Image reconstruction method, device, computer equipment and storage medium

Abstract

The present application relates to an image reconstruction method, device, computer equipment and storage medium. The method comprises: acquiring a first medical image; the scanning time corresponding to the first medical image is less than a preset standard scanning time; performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to characterize the edge information of the first medical image; and obtaining a second medical image corresponding to the standard scanning time according to the first medical image, the edge image and a preset image reconstruction model. The method improves the efficiency of the obtained second medical image corresponding to the standard scanning time.

Description

Technical Field

[0001] The present application relates to the field of image reconstruction technology, and in particular to an image reconstruction method, apparatus, computer device and storage medium. Background Art

[0002] With the development of medical imaging technology, positron emission computed tomography-computed tomography scanners (PET-CT) and positron emission computed tomography / magnetic resonance imaging (PET / MRI) have emerged. PET-CT is a large-scale functional metabolic and molecular imaging diagnostic device that combines PET and CT, and has the examination functions of both PET and CT. PET-MR is a large-scale functional metabolic molecular imaging diagnostic device that combines PET and MR, and has the examination functions of both PET and MR.

[0003] In traditional technology, when a PET-CT or PET-MR device is used to examine a subject, a standard dose of PET drug is usually injected into the subject, and the subject is scanned for a long time. The image is reconstructed using the data collected during the long scan to obtain a reconstructed PET image.

[0004] However, in the conventional technology, since the scanning time of the subject is relatively long, there is a problem of low efficiency in obtaining the reconstructed PET image. Summary of the invention

[0005] Based on this, it is necessary to provide an image reconstruction method, apparatus, computer equipment and storage medium to address the problem of low efficiency in obtaining reconstructed PET images in traditional technologies.

[0006] In a first aspect, an embodiment of the present invention provides an image reconstruction method, the method comprising:

[0007] Acquiring a first medical image; wherein a scanning time corresponding to the first medical image is less than a preset standard scanning time;

[0008] Performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image;

[0009] A second medical image corresponding to the standard scanning time is obtained according to the first medical image, the edge image and a preset image reconstruction model.

[0010] In a second aspect, an embodiment of the present invention provides an image reconstruction device, the device comprising:

[0011] A first acquisition module is used to acquire a first medical image; the scanning time corresponding to the first medical image is less than a preset standard scanning time;

[0012] A first calculation module, configured to perform gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image;

[0013] A reconstruction module is used to obtain a second medical image corresponding to the standard scanning time according to the first medical image, the edge image and a preset image reconstruction model.

[0014] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0015] Acquiring a first medical image; wherein a scanning time corresponding to the first medical image is less than a preset standard scanning time;

[0016] Performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image;

[0017] A second medical image corresponding to the standard scanning time is obtained according to the first medical image, the edge image and a preset image reconstruction model.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0019] Acquiring a first medical image; wherein a scanning time corresponding to the first medical image is less than a preset standard scanning time;

[0020] Performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image;

[0021] A second medical image corresponding to the standard scanning time is obtained according to the first medical image, the edge image and a preset image reconstruction model.

[0022] In the image reconstruction method, apparatus, computer device and storage medium provided in the above-mentioned embodiments, the computer device acquires a first medical image; the scanning time corresponding to the first medical image is less than a preset standard scanning time; the first medical image is subjected to gradient calculation to obtain an edge image corresponding to the first medical image; the edge image is used to characterize the edge information of the first medical image; and the second medical image corresponding to the standard scanning time is obtained according to the first medical image, the edge image and the preset image reconstruction model. In this method, the computer device can obtain an edge image characterizing the edge information of the first medical image by performing gradient calculation on the first medical image whose scanning time is less than the preset standard scanning time, and can then reconstruct a second medical image corresponding to the standard scanning time with rich details according to the first medical image whose scanning time is less than the preset standard scanning time, the edge image and the preset image reconstruction model, thereby improving the efficiency of the obtained second medical image. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the internal structure of a computer device provided by an embodiment;

[0024] Figure 1a A schematic diagram of a process for obtaining a prediction graph of a standard scanning duration provided by an embodiment;

[0025] Figure 2 A schematic flow chart of an image reconstruction method provided by an embodiment;

[0026] Figure 2a A schematic diagram of a standard scanning time image obtained by using an image reconstruction model in one embodiment;

[0027] Figure 2b A schematic diagram of a standard scanning time image obtained by using an image reconstruction model in one embodiment;

[0028] Figure 2c A schematic diagram of a standard scanning time image obtained by using an image reconstruction model in one embodiment;

[0029] Figure 3 A schematic flow chart of an image reconstruction method provided by another embodiment;

[0030] Figure 4 A schematic flow chart of an image reconstruction method provided by another embodiment;

[0031] Figure 5 A schematic flow chart of an image reconstruction method provided by another embodiment;

[0032] Figure 5a A schematic diagram of a network structure of an initial image reconstruction model provided by an embodiment;

[0033] Figure 6 A schematic flow chart of an image reconstruction method provided by another embodiment;

[0034] Figure 7 A schematic diagram of the structure of an image reconstruction device provided by an embodiment. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] The image reconstruction method provided in the embodiment of the present application can be applied to Figure 1 The computer device shown. The computer device includes a processor and a memory connected by a system bus, and a computer program is stored in the memory. When the processor executes the computer program, the steps of the following method embodiment can be executed. Optionally, the computer device may also include a network interface, a display screen and an input device. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory, and the non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. Optionally, the computer device can be a server, a personal computer, a personal digital assistant, or other terminal devices, such as a tablet computer, a mobile phone, etc., or a cloud or remote server. The embodiment of the present application does not limit the specific form of the computer device.

[0037] It should be noted that the image reconstruction method provided in the embodiments of the present application may be executed by an image reconstruction device, which may be implemented as part or all of a computer device through software, hardware, or a combination of software and hardware. In the following method embodiments, the execution subject is a computer device as an example for explanation.

[0038] It should be noted that there are two main factors that affect the quality of PET images obtained by positron emission computed tomography-computed tomography scanners (PET-CT) or positron emission computed tomography / magnetic resonance imaging (PET / MRI): one is the injection dose of PET drugs; the other is the scanning time of the PET system. Generally, the longer the scanning time of the PET system, the more data is collected, and the quality of the reconstructed PET image can meet clinical needs; conversely, if the scanning time is short, the collected data is insufficient, and the reconstructed PET image is difficult to be used clinically. At present, for the acquisition of PET data, it usually takes 3 minutes per bed when a normal dose is injected; if half of the normal dose is injected, it means that at least 6 minutes of data must be collected to reconstruct a PET image that meets clinical needs. However, long-term scanning will lead to the problem of low efficiency in obtaining reconstructed images. Therefore, improving the efficiency of obtaining PET reconstructed images without affecting the quality of the generated PET reconstructed images is of great significance to PET-CT and PET / MRI scanning. Figure 1a A schematic diagram of a process for obtaining a prediction graph of a standard scanning duration is provided in accordance with an embodiment. Figure 1a As shown, the computer device performs standardization processing on a large number of short-time scanning sample images, inputs the standardized short-time scanning sample images into the initial image reconstruction model to obtain an output result, and trains the initial image reconstruction model according to the output result of the initial image reconstruction model and the standardized standard scanning time sample images to obtain an image reconstruction model. In clinical practice, when it is necessary to reconstruct a prediction map of the standard scanning time, the short-time scanning images obtained clinically are standardized, and the standardized short-time scanning images are input into the image reconstruction model, and the output results are linearly transformed to obtain a standard scanning time prediction map.

[0039] The following specific embodiments are used to describe in detail the technical solution of the present invention and how the technical solution of the present invention solves the above technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0040] Figure 2 A flowchart of an image reconstruction method provided by an embodiment. Figure 2a A schematic diagram of a standard scanning time image obtained by using an image reconstruction model in one embodiment; Figure 2bA schematic diagram of a standard scanning time image obtained by using an image reconstruction model in one embodiment; Figure 2c Schematic diagram of a standard scan time image obtained by using an image reconstruction model in one embodiment; this embodiment involves a specific implementation process in which a computer device performs gradient calculation on a first medical image whose scan time is less than a preset standard scan time to obtain an edge image corresponding to the first medical image, and obtains a second medical image corresponding to the standard scan time based on the first medical image, the edge image and the preset image reconstruction model. Figure 2 As shown, the method may include:

[0041] S201, acquiring a first medical image; a scanning time corresponding to the first medical image is less than a preset standard scanning time.

[0042] It can be understood that the standard scanning time here refers to the scanning time corresponding to the generation of images that meet clinical needs by scanning the subject under the condition of injecting different doses of developer during the process of collecting data from the subject using the medical imaging device. For example, taking PET scanning as an example, if the dose of developer injected into the subject is a normal dose, the scanning time corresponding to the generation of PET images that meet clinical needs is 3 minutes, then the corresponding standard scanning time is 3 minutes; if the dose of developer injected into the subject is half of the normal dose, the scanning time corresponding to the generation of PET images that meet clinical needs is 6 minutes, then the corresponding standard scanning time is 6 minutes. Optionally, the computer device can obtain the first medical image from a PACS (Picture Archiving and Communication Systems) server, or can obtain the first medical image in real time from a medical imaging device. Optionally, the medical imaging device here can be a PET-CT device, a PET / MRI device, a PET device, or a CT device. Optionally, the first medical image may be a PET image generated by a PET-CT or PET / MRI medical imaging device, or may be a PET image generated by a single PET medical imaging device, or may be a CT image generated by a CT device.

[0043] S202, performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image.

[0044] Specifically, the computer device performs gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image. The edge image is used to characterize edge information of the first medical image. Optionally, the computer device may perform gradient calculation on the first medical image using a Sobel operator, or may perform gradient calculation on the first medical image using a Prewitt operator or a Roberts cross edge detection operator to obtain an edge image corresponding to the first medical image.

[0045] S203: Obtain a second medical image corresponding to the standard scanning time according to the first medical image, the edge image and a preset image reconstruction model.

[0046] Specifically, the computer device obtains a second medical image corresponding to the standard scanning time according to the first medical image, the edge image and the preset image reconstruction model. Optionally, the computer device may input the first medical image into the preset image reconstruction model to obtain a prediction map corresponding to the first medical image, and obtain the second medical image corresponding to the standard scanning time according to the prediction map and the edge image corresponding to the first medical image; or the first medical image and the edge image may be simultaneously input into the preset image reconstruction model to obtain the second medical image corresponding to the standard scanning time. Exemplarily, taking PET scanning as an example, if the dose of the contrast agent injected into the subject is a normal dose, the corresponding standard scanning time is 3 minutes, and if the scanning time corresponding to the acquired first medical image is 1.5 minutes, then the scanning time corresponding to the obtained second medical image is the standard scanning time of 3 minutes. Optionally, the network structure of the preset image reconstruction model may be a fully convolutional network (FullyConvolutional Networks), such as a V-Net network, a U-Net network, etc., or a generative adversarial network (Generative Adversarial Nets), such as a pix2pix network, a WGAN network, etc. Please refer to Figure 2a , Figure 2b , Figure 2c ,like Figure 2a , Figure 2b , Figure 2c As shown, from left to right in the figure are the short-time scan image, the standard scan time image obtained by the image reconstruction model of the present application, and the gold standard scan time image. It can be seen that the standard scan time image obtained by the present application is almost the same as the gold standard scan time image, that is, the accuracy of the standard scan time image obtained by the image reconstruction model of the present application is sufficient, and at the same time, the efficiency of the reconstructed image is improved by reconstructing the standard scan time image through the short-time scan image and the image reconstruction model, thereby solving the problem of low efficiency in obtaining the reconstructed image of the subject through long-time scanning.

[0047] In this embodiment, the computer device can obtain an edge image representing the edge information of the first medical image by performing gradient calculation on the first medical image whose scanning time is less than the preset standard scanning time, and then can reconstruct a second medical image with rich details corresponding to the standard scanning time based on the first medical image whose scanning time is less than the preset standard scanning time, the edge image and the preset image reconstruction model, thereby improving the efficiency of the obtained second medical image.

[0048] Figure 3 A flowchart of an image reconstruction method provided in another embodiment. This embodiment relates to a specific implementation process of a computer device obtaining a second medical image corresponding to a standard scanning time according to a first medical image, an edge image and a preset image reconstruction model. Figure 3 As shown, based on the above embodiment, as an optional implementation manner, the above S203 includes:

[0049] S301, obtaining a prediction map and an edge prediction map according to a first medical image, an edge image and an image reconstruction model; wherein the edge feature information included in the prediction map is less than the edge feature information included in the edge prediction map.

[0050] Specifically, the computer device obtains a prediction map and an edge prediction map based on the above-mentioned first medical image, edge image and image reconstruction model. The edge feature information included in the prediction map is less than the edge feature information included in the edge prediction map. It is understandable that in the process of obtaining the prediction map based on the first medical image and the reconstruction model, the edge feature information in the obtained prediction map will be lost due to incomplete extraction of the edge feature information of the first medical image, so that the edge feature information included in the prediction map is less than the edge feature information included in the edge prediction map. Optionally, the computer device can input the first medical image and the edge image into the image reconstruction model to obtain the prediction map, and obtain the edge prediction map corresponding to the edge image based on the feature information generated in the process of obtaining the prediction map.

[0051] S302: Obtain a second medical image according to the prediction map and the edge prediction map.

[0052] Specifically, the computer device can obtain the second medical image based on the prediction map and edge prediction map obtained above. Optionally, the computer device can fuse the features of the edge prediction map into the obtained prediction map, restore the detail information in the prediction map based on the edge prediction map, and obtain the second medical image.

[0053] In this embodiment, the computer device can quickly obtain a prediction map and an edge prediction map based on the first medical image, the edge image and the image reconstruction model, and then can quickly obtain a second medical image with rich detail information based on the prediction map and the edge prediction map, thereby improving the efficiency of the obtained second medical image; in addition, based on the first medical image, the edge image and the image reconstruction model, the prediction map and the edge prediction map can be accurately obtained, and then can accurately obtain a second medical image with rich detail information based on the prediction map and the edge prediction map, thereby improving the accuracy of the obtained second medical image.

[0054] Figure 4 A flowchart of an image reconstruction method provided in another embodiment. This embodiment relates to a specific implementation process of a computer device obtaining a prediction map and an edge prediction map based on a first medical image, an edge image and a preset image reconstruction model. Figure 4 As shown, based on the above embodiment, as an optional implementation, the above S301 includes:

[0055] S401, inputting a first medical image and an edge image into an image reconstruction model to obtain feature information of the first medical image.

[0056] Specifically, the computer device inputs the first medical image and the edge image into the above-mentioned image reconstruction model to obtain the feature information of the first medical image. Optionally, the image reconstruction model can perform downsampling and upsampling operations on the input first medical image to obtain the feature information of the first medical image. Optionally, before the computer device inputs the first medical image into the image reconstruction model, the resolution of the first medical image can be compared with the resolution of the sample image used when training the image reconstruction model. If the resolution of the first medical image is different from the resolution of the sample image, the first medical image can be resampled to an image with the same resolution space as the sample image, and then the resampled first medical image can be input into the image reconstruction model.

[0057] S402, obtaining a prediction graph based on the feature information.

[0058] Specifically, the computer device inputs the first medical image and the edge image into the image reconstruction model, and after obtaining the feature information of the first medical image, the image reconstruction model obtains the prediction map according to the obtained feature information of the first medical image. Optionally, the image reconstruction model can predict the feature information of the first medical image according to the obtained feature information of the first medical image, obtain the predicted feature information, and then generate the prediction map according to the obtained predicted feature information.

[0059] S403, using the edge attention mechanism, combining the feature information and the edge image, to obtain an edge prediction map.

[0060] Specifically, the computer device inputs the first medical image and the edge image into the image reconstruction model, and after obtaining the feature information of the first medical image, the image reconstruction model uses the edge attention mechanism to combine the obtained feature information of the first medical image and the input edge image to obtain an edge prediction map. It should be noted that the edge attention mechanism can exclude irrelevant information in the feature information of the first medical image under the guidance of the feature information of the first medical image, concentrate on learning and extracting features related to the edge, and combine the edge image to obtain the edge prediction map.

[0061] In this embodiment, the computer device inputs the first medical image and the edge image into the image reconstruction model to obtain the feature information of the first medical image, and then can accurately obtain the prediction map based on the feature information of the first medical image. Furthermore, by combining the feature information of the first medical image and the edge image and utilizing the edge attention mechanism, a detailed edge prediction map can be obtained, and then an accurate second medical image can be obtained based on the prediction map and the edge prediction map.

[0062] In some scenarios, in order to facilitate the convergence of the image reconstruction model, it is necessary to standardize the first medical image and the edge image input to the image reconstruction model. Since the edge image is obtained by performing gradient calculation on the first medical image, that is, in order to facilitate the convergence of the image reconstruction model, it is necessary to standardize the first medical image. On the basis of the above embodiment, as an optional implementation, before S202, the above method also includes: standardizing the first medical image according to the mean of the pixels of the first medical image and the standard deviation of the pixels of the first medical image to obtain the standardized first medical image; S202 includes: performing gradient calculation on the standardized first medical image to obtain the edge image corresponding to the first medical image.

[0063] Specifically, the computer device performs standardization processing on the first medical image according to the mean value of the pixels of the first medical image and the standard deviation of the pixels of the first medical image to obtain the first medical image after standardization processing, and then performs gradient calculation on the first medical image after standardization processing to obtain the edge image corresponding to the first medical image. Optionally, the computer device may calculate the edge image corresponding to the first medical image according to the formula The first medical image is standardized to obtain the first medical image after the standardization, where I′ st represents the first medical image, I' represents the first medical image after standardization, μ represents the mean of the pixels of the first medical image, and σ represents the standard deviation of the pixels of the first medical image.

[0064] In this embodiment, the computer device performs standardization processing on the first medical image according to the mean value of the pixels of the first medical image and the standard deviation of the pixels of the first medical image to obtain the standardized first medical image, and then the edge image corresponding to the first medical image is also the standardized edge image. In this way, inputting the standardized first medical image and the standardized edge image into the image reconstruction model can facilitate the convergence of the image reconstruction model and improve the efficiency of obtaining the second medical image corresponding to the standard scanning time.

[0065] In some scenarios, if the first medical image is standardized, it is necessary to perform linear transformation on the obtained second medical image. Based on the above embodiment, as an optional implementation, after the above S203, the above method further includes: performing linear transformation on the second medical image according to the mean value of the pixels of the first medical image and the standard deviation of the pixels of the first medical image to obtain a processed second medical image.

[0066] Specifically, the computer device performs linear transformation processing on the second medical image according to the mean value of the pixels of the first medical image and the standard deviation of the pixels of the first medical image to obtain a processed second medical image. Optionally, the computer device may perform linear transformation processing on the second medical image according to the formula I=I DL *σ+μ performs linear transformation on the second medical image to obtain the processed second medical image, where I DL represents the second medical image, I represents the processed second medical image, μ represents the mean of the pixels of the first medical image, and σ represents the standard deviation of the pixels of the first medical image.

[0067] In this embodiment, the computer device performs linear transformation processing on the second medical image based on the mean value and standard deviation of the pixels of the first medical image, so that the size and number of channels of the processed second medical image are consistent with those of the first sample medical image, thereby improving the accuracy of the processed second medical image.

[0068] Figure 5 A flowchart of an image reconstruction method provided in another embodiment. Figure 5a The network structure diagram of the initial image reconstruction model provided by an embodiment. This embodiment relates to the specific implementation process of the computer device training the image reconstruction model. Figure 5 As shown, the training process of the image reconstruction model may include:

[0069] S501, performing gradient calculation on a first sample medical image to obtain a first sample edge image; the first sample edge image is used to characterize edge information of the first sample medical image; and the scanning time corresponding to the first sample medical image is less than the standard scanning time.

[0070] Specifically, the computer device performs gradient calculation on the first sample medical image to obtain a first sample edge image. The first sample edge image is used to characterize the edge information of the first sample medical image, and the scanning time corresponding to the first sample medical image is less than the standard scanning time. Exemplarily, in this embodiment, if the standard scanning time is 3 minutes, the scanning time corresponding to the first sample medical image can be 1.5 minutes or 1 minute. Without loss of generality, a medical image with a scanning time less than half of the standard scanning time can be used as the first sample medical image in this embodiment. Optionally, the computer device can obtain the first sample medical image from a PACS (Picture Archiving and Communication Systems) server, or can obtain the first sample medical image in real time from a medical imaging device. Optionally, the medical imaging device here can be a PET-CT device, a PET / MRI device, or a CT device. Optionally, the first sample medical image can be a PET image generated by a PET-CT or PET / MRI medical imaging device, or a PET image generated by a single PET medical imaging device, or a CT image generated by a CT device. Optionally, the computer device can use a Sobel operator to perform gradient calculation on the first sample medical image, or use a Prewitt operator or a Roberts cross operator to perform gradient calculation on the first sample medical image to obtain an edge image corresponding to the first sample medical image.

[0071] S502, performing gradient calculation on the second sample medical image to obtain a second sample edge image; the second sample edge image is used to characterize edge information of the second sample medical image; and the scanning time length corresponding to the second sample medical image is the standard scanning time length.

[0072] Specifically, the computer device performs gradient calculation on the second sample medical image to obtain a second sample edge image. The second sample edge image is used to characterize edge information of the second sample medical image, and the scanning time corresponding to the second sample medical image is the standard scanning time. Optionally, the computer device can obtain the second sample medical image from a PACS (Picture Archiving and Communication Systems) server, or can obtain the second sample medical image in real time from a medical imaging device. Optionally, the medical imaging device here can be a PET-CT device, a PET / MRI device, or a CT device. Optionally, the second sample medical image may be a PET image generated by a PET-CT or PET / MRI medical imaging device, or may be a PET image generated by a single PET medical imaging device, or may be a CT image generated by a CT device. It should be noted that the second sample medical image is an image corresponding to the image type of the first sample medical image. For example, if the first sample medical image is a PET image with a scan time shorter than a standard scan time, the second sample medical image is a PET image corresponding to the standard scan time; if the first sample medical image is a CT image with a scan time shorter than a standard scan time, the second sample medical image is a CT image corresponding to the annotated scan time. Optionally, the computer device may perform gradient calculation on the second sample medical image using a Sobel operator, or may perform gradient calculation on the second sample medical image using a Prewitt operator or a Roberts cross edge detection operator to obtain an edge image corresponding to the second sample medical image.

[0073] S503, obtaining a sample edge prediction map and a reconstructed sample image according to the first sample medical image, the first edge image and a preset initial image reconstruction model; the reconstructed sample image is an image of a standard scanning time length corresponding to the first sample image.

[0074] Specifically, the computer device obtains a sample edge prediction map and a reconstructed sample image based on the first sample medical image, the first edge image and a preset initial image reconstruction model. The reconstructed sample image is an image of a standard scanning time length corresponding to the first sample image. Optionally, the computer device can input the first sample medical image and the first edge image into a preset initial image reconstruction model to obtain feature information of the first sample medical image, obtain a sample prediction map of the first sample medical image based on the feature information of the first sample medical image, utilize an edge attention mechanism, combine the feature information of the first sample medical image and the first edge image to obtain a sample edge prediction map, and obtain a reconstructed sample image based on the obtained sample prediction map and the sample edge prediction map. Figure 5a As shown, the main function of the edge attention mechanism is to exclude irrelevant information with the help of the feature information of the first sample medical image, concentrate on learning and extracting features related to the boundary, and connect the obtained sample edge prediction map to the initial image reconstruction model to assist the initial image reconstruction model in restoring the detail information of the first sample medical image, fuse the first sample medical image with the first edge image, pass through three gate mechanisms (Gate Module) in sequence, and finally output the prediction of the first edge image through a layer of convolution operation, wherein the gate mechanism is the most core basic unit for extracting boundary-related areas, and the gate mechanism performs bilinear upsampling, convolution, concatenation and sigmoid processing on the deeper network layer of the initial image reconstruction model (providing advanced semantic feature information, and the second, third and fourth downsampling output results are used in this embodiment), and then the feature map after sigmoid processing and the output of the residual block of the edge attention mechanism (the network is shallow) are element-wise dot-multiplied, and the result of the dot-multiplication is used as the input of the next gate mechanism, and the edge attention mechanism is locally supervised by introducing the value of the loss function of the first edge image and the sample edge prediction map, so as to better complete the reconstruction of the boundary area. Optionally, in this embodiment, in order to generate a high-quality reconstructed sample image with rich details, the network structure of the preset initial image reconstruction model can be a DeepEdgeResUNet network, the network structure of which is as follows: Figure 5aAs shown in the figure, the top layer of the DeepEdgeResUNet network is a long residual connection from input to output, which enables the network to directly learn to reconstruct the residual between the sample image and the first sample medical image, accelerating the convergence of the deep network. From top to bottom, the shallow image has a larger dimension and a larger resolution, and a dense connection is used to reduce information loss; the image dimension is smaller, the resolution is lower, and the information is less, so a sparse connection is used. In addition, the DeepEdgeResUNet network extensively uses residual blocks composed of convolution, BN batch normalization, and ReLU linear rectification functions, which solves the problem of gradient disappearance while improving network performance and ensuring network convergence. In order to avoid the impact of too many network parameters on generalization ability and running time, the DeepEdgeResUNet network specifically uses a depthwise separable residual block composed of depthwise separable convolution, BN batch normalization and ReLU linear rectification function. The use of the depthwise separable residual block greatly reduces the number of network parameters and running costs, making the network have strong fitting capabilities while being time-saving and lightweight.

[0075] In this embodiment, in order to further ensure the quantitative accuracy of the obtained reconstructed sample image, the first sample medical image, the first sample edge image, the second sample medical image and the second sample edge image can be subjected to 2.5D processing. The 2.5D processing refers to that when the initial image reconstruction model is trained, each training process is performed in an image block instead of in the entire volume of the input image. For example, 5 2D first sample medical images are input into the initial image reconstruction model to obtain 1 2D reconstructed sample image. Optionally, in this embodiment, the standardized first sample medical image and the processed second sample medical image can be randomly cropped respectively. The cropping size can be any fixed size that meets the requirements of the initial image reconstruction model and the image dimension, but it must be ensured that the positions of the image cropping correspond one to one. For example, the cropping size can be [64,64,5]. Then, corresponding to the 2.5D processing, the input of the initial image reconstruction model can be expressed as [64,64,5], the corresponding second sample medical image can be expressed as [64,64,1], and the input of the edge attention mechanism can be expressed as [64,64,10].

[0076] S504, training an initial image reconstruction model according to the sample edge prediction map, the second sample edge image, the reconstructed sample image and the second sample medical image to obtain an image reconstruction model.

[0077] Specifically, the computer device trains the initial image reconstruction model according to the sample edge prediction map, the second sample edge image, the reconstructed sample image, and the second sample medical image obtained above to obtain the image reconstruction model. Optionally, the computer device can obtain the value of the loss function of the initial image reconstruction model according to the sample edge prediction map, the second sample edge image, the reconstructed sample image, and the second sample medical image, and train the initial image reconstruction model according to the value of the loss function of the initial image reconstruction model, and determine the initial image reconstruction model corresponding to when the value of the loss function of the initial image reconstruction model reaches a stable value as the above image reconstruction model. Optionally, when training the initial image reconstruction model, the optimizer can be selected as the Adam optimizer, which can converge quickly and has good generalization ability. Optionally, the learning rate for the initial image reconstruction model training can use the learning rate range test (LR Range Test) technique to select the best learning rate. The process can be described as: first, set the learning rate to a very small value, then simply iterate the model and data several times, increase the learning rate after each iteration, and record the training loss each time, and then draw the LR Range Test graph. Generally, a rational LR Range Test graph contains three areas: in the first area, the learning rate is too small and the loss remains basically unchanged, in the second area, the loss decreases and converges quickly, and in the last area, the learning rate is so large that the loss begins to diverge. The best learning rate can be determined as the learning rate corresponding to the lowest point in the LR Range Test graph, and this best learning rate is used as the initial learning rate of the Adam optimizer.

[0078] In this embodiment, the computer device performs gradient calculation on the second sample image of the standard scanning time, and can obtain an accurate second sample edge image. According to the first sample medical image, the first edge image and the preset initial image reconstruction model, the sample edge prediction map and the reconstructed sample image can be obtained. Then, according to the sample edge prediction map, the second sample edge image, the reconstructed sample image and the second sample medical image, the initial image reconstruction model can be accurately trained, thereby improving the accuracy of the obtained image reconstruction model.

[0079] Figure 6 A flowchart of an image reconstruction method provided for another embodiment. This embodiment relates to a specific implementation process in which a computer device trains an initial image reconstruction model based on a sample edge prediction map, a second sample edge image, a reconstructed sample image, and a second sample medical image to obtain an image reconstruction model. Figure 6 As shown, based on the above embodiment, as an optional implementation manner, the above S504 includes:

[0080] S601, obtaining a value of a first loss function of an initial image reconstruction model according to a sample edge prediction image and a second sample edge image.

[0081] Specifically, the computer device obtains the value of the first loss function of the initial image reconstruction model based on the sample edge prediction map and the second sample edge image. Optionally, the computer device can compare the pixel value of the obtained sample edge prediction map with the pixel value of the second sample edge image to obtain the value of the first loss function of the initial image reconstruction model.

[0082] S602, obtaining a value of a second loss function of the initial image reconstruction model according to the pixel values ​​of the reconstructed sample image and the pixel values ​​of the second sample medical image.

[0083] Specifically, the computer device obtains the value of the second loss function of the initial image reconstruction model according to the obtained pixel values ​​of the reconstructed sample image and the pixel values ​​of the second sample medical image. Optionally, the computer device may obtain the value of the second loss function of the initial image reconstruction model according to the pixel values ​​of the reconstructed sample image, the pixel values ​​of the second sample medical image, and the formula loss(x i ,y i )=|x i -y i |, and obtain the value of the second loss function of the initial image reconstruction model, where x i Represents the pixel value of the reconstructed sample image, y i represents the pixel value of the second sample medical image, loss(x i ,y i ) represents the value of the second loss function of the initial image reconstruction model, where loss(x i ,y i ) is used to calculate the pixel-by-pixel intensity difference between the reconstructed sample image and the second sample medical image to ensure that the quantitative error between the reconstructed sample image and the second sample image is as small as possible.

[0084] S603, obtaining a value of a regional loss function of an initial image reconstruction model according to the mean value of each region of interest of the reconstructed sample image and the mean value of each region of interest of the second sample medical image.

[0085] Specifically, the computer device obtains the value of the regional loss function of the initial image reconstruction model according to the mean of each region of interest of the reconstructed sample image and the mean of each region of interest of the second sample medical image. Optionally, the computer device may obtain the value of the regional loss function of the initial image reconstruction model according to the mean of each region of interest of the reconstructed sample image, the mean of each region of interest of the second sample medical image, and the formula Get the value of the regional loss function of the initial image reconstruction model, where: Represents the mean value of each region of interest (ROI) of the reconstructed sample image, represents the mean of each region of interest (ROI) of the second sample medical image, i represents the index of each region of interest, mean represents the mean, and loss(x, y) represents the value of the regional loss function of the initial image reconstruction model, wherein loss(x, y) is used to calculate the relative error between each region of interest of the reconstructed sample image and each region of interest of the second sample medical image to ensure the quantitative accuracy of the reconstructed sample image.

[0086] S604, obtaining a value of a gradient loss function of an initial image reconstruction model according to the gradient amplitude of each pixel of the reconstructed sample image and the gradient amplitude of each pixel of the second sample medical image.

[0087] Specifically, the computer device obtains the value of the gradient loss function of the initial image reconstruction model according to the gradient amplitude of each pixel of the reconstructed sample image and the gradient amplitude of each pixel of the second sample medical image. Optionally, the computer device can obtain the value of the gradient loss function of the initial image reconstruction model according to the gradient amplitude of each pixel of the reconstructed sample image, the gradient amplitude of each pixel of the second sample medical image, and the formula loss(x Gi ,y Gi )=|G(x i )-G(y i )|, and obtain the value of the gradient loss function of the initial image reconstruction model, where loss(x Gi ,y Gi ) represents the value of the gradient loss function of the initial image reconstruction model, G(x i ) represents the gradient amplitude of each pixel of the reconstructed sample image, G(y i ) represents the gradient amplitude of each pixel of the second sample medical image, where loss(x Gi ,y Gi ) is used to calculate the gradient amplitude of each pixel of the reconstructed sample image and the gradient amplitude of each pixel of the second sample medical image to ensure that the obtained reconstructed sample image has rich detail information.

[0088] S605, training the initial image reconstruction model according to the sum of the value of the first loss function, the value of the second loss function, the value of the region loss function, and the value of the gradient loss function to obtain an image reconstruction model.

[0089] Specifically, the computer device trains the initial image reconstruction model according to the sum of the value of the first loss function, the value of the second loss function, the value of the regional loss function, and the value of the gradient loss function of the initial image reconstruction model, and determines the initial image reconstruction model corresponding to the sum of the value of the first loss function, the value of the second loss function, the value of the regional loss function, and the value of the gradient loss function of the initial image reconstruction model reaches a stable value as the above-mentioned image reconstruction model. Optionally, the computer device can also train the initial image reconstruction model according to the weighted sum of the value of the first loss function, the value of the second loss function, the value of the regional loss function, and the value of the gradient loss function of the initial image reconstruction model to obtain the above-mentioned image reconstruction model.

[0090] In this embodiment, the value of the first loss function of the initial image reconstruction model obtained by the computer device can ensure that the quantitative error between the obtained sample edge prediction map and the second sample edge image is as small as possible, the value of the second loss function can ensure that the quantitative error between the obtained reconstructed sample image and the second sample image is as small as possible, the value of the regional loss function can ensure the quantitative accuracy of the obtained reconstructed sample image, and the value of the gradient loss function can ensure that the obtained reconstructed sample image has rich detail information. Then, the computer device can accurately train the initial image reconstruction model according to the sum of the value of the first loss function, the value of the second loss function, the value of the regional loss function, and the value of the gradient loss function, thereby improving the accuracy of the obtained image reconstruction model.

[0091] It should be understood that although Figure 2-6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-6 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0092] Figure 7 FIG. 1 is a schematic diagram of the structure of an image reconstruction device provided by an embodiment. Figure 7 As shown, the device may include: a first acquisition module 10 , a first calculation module 11 and a reconstruction module 12 .

[0093] Specifically, the first acquisition module 10 is used to acquire a first medical image; the scanning time corresponding to the first medical image is less than a preset standard scanning time;

[0094] A first calculation module 11 is used to perform gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image;

[0095] The reconstruction module 12 is used to obtain a second medical image corresponding to a standard scanning time according to the first medical image, the edge image and a preset image reconstruction model.

[0096] The image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0097] On the basis of the above embodiment, optionally, the above reconstruction module 12 includes: a first acquisition unit and a second acquisition unit.

[0098] Specifically, the first acquisition unit is used to obtain a prediction map and an edge prediction map according to the first medical image, the edge image and the image reconstruction model; wherein the edge feature information included in the prediction map is less than the edge feature information included in the edge prediction map.

[0099] The second acquisition unit is used to obtain a second medical image according to the prediction map and the edge prediction map.

[0100] The image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0101] Based on the above embodiment, optionally, the above-mentioned first acquisition unit is specifically used to input the first medical image and the edge image into an image reconstruction model to obtain feature information of the first medical image; obtain a prediction map based on the feature information; and use an edge attention mechanism to combine the feature information and the edge image to obtain an edge prediction map.

[0102] The image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0103] On the basis of the above embodiment, optionally, the above device further includes: a standardization processing module.

[0104] Specifically, the standardization processing module is used to perform standardization processing on the first medical image according to the mean value of the pixels of the first medical image and the standard deviation of the pixels of the first medical image to obtain the first medical image after standardization processing;

[0105] The first calculation module 11 is specifically used to perform gradient calculation on the first medical image after the standardization process to obtain an edge image corresponding to the first medical image.

[0106] The image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0107] Based on the above embodiment, optionally, the above device further includes: a linear transformation processing module.

[0108] Specifically, the linear transformation processing module is used to perform linear transformation processing on the second medical image according to the mean value of the pixels of the first medical image and the standard deviation of the pixels of the first medical image to obtain a processed second medical image.

[0109] The image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0110] On the basis of the above embodiment, optionally, the above device further includes: a second calculation module, a third calculation module, a second acquisition module and a training module.

[0111] Specifically, the second calculation module is used to perform gradient calculation on the first sample medical image to obtain a first sample edge image; the first sample edge image is used to characterize edge information of the first sample medical image; the scanning time corresponding to the first sample medical image is less than the standard scanning time;

[0112] A third calculation module is used to perform gradient calculation on the second sample medical image to obtain a second sample edge image; the second sample edge image is used to characterize edge information of the second sample medical image; and the scanning time corresponding to the second sample medical image is the standard scanning time;

[0113] A second acquisition module is used to obtain a sample edge prediction map and a reconstructed sample image according to the first sample medical image, the first edge image and a preset initial image reconstruction model; the reconstructed sample image is an image of a standard scanning time length corresponding to the first sample image;

[0114] The training module is used to train the initial image reconstruction model according to the sample edge prediction map, the second sample edge image, the reconstructed sample image and the second sample medical image to obtain the image reconstruction model.

[0115] The image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0116] On the basis of the above embodiment, optionally, the above training module includes: a third acquisition unit, a fourth acquisition unit, a fifth acquisition unit, a sixth acquisition unit and a training unit.

[0117] Specifically, the third acquisition unit is used to obtain the value of the first loss function of the initial image reconstruction model according to the sample edge prediction image and the second sample edge image;

[0118] A fourth acquisition unit, used for obtaining a value of a second loss function of the initial image reconstruction model according to the pixel value of the reconstructed sample image and the pixel value of the second sample medical image;

[0119] A fifth acquisition unit, configured to obtain a value of a regional loss function of the initial image reconstruction model according to the mean value of each region of interest of the reconstructed sample image and the mean value of each region of interest of the second sample medical image;

[0120] A sixth acquisition unit, configured to obtain a value of a gradient loss function of an initial image reconstruction model according to a gradient amplitude of each pixel of the reconstructed sample image and a gradient amplitude of each pixel of the second sample medical image;

[0121] The training unit is used to train the initial image reconstruction model according to the sum of the value of the first loss function, the value of the second loss function, the value of the region loss function, and the value of the gradient loss function to obtain the image reconstruction model.

[0122] The image reconstruction device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0123] For the specific definition of the image reconstruction device, please refer to the definition of the image reconstruction method above, which will not be repeated here. Each module in the above-mentioned image reconstruction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0124] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0125] Acquiring a first medical image; wherein a scanning time corresponding to the first medical image is less than a preset standard scanning time;

[0126] Performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image;

[0127] A second medical image corresponding to the standard scanning time is obtained according to the first medical image, the edge image and a preset image reconstruction model.

[0128] The implementation principle and technical effect of the computer device provided in the above embodiment are similar to those of the above method embodiment, and will not be repeated here.

[0129] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0130] Acquiring a first medical image; wherein a scanning time corresponding to the first medical image is less than a preset standard scanning time;

[0131] Performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image;

[0132] A second medical image corresponding to the standard scanning time is obtained according to the first medical image, the edge image and a preset image reconstruction model.

[0133] The computer-readable storage medium provided in the above embodiment has similar implementation principles and technical effects as those of the above method embodiment, and will not be described in detail here.

[0134] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0135] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0136] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An image reconstruction method, characterized in that: The method comprises: Acquiring a first medical image; wherein a scanning time corresponding to the first medical image is less than a preset standard scanning time; Performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image; According to the first medical image, the edge image and a preset image reconstruction model, a second medical image corresponding to the standard scanning time is obtained; the image reconstruction model is obtained by training an initial image reconstruction model according to the sample edge prediction map, the second sample edge image, the reconstructed sample image and the second sample medical image; the sample edge prediction map and the reconstructed sample image are obtained according to the first sample medical image, the first sample edge image and the initial image reconstruction model, the scanning time corresponding to the first sample medical image is less than the standard scanning time, and the scanning time corresponding to the second sample medical image is the standard scanning time.

2. The method according to claim 1, characterized in that The step of obtaining the second medical image corresponding to the standard scanning time according to the first medical image, the edge image and a preset image reconstruction model includes: According to the first medical image, the edge image and the image reconstruction model, a prediction map and an edge prediction map are obtained; wherein the edge feature information included in the prediction map is less than the edge feature information included in the edge prediction map; The second medical image is obtained according to the prediction map and the edge prediction map.

3. The method according to claim 2, characterized in that The step of obtaining a prediction map and an edge prediction map according to the first medical image, the edge image and the image reconstruction model comprises: Inputting the first medical image and the edge image into the image reconstruction model to obtain feature information of the first medical image; According to the feature information, obtaining the prediction graph; The edge prediction map is obtained by combining the feature information and the edge image using an edge attention mechanism.

4. The method according to claim 1, characterized in that: Before performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image, the method further includes: performing standardization processing on the first medical image according to a mean value of pixels of the first medical image and a standard deviation of pixels of the first medical image to obtain a standardized first medical image; The performing gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image includes: Gradient calculation is performed on the first medical image after the standardization process to obtain an edge image corresponding to the first medical image.

5. The method according to claim 4, characterized in that After obtaining the second medical image corresponding to the standard scanning time according to the first medical image, the edge image and the preset image reconstruction model, the method further includes: According to the mean value of the pixels of the first medical image and the standard deviation of the pixels of the first medical image, a linear transformation process is performed on the second medical image to obtain a processed second medical image.

6. The method according to claim 1, characterized in that The training process of the image reconstruction model includes: Performing gradient calculation on the first sample medical image to obtain a first sample edge image; the first sample edge image is used to characterize edge information of the first sample medical image; Performing gradient calculation on the second sample medical image to obtain a second sample edge image; the second sample edge image is used to characterize edge information of the second sample medical image; According to the first sample medical image, the first sample edge image and the preset initial image reconstruction model, a sample edge prediction map and a reconstructed sample image are obtained; the reconstructed sample image is an image of a standard scanning time length corresponding to the first sample image; The initial image reconstruction model is trained according to the sample edge prediction map, the second sample edge image, the reconstructed sample image and the second sample medical image to obtain the image reconstruction model.

7. The method according to claim 6, characterized in that The step of training the initial image reconstruction model according to the sample edge prediction map, the second sample edge image, the reconstructed sample image and the second sample medical image to obtain the image reconstruction model comprises: Obtaining a value of a first loss function of the initial image reconstruction model according to the sample edge prediction map and the second sample edge image; Obtaining a value of a second loss function of the initial image reconstruction model according to the pixel value of the reconstructed sample image and the pixel value of the second sample medical image; Obtaining a value of a regional loss function of the initial image reconstruction model according to a mean value of each region of interest of the reconstructed sample image and a mean value of each region of interest of the second sample medical image; Obtaining a value of a gradient loss function of the initial image reconstruction model according to a gradient magnitude of each pixel of the reconstructed sample image and a gradient magnitude of each pixel of the second sample medical image; The initial image reconstruction model is trained according to the sum of the value of the first loss function, the value of the second loss function, the value of the region loss function, and the value of the gradient loss function to obtain the image reconstruction model.

8. An image reconstruction device, characterized in that: The device comprises: A first acquisition module is used to acquire a first medical image; the scanning time corresponding to the first medical image is less than a preset standard scanning time; A first calculation module, configured to perform gradient calculation on the first medical image to obtain an edge image corresponding to the first medical image; the edge image is used to represent edge information of the first medical image; A reconstruction module is used to obtain a second medical image corresponding to the standard scanning time according to the first medical image, the edge image and a preset image reconstruction model; the image reconstruction model is obtained by training an initial image reconstruction model according to a sample edge prediction map, a second sample edge image, a reconstructed sample image and a second sample medical image; the sample edge prediction map and the reconstructed sample image are obtained according to the first sample medical image, the first sample edge image and the initial image reconstruction model, the scanning time corresponding to the first sample medical image is less than the standard scanning time, and the scanning time corresponding to the second sample medical image is the standard scanning time.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images