomography reconstruction model to obtain the final computer tomography. The present application improves the efficiency and effect of computer tomography reconstruction based on projection domain data denoising, computer tomography reconstruction model and enhancement of model results. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0059] Figure 1 A flowchart of a computer tomography reconstruction method provided in an embodiment of the present application;

[0060] Figure 2 A schematic diagram of the structure of a denoising model example disclosed in an embodiment of the present application;

[0061] Figure 3 A schematic diagram of the structure of an example of a generator and a discriminator disclosed in an embodiment of the present application;

[0062] Figure 4 A schematic diagram of the structure of an enhanced model example disclosed in an embodiment of the present application;

[0063] Figure 5A schematic diagram of the structure of a computer tomography reconstruction device provided in an embodiment of the present application;

[0064] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0066] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0067] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0068] CT (Computed Tomography) is a medical imaging technology, among which SPECT (Single-Photon Emission Computed Tomography) and PET (Positron Emission Tomography) are two CT technologies in nuclear medicine. Since they both image gamma rays emitted from the patient's body, they are collectively called ECT (Emission Computed Tomography). Taking SPECT as an example, SPECT equipment is a commonly used clinical imaging equipment in the field of nuclear medicine. It can be used for functional evaluation of organs such as thyroid, kidney, heart, brain, lung and other organs and diagnosis of related diseases. It also plays a major role in the clinical diagnosis and staging of various malignant tumors. Compared with traditional gamma cameras, SPECT equipment can not only reflect the function and morphology of organs and tissues, observe the changes of organs and diseases in three dimensions, but also display the above information in tomographic images in different directions.

[0069] Traditional computed tomography reconstruction techniques include methods based on iterative reconstruction and methods based on traditional filtered back projection reconstruction. However, the reconstruction efficiency and reconstruction effect of traditional computed tomography reconstruction techniques need to be improved.

[0070] In order to solve the above problems, the present application provides a computer tomography reconstruction method. The computer tomography reconstruction method of the present application is described in detail below in conjunction with the accompanying drawings.

[0071] Reference Figure 1 , Figure 1 A flowchart of a computer tomography reconstruction method provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, a computer tomography reconstruction method provided in an embodiment of the present application may include steps S101 to S104, and these steps are described in detail below.

[0072] S101: Acquire original projection domain data;

[0073] In the present application, the original projection domain data is the projection domain data collected by a computer tomography device.

[0074] S102: performing denoising processing on the original projection domain data to obtain denoised projection domain data;

[0075] S103: inputting the projection domain data after denoising into a computer tomography reconstruction model to obtain computer tomography in the image domain output by the computer tomography reconstruction model; the computer tomography reconstruction model is trained based on the projection domain training data and the image domain computer tomography training data;

[0076] S104: enhancing the computed tomography in the image domain output by the computed tomography reconstruction model to obtain a final computed tomography.

[0077] In the present application, the final computed tomography imaging can be applied to clinical analysis and processing based on computed tomography imaging.

[0078] The present embodiment provides a method for computer tomography reconstruction, comprising: obtaining original projection domain data; denoising the original projection domain data to obtain denoised projection domain data; inputting the denoised projection domain data into a computer tomography reconstruction model to obtain computer tomography in the image domain output by the computer tomography reconstruction model; and enhancing the computer tomography in the image domain output by the computer tomography reconstruction model to obtain a final computer tomography. The present application improves the efficiency and effect of computer tomography reconstruction based on projection domain data denoising, computer tomography reconstruction model, and enhancement of model results.

[0079] In a possible implementation, the performing denoising on the original projection domain data to obtain denoised projection domain data includes:

[0080] The original projection domain data is input into a trained denoising model to obtain denoised projection domain data output by the denoising model; the denoising model is trained using noisy projection domain data as training samples, denoised projection domain data as sample labels, and the projection domain data output by the model approaching the denoised projection domain data as a training target.

[0081] In the present application, a denoising model may be pre-constructed, the denoising model comprising a coding group and a decoding group, wherein the coding group and the decoding group are symmetrical structures, and corresponding layer structures of the coding group and the decoding group are jump-connected.

[0082] For ease of understanding, refer to Figure 2 , Figure 2 A schematic diagram of a denoising model example disclosed in an embodiment of the present application is shown in FIG. Figure 2 As shown in Figure 1, the encoding group of the denoising model consists of 2 layers of 32x(3x3) convolutional layers, 2 layers of 64x(3x3) convolutional layers, 2 layers of 128x(3x3) convolutional layers, 2 layers of 256x(3x3) convolutional layers, 2 layers of 512x(3x3) convolutional layers and a pooling layer ( Figure 2 The decoding group consists of a symmetrical structure, which is composed of 2 layers of 256x (3x3) convolutional layers, 2 layers of 128x (3x3) convolutional layers, 2 layers of 64x (3x3) convolutional layers, 2 layers of 32x (3x3) convolutional layers and an upsampling layer ( Figure 2 (not shown in the figure), wherein the corresponding layers of the encoding group and the decoding group are channel-fused, for example, the two 32x (3x3) convolutional layers of the encoding group and the decoding group are skip-connected.

[0083] After the denoising model is constructed, the noisy projection domain data and the denoised projection domain data corresponding to the noisy projection domain data can be determined. In a possible implementation, a computed tomography image in the image domain generated clinically can be first obtained, and the computed tomography image in the image domain is transformed by an inverse Radon transform to obtain the corresponding projection domain data, and noise (such as Poisson noise) is added to the projection domain data to generate noisy projection domain data, and the denoised projection domain data corresponding to the noisy projection domain data is the projection domain data before the noise is added.

[0084] After determining the noisy projection domain data and the denoised projection domain data corresponding to the noisy projection domain data, the noisy projection domain data can be used as training samples, the denoised projection domain data can be used as sample labels, and the projection domain data output by the model approaching the denoised projection domain data can be used as a training target to train the denoising model and obtain a trained denoising model.

[0085] It should be noted that, in a feasible method, the noisy projection domain data is used as the training sample, the denoised projection domain data is used as the sample label, and the projection domain data output by the model is close to the denoised projection domain data as the training target. When the denoising model is trained, the loss function can be mean-square error (MSE), the optimizer can be Adam, and the evaluation index can be the signal-to-noise ratio.

[0086] In a possible implementation, the training method of the computed tomography reconstruction model includes the following steps:

[0087] S201: Determine training data, where the training data includes computed tomography training data in the image domain and projection domain training data corresponding to the computed tomography training data in the image domain;

[0088] In the present application, computed tomography images in the clinical image domain can be obtained as computed tomography training data in the image domain, and the computed tomography images in the clinical image domain can be transformed by inverse Radon transform to obtain corresponding projection domain data, which is the projection domain training data.

[0089] S202: Obtain a pre-built generator and discriminator;

[0090] In the present application, both the generator and the discriminator may adopt the network structure of U-Net, wherein the network structure of U-Net adopted by the generator may be the same as or different from the network structure of U-Net adopted by the discriminator. In one possible implementation, the network structure of U-Net adopted by the generator includes a coding group and a decoding group, wherein the coding group and the decoding group are symmetrical structures, and the corresponding layer structures of the coding group and the decoding group are jump-connected. The network structure of U-Net adopted by the discriminator may also include a coding group and a decoding group, wherein the coding group and the decoding group are symmetrical structures, and the corresponding layer structures of the coding group and the decoding group are jump-connected.

[0091] For ease of understanding, refer to Figure 3 , Figure 3 A schematic diagram of the structure of an example of a generator and a discriminator disclosed in an embodiment of the present application.

[0092] like Figure 3 As shown, the encoding group of the generator consists of 3 layers of 32x(3x3) convolutional layers, 3 layers of 64x(3x3) convolutional layers, 3 layers of 128x(3x3) convolutional layers, 3 layers of 256x(3x3) convolutional layers, 3 layers of 512x(3x3) convolutional layers and pooling layers ( Figure 3 The decoding group of the generator consists of a symmetrical structure, which is composed of 3 layers of 256x(3x3) convolutional layers, 3 layers of 128x(3x3) convolutional layers, 3 layers of 64x(3x3) convolutional layers, 3 layers of 32x(3x3) convolutional layers and an upsampling layer ( Figure 3 (not shown in the figure), wherein the corresponding layers of the encoding group of the generator and the decoding group of the generator are channel-fused, for example, the 3-layer 32x (3x3) convolutional layers of the encoding group of the generator and the decoding group of the generator are jump-connected.

[0093] The discriminator encoding group consists of 2 layers of 32x(3x3) convolutional layers, 2 layers of 64x(3x3) convolutional layers, 2 layers of 128x(3x3) convolutional layers, 2 layers of 256x(3x3) convolutional layers, 2 layers of 512x(3x3) convolutional layers and pooling layers ( Figure 3 The decoding group of the discriminator consists of a symmetrical structure, which is composed of 2 layers of 256x(3x3) convolutional layers, 2 layers of 128x(3x3) convolutional layers, 2 layers of 64x(3x3) convolutional layers, 2 layers of 32x(3x3) convolutional layers and an upsampling layer ( Figure 3 (not shown in the figure), wherein the corresponding layers of the encoding group of the discriminator and the decoding group of the discriminator are channel-fused, for example, the 2-layer 32x (3x3) convolutional layers of the encoding group of the discriminator and the decoding group of the discriminator are jump-connected.

[0094] It should be noted that the generator is mainly used to reconstruct the projection domain data into computer tomography in the image domain, and the discriminator is mainly used to convert the computer tomography in the image domain generated by the generator into projection domain data.

[0095] S203: Based on the projection domain training data and the computed tomography training data in the image domain, the generator and the discriminator are iteratively trained for multiple times to obtain a trained generator and a trained discriminator; the trained generator is the computed tomography reconstruction model.

[0096] Specifically, in each iterative training process, the process of training the generator and the discriminator based on the projection domain training data and the computed tomography training data in the image domain includes the following steps:

[0097] S301: using the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels, and only training the generator;

[0098] When the projection domain training data is used as training samples and the computed tomography training data in the image domain is used as sample labels, and only the generator is trained, the projection domain training data can be input into the generator to obtain the computed tomography in the image domain output by the generator, and the training goal is to make the computed tomography in the image domain output by the generator approach the computed tomography training data in the image domain, that is, to minimize the generator loss, and only the generator is trained.

[0099] S302: using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels, and only training the discriminator;

[0100] When the computed tomography training data in the image domain is used as training samples and the projection domain training data is used as sample labels, and only the discriminator is trained, the computed tomography training data in the image domain can be input into the discriminator to obtain the projection domain data output by the discriminator, and the training goal is to make the projection domain data output by the discriminator approach the projection domain training data, that is, to minimize the discriminator loss, and only the discriminator is trained.

[0101] S303: Fix the parameters of the discriminator, and train the generator again using the projection domain training data as training samples and sample labels.

[0102] When the parameters of the discriminator are fixed and the projection domain training data is used as training samples and sample labels to retrain the generator, the projection domain training data can be input into the generator to obtain the computed tomography of the image domain output by the generator; and the computed tomography of the image domain output by the generator is input into the discriminator to obtain the projection domain data output by the discriminator; the generator is retrained with the projection domain data output by the discriminator approaching the projection domain training data as the training goal, that is, minimizing the cascade network loss.

[0103] In a possible implementation, during each iterative training process, the loss function for training the generator and the discriminator based on the projection domain training data and the computed tomography training data in the image domain includes:

[0104] Generator loss, discriminator loss, supervision loss of corresponding network layers and cascade network loss;

[0105] The generator loss is used to characterize the similarity between the output of the generator and the computed tomography training data in the image domain when only the generator is trained with the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels;

[0106] The discriminator loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when only the discriminator is trained using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels;

[0107] The cascade network loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when the parameters of the discriminator are fixed and the projection domain training data is used as training samples and sample labels and the generator is retrained;

[0108] The supervision loss of the corresponding network layer is used to characterize the similarity of the feature maps of the corresponding layer structures in the generator and the discriminator during each iterative training process.

[0109] It should be noted that in the U-Net network, there will be a high similarity between the feature maps of the corresponding network layers, resulting in a waste of computing resources. To solve this problem, in this application, the supervision loss of the corresponding network layer is added during each iterative training process, that is, the similarity of the feature maps of the corresponding layer structures in the generator and / or the discriminator is calculated. If the similarity is greater than the preset threshold, one of the network layers in the corresponding network layer can be distilled and optimized to avoid repeated calculations of similar feature maps and save computing resources. Among them, the Euclidean distance can be used to measure the similarity between feature maps.

[0110] It should also be noted that the generator loss, the discriminator loss, the supervision loss of the corresponding network layer and the cascade network loss can all be mean-square error (MSE), the optimizer can be Adam, and the evaluation criterion can be accuracy.

[0111] In a possible implementation, the step of enhancing the computed tomography in the image domain output by the computed tomography reconstruction model to obtain a final computed tomography includes:

[0112] The computed tomography in the image domain output by the computed tomography reconstruction model is input into a trained enhancement model to obtain an enhanced computed tomography output by the enhancement model as the final computed tomography; the enhancement model is obtained by training with unenhanced computed tomography as training samples, enhanced computed tomography as sample labels, and the computed tomography output by the model approaching the enhanced computed tomography as a training target.

[0113] In the present application, an enhanced model can be pre-built, and the enhanced model can be composed of super residual network components, each of which is composed of convolution, batch normalization, and ReLU activation. Figure 4 , Figure 4 Schematic diagram of the structure of an enhanced model example disclosed in the embodiment of the present application. Figure 4 As shown, the enhanced model consists of N super residual network components. The value of N can be determined based on the scene requirements. In a possible implementation, the value of N can be 16.

[0114] After the enhancement model is constructed, the unenhanced computed tomography and the enhanced computed tomography can be determined. In one achievable manner, the enhanced computed tomography may be a computed tomography in the clinically generated image domain, and the unenhanced computed tomography may be a computed tomography generated by the computed tomography reconstruction model using projection domain data corresponding to the computed tomography in the clinically generated image domain.

[0115] After determining the unenhanced CT imaging and the enhanced CT imaging, the unenhanced CT imaging can be used as a training sample, the enhanced CT imaging can be used as a sample label, and the CT imaging output by the model is close to the enhanced CT imaging as a training target to train the enhancement model.

[0116] It should be noted that, when using unenhanced computed tomography as training samples, enhanced computed tomography as sample labels, and the computed tomography output by the model approaching the enhanced computed tomography as the training target, when training the enhanced model, the loss function can be perceptual loss, the optimizer can be Adam, and the evaluation criterion can be peak signal-to-noise ratio.

[0117] A computer tomography reconstruction method provided in an embodiment of the present application is introduced above. A device for executing the computer tomography reconstruction method will be introduced below.

[0118] See also Figure 5 , Figure 5 The following is a schematic diagram of the structure of a computer tomography reconstruction device provided in an embodiment of the present application. Figure 5 As shown, the computer tomography reconstruction device comprises:

[0119] An acquisition unit 11 is used to acquire original projection domain data;

[0120] A denoising processing unit 12 is used to perform denoising on the original projection domain data to obtain denoised projection domain data;

[0121] A reconstruction unit 13, used for inputting the projection domain data after the denoising process into a computer tomography reconstruction model to obtain a computer tomography image in the image domain output by the computer tomography reconstruction model;

[0122] The enhancement unit 14 is used to enhance the computed tomography in the image domain output by the computed tomography reconstruction model to obtain a final computed tomography.

[0123] In a possible implementation, the denoising processing unit is specifically used to:

[0124] The original projection domain data is input into a trained denoising model to obtain denoised projection domain data output by the denoising model; the denoising model is trained using noisy projection domain data as training samples, denoised projection domain data as sample labels, and the projection domain data output by the model approaching the denoised projection domain data as a training target.

[0125] In a possible implementation, the device further includes: a computed tomography reconstruction model training unit, the computed tomography reconstruction model training unit including:

[0126] A training data determination unit, configured to determine training data, wherein the training data includes computed tomography training data in the image domain and projection domain training data corresponding to the computed tomography training data in the image domain;

[0127] Generator and discriminator acquisition units, used to acquire pre-built generators and discriminators;

[0128] A training unit is used to perform multiple iterative training on the generator and the discriminator based on the projection domain training data and the computed tomography training data in the image domain to obtain a trained generator and a trained discriminator; the trained generator is the computed tomography reconstruction model.

[0129] In a possible implementation, during each iterative training process, the training unit is specifically used to:

[0130] Using the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels, only training the generator;

[0131] Using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels, only training the discriminator;

[0132] The parameters of the discriminator are fixed, and the generator is trained again using the projection domain training data as training samples and sample labels.

[0133] In a possible implementation, during each iterative training process, the loss function includes:

[0134] Generator loss, discriminator loss, supervision loss of corresponding network layers and cascade network loss;

[0135] The generator loss is used to characterize the similarity between the output of the generator and the computed tomography training data in the image domain when only the generator is trained with the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels;

[0136] The discriminator loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when only the discriminator is trained using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels;

[0137] The cascade network loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when the parameters of the discriminator are fixed and the projection domain training data is used as training samples and sample labels and the generator is retrained;

[0138] The supervision loss of the corresponding network layer is used to characterize the similarity of the feature maps of the corresponding layer structures in the generator and the discriminator during each iterative training process.

[0139] In a possible implementation, the enhancement unit includes:

[0140] The computed tomography in the image domain output by the computed tomography reconstruction model is input into a trained enhancement model to obtain an enhanced computed tomography output by the enhancement model as the final computed tomography; the enhancement model is obtained by training with unenhanced computed tomography as training samples, enhanced computed tomography as sample labels, and the computed tomography output by the model approaching the enhanced computed tomography as a training target.

[0141] The present application also provides an electronic device in an embodiment. Figure 6 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0142] like Figure 6 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0143] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0144] An embodiment of the present application also provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the computer tomography reconstruction methods provided in the embodiments of the present application.

[0145] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement any one of the computer tomography reconstruction methods provided in the embodiment of the present application.

[0146] It should also be noted that 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 over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0147] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0148] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0149] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A computer tomography reconstruction method, characterized in that: include: Get the original projection domain data; Performing denoising on the original projection domain data to obtain denoised projection domain data; Inputting the projection domain data after denoising into a computer tomography reconstruction model to obtain computer tomography in the image domain output by the computer tomography reconstruction model; the computer tomography reconstruction model is trained based on the projection domain training data and the image domain computer tomography training data; The computed tomography in the image domain output by the computed tomography reconstruction model is enhanced to obtain a final computed tomography.

2. The method according to claim 1, characterized in that The denoising process is performed on the original projection domain data to obtain the denoised projection domain data, including: The original projection domain data is input into a trained denoising model to obtain denoised projection domain data output by the denoising model; the denoising model is trained using noisy projection domain data as training samples, denoised projection domain data as sample labels, and the projection domain data output by the model approaching the denoised projection domain data as a training target.

3. The method according to claim 1, characterized in that: The computer tomography reconstruction model is trained as follows: Determining training data, wherein the training data includes computed tomography training data in the image domain and projection domain training data corresponding to the computed tomography training data in the image domain; Get pre-built generators and discriminators; Based on the projection domain training data and the computed tomography training data in the image domain, the generator and the discriminator are iteratively trained multiple times to obtain a trained generator and a trained discriminator; the trained generator is the computed tomography reconstruction model.

4. The method according to claim 3, characterized in that: During each iterative training process, the generator and the discriminator are trained based on the projection domain training data and the computed tomography training data in the image domain, including: Using the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels, only training the generator; Using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels, only training the discriminator; The parameters of the discriminator are fixed, and the generator is trained again using the projection domain training data as training samples and sample labels.

5. The method according to claim 4, characterized in that During each iterative training process, based on the projection domain training data and the computed tomography training data in the image domain, the loss function for training the generator and the discriminator includes: Generator loss, discriminator loss, supervision loss of corresponding network layers and cascade network loss; The generator loss is used to characterize the similarity between the output of the generator and the computed tomography training data in the image domain when only the generator is trained with the projection domain training data as training samples and the computed tomography training data in the image domain as sample labels; The discriminator loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when only the discriminator is trained using the computed tomography training data in the image domain as training samples and the projection domain training data as sample labels; The cascade network loss is used to characterize the similarity between the output of the discriminator and the projection domain training data when the parameters of the discriminator are fixed and the projection domain training data is used as training samples and sample labels and the generator is retrained; The supervision loss of the corresponding network layer is used to characterize the similarity of the feature maps of the corresponding layer structures in the generator and the discriminator during each iterative training process.

6. The method according to claim 1, characterized in that The step of enhancing the computed tomography in the image domain output by the computed tomography reconstruction model to obtain a final computed tomography includes: The computed tomography in the image domain output by the computed tomography reconstruction model is input into a trained enhancement model to obtain an enhanced computed tomography output by the enhancement model as the final computed tomography; the enhancement model is obtained by training with unenhanced computed tomography as training samples, enhanced computed tomography as sample labels, and the computed tomography output by the model approaching the enhanced computed tomography as a training target.

7. A computer tomography reconstruction device, characterized in that: include: An acquisition unit, used for acquiring original projection domain data; A denoising processing unit, used for performing denoising processing on the original projection domain data to obtain denoised projection domain data; A reconstruction unit, used for inputting the projection domain data after the denoising process into a computer tomography reconstruction model to obtain a computer tomography image in the image domain output by the computer tomography reconstruction model; The enhancement unit is used to enhance the computed tomography in the image domain output by the computed tomography reconstruction model to obtain a final computed tomography.

8. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on an electronic device, enable the electronic device to implement the computer tomography reconstruction method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the computer tomography reconstruction method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the computer tomography reconstruction method as described in any one of claims 1 to 6.

Images