Image processing method, electronic device, and computer readable storage medium

Abstract

The present application discloses an image processing method, an electronic device, and a computer readable storage medium. The method comprises: acquiring a multi-phase image collected at different times, wherein display content of the multi-phase image at least comprises a monitoring area of a target part of an object to be monitored; performing texture feature extraction on the multi-phase image to obtain a target texture feature of the multi-phase image; on the basis of the position relationship between the monitoring area and other areas in the multi-phase image, determining a target neural distance of the multi-phase image, wherein the other areas are used for representing areas of the target part other than the monitoring area; and on the basis of the target texture feature and the target neural distance, generating a risk index of the monitoring area, wherein the risk index is used for representing the probability that the monitoring area has a risk. The present application solves the technical problem in the related art of low accuracy of determining whether the monitoring area has a risk or not.

Description

Image processing method, electronic device, and computer-readable storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on July 20, 2023, with application number 202310896158.0 and application name “Image processing method, electronic device and computer-readable storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of image processing, and in particular to an image processing method, an electronic device, and a computer-readable storage medium. Background Art

[0003] At present, deep learning prediction models can usually be used to predict risks in the monitoring area of ​​the target part of the monitored object. However, due to the close distance between the monitoring area and other areas, the accuracy of risk prediction for the monitoring area using this method is low, resulting in the inability to accurately determine whether there is a risk in the monitoring area.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide an image processing method, an electronic device, and a computer-readable storage medium to at least solve the technical problem of low accuracy in determining whether a monitoring area is at risk in the related art.

[0007] According to one aspect of an embodiment of the present application, an image processing method is provided, comprising: acquiring multiple images acquired at different times, wherein the display content of the multiple images at least includes a monitoring area of ​​a target part of an object to be monitored; performing texture feature extraction on the multiple images to obtain target texture features of the multiple images; determining a target nerve distance of the multiple images based on a positional relationship between the monitoring area and other areas in the multiple images, wherein the other areas are used to characterize areas of the target part other than the monitoring area; and generating a risk index for the monitoring area based on the target texture features and the target nerve distance, wherein the risk index is used to characterize the probability that a risk exists in the monitoring area.

[0008] According to another aspect of an embodiment of the present application, an image processing method is also provided, including: responding to an input instruction acting on an operation interface, displaying multiple images acquired at different times on the operation interface, wherein the display content of the multiple images at least includes a monitoring area of ​​a target part of the object to be monitored; responding to an image processing instruction acting on the operation interface, displaying a risk indicator of the monitoring area on the operation interface, wherein the risk indicator is generated based on target texture features and target nerve distance of the multiple images, the target texture features are obtained by extracting texture features of the multiple images, and the target nerve distance is determined based on the positional relationship between the monitoring area and other areas in the multiple images.

[0009] According to another aspect of an embodiment of the present application, an image processing method is also provided, including: displaying multiple images acquired at different times on a presentation screen of a virtual reality (VR) device or an augmented reality (AR) device, wherein the display content of the multiple images at least includes a monitoring area of ​​a target part of an object to be monitored; performing texture feature extraction on the multiple images to obtain target texture features of the multiple images; determining a target nerve distance of the multiple images based on a positional relationship between the monitoring area and other areas in the multiple images, wherein the other areas are used to characterize areas of the target part other than the monitoring area; generating a risk indicator of the monitoring area based on the target texture features and the target nerve distance, wherein the risk indicator is used to characterize the probability of risk existing in the monitoring area; and driving the VR device or AR device to display the risk indicator.

[0010] According to another aspect of an embodiment of the present application, an image processing method is also provided, including: acquiring multiple images collected at different times by calling a first interface, wherein the first interface includes a first parameter, and the parameter value of the first parameter is the multiple images, and the display content of the multiple images at least includes the monitoring area of ​​the target part of the object to be monitored; performing texture feature extraction on the multiple images to obtain target texture features of the multiple images; determining the target nerve distance of the multiple images based on the positional relationship between the monitoring area and other areas in the multiple images, wherein the other areas are used to characterize the area of ​​the target part other than the monitoring area; generating a risk index of the monitoring area based on the target texture features and the target nerve distance, wherein the risk index is used to characterize the probability of risk existing in the monitoring area; outputting the risk index by calling a second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter is the risk index.

[0011] According to another aspect of the embodiments of the present application, a computer-assisted cancer prognosis method is provided, comprising:

[0012] Acquiring multiple medical images acquired at different times, wherein the display content of the multiple medical images at least includes a cancer region of a target site of the subject to be monitored;

[0013] Extracting texture features from the medical images of the plurality of periods to obtain target texture features of the medical images of the plurality of periods;

[0014] determining target nerve distances of the medical images in the plurality of phases based on a positional relationship between the cancer region and other regions in the medical images in the plurality of phases, wherein the other regions are used to represent regions of the target site other than the cancer region;

[0015] A risk index of the monitoring area is generated based on the target texture feature and the target nerve distance, wherein the risk index is used to characterize the probability that the cancer area has a risk.

[0016] According to another aspect of the embodiments of the present application, a computer-assisted pancreatic cancer prognosis method is provided, comprising:

[0017] Acquiring multiple medical images acquired at different times, wherein the display contents of the multiple medical images at least include a pancreatic cancer region of the subject to be monitored;

[0018] Extracting texture features from the medical images of the plurality of periods to obtain target texture features of the medical images of the plurality of periods;

[0019] determining target nerve distances of the medical images in the plurality of phases based on a positional relationship between the pancreatic cancer region and other regions in the medical images in the plurality of phases, wherein the other regions are used to represent regions outside the pancreatic cancer region;

[0020] A risk index of the monitoring area is generated based on the target texture feature and the target nerve distance, wherein the risk index is used to characterize the probability that the pancreatic cancer area has a risk.

[0021] According to another aspect of an embodiment of the present application, a computer-assisted cancer prognosis system is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to perform a computer-assisted cancer prognosis method, the method comprising:

[0022] Acquiring multiple medical images acquired at different times, wherein the display content of the multiple medical images at least includes a cancer region of a target site of the subject to be monitored;

[0023] Extracting texture features from the medical images of the plurality of periods to obtain target texture features of the medical images of the plurality of periods;

[0024] determining target nerve distances of the medical images in the plurality of phases based on a positional relationship between the cancer region and other regions in the medical images in the plurality of phases, wherein the other regions are used to represent regions of the target site other than the cancer region;

[0025] A risk index of the monitoring area is generated based on the target texture feature and the target nerve distance, wherein the risk index is used to characterize the probability that the cancer area has a risk.

[0026] According to another aspect of an embodiment of the present application, an electronic device is provided, including: a memory storing an executable program; and a processor for running the program, wherein any one of the above methods is executed when the program is running.

[0027] According to another aspect of an embodiment of the present application, a computer-readable storage medium is further provided, the computer-readable storage medium including a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the methods described above in claim 1 .

[0028] According to another aspect of an embodiment of the present application, a computer program product is further provided, comprising computer-executable instructions, which, when executed by a processor, implement the steps of any one of the above methods.

[0029] According to another aspect of the embodiments of the present application, a computer program is further provided, which implements the steps of any of the above methods when executed by a processor.

[0030] In an embodiment of the present application, a method is adopted in which multiple images acquired at different times are acquired; texture features of the multiple images are extracted to obtain target texture features of the multiple images; the target nerve distance of the multiple images is determined based on the positional relationship between the monitoring area and other areas in the multiple images; and a risk index of the monitoring area is generated based on the target texture features and the target nerve distance. The risk index of the monitoring area is generated based on the target texture features of the monitoring area in the multiple images acquired at different times and the target nerve distance between the monitoring area and other areas. In this way, the contact situation between the monitoring area and other areas is fully considered in the risk prediction process of the monitoring area, thereby improving the accuracy of the determined risk index, and further solving the technical problem of low accuracy in determining whether there is a risk in the monitoring area in the related art.

[0031] It is easy to notice that the above general description and the following detailed description are merely for the purpose of exemplifying and explaining the present application, and do not constitute a limitation of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0033] FIG1 is a schematic diagram of a hardware environment of a virtual reality device according to an image processing method according to an embodiment of the present application;

[0034] FIG2 is a structural block diagram of a computing environment of an image processing method according to an embodiment of the present application;

[0035] FIG3 is a flowchart of an image processing method according to Example 1 of the present application;

[0036] FIG4 is a schematic diagram of an image processing process according to Example 1 of the present application;

[0037] FIG5 is a schematic diagram of an image processing result according to Example 1 of the present application;

[0038] FIG6 is a flowchart of an image processing method according to Embodiment 2 of the present application;

[0039] FIG7 is a flowchart of an image processing method according to Example 3 of the present application;

[0040] FIG8 is a flowchart of an image processing method according to Embodiment 4 of the present application;

[0041] FIG9 is a structural block diagram of an image processing device according to Embodiment 5 of the present application;

[0042] FIG10 is a structural block diagram of an image processing device according to Embodiment 6 of the present application;

[0043] FIG11 is a structural block diagram of an image processing device according to Embodiment 7 of the present application;

[0044] FIG12 is a structural block diagram of an image processing device according to Embodiment 8 of the present application;

[0045] Figure 13 is a structural block diagram of an electronic device according to embodiment 12 of the present application. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0047] It should be noted that 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 are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0048] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretations:

[0049] Multi-phase CT: Multi-phase Computed Tomography, used to obtain multi-phase images including the monitoring area.

[0050] PDAC: Pancreatic ductal adenocarcinoma, pancreatic ductal adenocarcinoma, also known as pancreatic cancer.

[0051] CNN: Convolutional Neural Network, convolutional neural network.

[0052] Neural distance: refers to the distance between a point on the boundary of the monitoring area and a point on the boundary of other areas near the monitoring area. It can be used to evaluate the relationship between the monitoring area and other areas.

[0053] Texture perception model: It can be used to combine local information and global information in multi-phase images to improve the extraction of texture features in multi-phase images.

[0054] Cancer prognosis: A prediction of the future course of a cancer patient's condition. Prognosis can include predictions of patient survival time, likelihood of disease recurrence, treatment effectiveness, and quality of life.

[0055] Example 1

[0056] According to an embodiment of the present application, an image processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0057] FIG1 is a schematic diagram of the hardware environment of a virtual reality device according to an image processing method according to an embodiment of the present application. As shown in FIG1 , a virtual reality device 104 is connected to a terminal 106, which is connected to a server 102 via a network. The virtual reality device 104 is not limited to a virtual reality helmet, virtual reality glasses, or an all-in-one virtual reality device. The terminal 104 is not limited to a PC, mobile phone, or tablet computer. The server 102 can be a server corresponding to a media file operator. The network includes, but is not limited to, a wide area network, a metropolitan area network, or a local area network.

[0058] Optionally, the virtual reality device 104 of this embodiment includes: a memory, a processor, and a transmission device. The memory is used to store an application program, which can be used to execute the following: acquiring multiple images acquired at different times, wherein the display content of the multiple images at least includes a monitoring area of ​​a target part of the monitored object; extracting texture features from the multiple images to obtain target texture features of the multiple images; determining target nerve distances of the multiple images based on the positional relationship between the monitoring area and other areas in the multiple images, wherein the other areas are used to represent areas of the target part other than the monitoring area; and generating a risk index for the monitoring area based on the target texture features and the target nerve distance, wherein the risk index is used to represent the probability of the presence of risk in the monitoring area. This solves the technical problem of low accuracy in determining whether a monitoring area has risk in related technologies, thereby achieving the purpose of improving the accuracy of monitoring whether a monitoring area has risk.

[0059] The terminal of this embodiment can be used to display multiple images of the monitoring area collected at different times, target texture features of the multiple images, the positional relationship between the monitoring area and other areas in the multiple images, risk indicators of the monitoring area, and other information on the presentation screen of a virtual reality (VR) device or an augmented reality (AR) device, and send a display instruction to the virtual reality device 104. After receiving the display instruction, the virtual reality device 104 displays it at the target delivery location.

[0060] Optionally, the virtual reality device 104 of this embodiment includes an eye-tracking HMD (Head Mount Display) and an eye-tracking module, which function similarly to those in the aforementioned embodiment. Specifically, the screen in the HMD displays real-time images, and the eye-tracking module in the HMD captures the real-time trajectory of the user's eye movements. The terminal of this embodiment uses a tracking system to obtain the user's position and motion information in real three-dimensional space, and calculates the three-dimensional coordinates of the user's head in virtual three-dimensional space, as well as the user's field of view in the virtual three-dimensional space.

[0061] The hardware structure block diagram shown in Figure 1 can be used not only as an exemplary block diagram of the above-mentioned AR / VR device (or mobile device), but also as an exemplary block diagram of the above-mentioned server. In an optional embodiment, Figure 2 shows an embodiment of using the AR / VR device (or mobile device) shown in Figure 1 as a computing node in the computing environment 201 in a block diagram. Figure 2 is a structural block diagram of a computing environment according to an embodiment of the present application. As shown in Figure 2, the computing environment 201 includes multiple (210-1, 210-2, ..., shown in the figure) computing nodes (such as servers) running on a distributed network. Different computing nodes contain local processing and memory resources, and end users 202 can remotely run applications or store data in the computing environment 201. Applications can be provided as multiple services 220-1, 220-2, 220-3 and 220-4 in the computing environment 201, representing services "A", "D", "E" and "H" respectively.

[0062] End user 202 can provide and access services through a web browser or other software application on a client. In some embodiments, the provisioning and / or request of end user 202 can be provided to the ingress gateway 230. The ingress gateway 230 may include a corresponding agent to handle the provisioning and / or request for services (one or more services provided in the computing environment 201).

[0063] Services are provided or deployed based on various virtualization technologies supported by the computing environment 201. In some embodiments, services can be provided based on virtual machine (VM)-based virtualization, container-based virtualization, and / or similar methods. Virtual machine-based virtualization can simulate a real computer by initializing a virtual machine, executing programs and applications without directly accessing any actual hardware resources. While virtual machines virtualize machines, container-based virtualization can start containers to virtualize the entire operating system (OS) so that multiple workloads can run on a single operating system instance.

[0064] In one embodiment based on container virtualization, several containers of a service can be assembled into a Pod (e.g., a Kubernetes Pod). For example, as shown in Figure 2, service 220-2 can be equipped with one or more Pods 240-1, 240-2, ..., 240-N (collectively referred to as Pods). The Pod may include a proxy 245 and one or more containers 242-1, 242-2, ..., 242-M (collectively referred to as containers). One or more containers in the Pod process requests related to one or more corresponding functions of the service, and the proxy 245 generally controls network functions related to the service, such as routing, load balancing, etc. Other services can also be equipped with similar Pods.

[0065] During operation, executing a user request from end user 202 may require invoking one or more services in computing environment 201. Executing one or more functions of one service may require invoking one or more functions of another service. As shown in FIG2 , service "A" 220-1 receives a user request from end user 202 from ingress gateway 230. Service "A" 220-1 may invoke service "D" 220-2, and service "D" 220-2 may request service "E" 220-3 to execute one or more functions.

[0066] This computing environment can be a cloud computing environment, where resource allocation is managed by the cloud service provider, allowing for feature development without having to worry about implementing, adjusting, or scaling servers. This computing environment allows developers to execute code in response to events without building or maintaining complex infrastructure. Services can be partitioned to perform a set of functions that can scale independently and automatically, rather than scaling a single hardware device to handle the potential load.

[0067] In the above operating environment, the present application provides an image processing method as shown in Figure 3. It should be noted that the image processing method of this embodiment can be executed by the mobile terminal of the embodiment shown in Figure 1. Figure 3 is a flow chart of an image processing method according to Example 1 of the present application. As shown in Figure 3, the method may include the following steps:

[0068] Step S302: Acquire multiple images collected at different times.

[0069] The display content of the multi-phase image at least includes the monitoring area of ​​the target part of the object to be monitored.

[0070] The monitoring object may refer to an animal whose tissues or organs may develop lesions, such as humans, cats, hamsters, and the like. The monitoring area of ​​the target site may refer to an area of ​​the tissue or organ that may develop lesions, such as a tumor area on the pancreas. The multi-phase image may refer to image acquisition of the monitoring area at different times. For example, the monitoring area may be scanned and imaged at different times by tomography or magnetic resonance imaging to acquire multi-phase images of the monitoring area at different times.

[0071] Taking into account that it may take a long time for the target part to develop a lesion, a single or multiple images of the monitoring area obtained in a short period of time may not be able to accurately determine whether a lesion has occurred in the monitoring area, as well as the corresponding lesion conditions, such as whether a tumor has occurred, the trend of tumor lesions, etc. Therefore, in an optional scheme of this embodiment, in order to accurately determine whether a lesion has occurred in the monitoring area of ​​the target part, and whether there are risks, such as worsening of the severity of the tumor, spread of the tumor area, etc., the image processing system can first obtain the above-mentioned multi-phase images including the monitoring area collected at different times, thereby avoiding the limitations of the lesion conditions of the monitoring area reflected by a single-phase image, resulting in poor accuracy in determining whether there are risks in the monitoring area.

[0072] In an optional solution of this embodiment, the multi-phase images include at least images of a non-contrast phase, an early development phase, and a current phase. For example, in the case of a pancreatic cancer monitoring area, the multi-phase images include at least images of a non-contrast phase, a pancreatic phase, and a portal vein phase.

[0073] Step S304: extracting texture features from the multi-period images to obtain target texture features of the multi-period images.

[0074] The above-mentioned target texture features can be texture features obtained by fusing the global texture features and local texture features presented by the monitoring area, wherein the local texture features can refer to the texture features of the monitoring area, which can include but are not limited to: color, texture, shape, edge, corner point and other features of the monitoring area; the global texture features can refer to the texture features of the entire image in multiple images, such as the texture features of the target part, the texture features of the area outside the target part, etc.

[0075] For example, if the monitored area is the PDAC area, the corresponding other areas may be the areas where the blood vessels around the pancreas are located. The corresponding local texture features may refer to the color, texture, shape, edge, corner points and other features of the PDAC area. The corresponding global texture features may refer to the color, texture, shape, edge, corner points and other features of the pancreas and the blood vessels around the pancreas.

[0076] In an optional scheme of this embodiment, considering that one of the main ways to determine whether there is a risk in the monitoring area is based on the image effects presented by the monitoring area, such as image texture, therefore, in order to improve the accuracy of determining whether there is a risk in the monitoring area, the image processing system can, after acquiring multiple images at different times, extract texture features from the multiple images to determine the target texture features of the above multiple images.

[0077] In an alternative embodiment of this embodiment, when extracting texture features from multi-phase images to obtain target texture features, it is considered that in areas other than the target site and target site of the monitoring region, there may be a large number of important tissues and organs. For example, in areas other than the PDAC region, there may be a large number of important blood vessels on and around the pancreas. These important tissues and organs may have a certain impact on the monitoring of the monitoring region. For example, if the color of the blood vessels is similar to that of the PDAC region, it may lead to a misjudgment of PDAC spread. Furthermore, it is considered that the monitoring region may also affect these important tissues and organs when it is diseased. For example, the PDAC region may invade the blood vessels around the pancreas. Therefore, to ensure the accuracy of determining whether the monitoring region is at risk, when extracting texture features from multi-phase images, in addition to monitoring the monitoring region based solely on the texture features presented by the monitoring region, that is, extracting local texture features of the monitoring region, the image processing system may also monitor the texture presented by other areas of the monitoring region, that is, extracting global texture features. The local texture features and the global texture features are then fused to obtain the target texture features, thereby ensuring the accuracy of determining whether the monitoring region is at risk based on the target texture features.

[0078] Step S306 , determining the target nerve distance of the multi-phase image based on the positional relationship between the monitoring area and other areas in the multi-phase image.

[0079] Among them, the other areas are used to represent the areas of the target part other than the monitoring area.

[0080] The target nerve distance may refer to the distance between the surface of the monitoring area and the surface of other areas. For example, if the monitoring area is a PDAC area, the target nerve distance may refer to the distance between the edge of the monitoring area and the blood vessels around the pancreas.

[0081] In an optional solution of this embodiment, considering that other regions may affect the accuracy of prognostic prediction for the monitored area, for example, there are many important blood vessels around the pancreas, which are close to the PDAC area. When resecting the PDAC area, there may be mis-resection, which may have a negative impact on the patient. Therefore, in order to accurately predict the prognosis of the monitored area, in addition to directly using the aforementioned target texture features to determine whether the monitored area is at risk, the distance between the monitored area and other areas in multiple image phases, i.e., the aforementioned target nerve distance, can be further combined to determine whether the monitored area is at risk, thereby improving the accuracy of the determination result.

[0082] In an optional solution of this embodiment, the target nerve distances corresponding to different images can be determined based on the positional relationship between the monitoring area and other areas in multiple images, such as the relative position, structural connection and other information between the aforementioned monitoring area and other areas.

[0083] Step S308: Generate a risk index for the monitoring area based on the target texture features and the target nerve distance.

[0084] Among them, the risk index is used to characterize the probability of risk existing in the monitoring area.

[0085] The above-mentioned risk indicators may refer to whether there is a risk in the monitoring area, and the probability of the risk existing. Generally, the range of the above-mentioned risk indicators may be determined as 0-1. The larger the risk indicator, the more likely the risk will occur in the monitoring area, and the greater the negative impact of the lesions in the monitoring area on the monitored object.

[0086] In an optional solution of this embodiment, the risk index of the monitoring area can be determined based on the target texture features and target nerve distances determined above. For example, if the target texture features indicate that the lesion condition in the monitoring area is more severe and the target nerve distance is shorter, the corresponding risk index is higher. By utilizing the target texture features and target nerve distances corresponding to the monitoring area in the above-mentioned multi-phase images, the image processing system can quickly determine the risk index of the monitoring area, eliminating the need for staff to repeatedly compare the textures presented by the monitoring area in the multi-phase images. At the same time, it avoids the situation where the staff cannot accurately observe the changes in the monitoring area due to the small changes in the texture features presented by the monitoring area at different times, thereby reducing the occurrence of misjudgments and reducing the work pressure of the staff.

[0087] In an embodiment of the present application, a method is adopted in which multiple images acquired at different times are acquired; texture features of the multiple images are extracted to obtain target texture features of the multiple images; the target nerve distance of the multiple images is determined based on the positional relationship between the monitoring area and other areas in the multiple images; and a risk index of the monitoring area is generated based on the target texture features and the target nerve distance. The risk index of the monitoring area is generated based on the target texture features of the monitoring area in the multiple images acquired at different times and the target nerve distance between the monitoring area and other areas. In this way, the contact situation between the monitoring area and other areas is fully considered in the risk prediction process of the monitoring area, thereby improving the accuracy of the determined risk index, and further solving the technical problem of low accuracy in determining whether there is a risk in the monitoring area in the related art.

[0088] In an embodiment of the present application, texture feature extraction is performed on multiple images to obtain target texture features of the multiple images, including: feature extraction on the images to obtain initial texture features of the images; and using at least one texture perception model to fuse global information and local information in the initial texture features to obtain target texture features.

[0089] The initial texture features can refer to the texture features of the monitoring area and other areas obtained by feature extraction from the image, or can be the global texture features of the image. The global information can refer to the information between the aforementioned monitoring area and other areas, such as the texture information between the pancreas and the surrounding blood vessels. The local information can refer to the information of the aforementioned monitoring area itself, such as the texture information of the PDAC area. The texture perception model can be a mode for downsampling the initial texture features and processing the downsampling results using an attention mechanism. The texture perception model includes at least a CNN convolutional neural network and a Transformer network.

[0090] In an optional scheme of this embodiment, the number of the above-mentioned texture perception models is at least 1. The more texture perception models there are, the higher the accuracy of the target texture features obtained, and the corresponding accuracy of determining whether there is a risk in the monitoring area is higher, but the efficiency is lower. Therefore, considering the efficiency of determining whether there is a risk in the monitoring area, the number of the above-mentioned texture perception models can be set to 3.

[0091] In an optional solution of this embodiment, the image processing system can first use a preset feature extraction module to extract features from the multi-period image to determine the initial texture features of the monitoring area in the image, and then use at least one of the above-mentioned texture perception models to downsample the initial texture features to obtain the above-mentioned global information and local information in the initial texture features, and then use the attention mechanism to process the global information and local information to obtain the above-mentioned target texture features. It should be noted that the process of obtaining the target texture features is a process performed by a single texture perception model. If there are multiple texture perception models, for example, the number of texture perception models is set to 3, then the target texture features corresponding to the previous texture perception model need to be used as the initial texture features of the next texture perception model, and the process of obtaining the target texture features is repeated multiple times to improve the accuracy of the target texture features finally obtained.

[0092] In an optional solution of this embodiment, the feature extraction module for extracting initial texture features includes at least: a 5×5×5 convolution layer and a 3×3×3 convolution layer connected in sequence.

[0093] In an embodiment of the present application, at least one texture perception model block is used to fuse the global information and local information in the initial texture features to obtain the target texture features, including: using the convolutional neural network module in the texture perception model to downsample the initial texture features to obtain the local texture features of the image; using the self-attention module in the texture perception model to perform attention processing on the local texture features to obtain the target texture features of the image.

[0094] The above-mentioned convolutional neural network module can be a module for capturing local information from initial texture features, such as the local texture features of the monitoring area in multiple images. The above-mentioned self-attention module can be a module for capturing the dependencies between different local texture features and obtaining target texture features, which can achieve the purpose of fusing local information and global information.

[0095] In an optional scheme of this embodiment, in the process of using at least one texture perception module to process the initial texture features to obtain the target texture features, the image processing system can first use the convolutional neural network module in the texture perception model to downsample the aforementioned extracted initial texture features to obtain the local texture features of the image, and then use the self-attention module in the texture perception module to perform self-attention processing on the local texture features to obtain the above-mentioned target texture features.

[0096] In an embodiment of the present application, a convolutional neural network module in a texture perception model is used to downsample the initial texture features, and the local texture features of the image include: using the first convolutional layer in the convolutional neural network module to capture the first local information in the initial texture features; using the second convolutional layer in the convolutional neural network module to map the first local information to a preset space to obtain a first mapped texture feature; using the third convolutional layer in the convolutional neural network module to restore the mapped texture features to the original space corresponding to the initial texture features to obtain a restored texture feature; and using the normalization layer in the convolutional neural network module to normalize the restored texture features to obtain a local texture feature.

[0097] The dimension of the preset space is greater than the dimension of the original space. The first convolution layer in the convolutional neural network module may refer to a convolution layer for capturing the first local information of each of the monitoring area and other areas from the initial texture features, such as the texture information of each of the monitoring area and other areas, which may be a 3×3×3 structure. The second convolution layer may refer to a convolution layer for mapping the captured first local information to a high-dimensional preset space to obtain a hidden feature that can be encoded, which may be a 1×1×1 structure. The third convolution layer may refer to a convolution layer for restoring the encoded hidden feature to obtain a restored texture feature. The normalization layer may be a convolution layer for normalizing the restored texture feature to obtain a local texture feature with higher precision.

[0098] In an optional scheme of this embodiment, in the process of downsampling the initial texture features using a convolutional neural network to obtain local texture features, in order to ensure the accuracy of the obtained local texture features, the image processing system can first use the first convolution layer in the convolutional neural network module to capture the local information of the above-mentioned monitoring area and other areas from the initial texture features, that is, the above-mentioned first local information. In order to improve the efficiency of capturing the first local information, when capturing the first local information, the initial texture features of the initial multi-period images can be divided into multiple image blocks, and then the corresponding first local information can be captured from the corresponding initial texture features based on the multiple image blocks.

[0099] After capturing the first local information, the image processing system can use the second convolution layer in the convolutional neural network module to map and encode the first local information into a high-dimensional preset space to obtain the corresponding hidden feature, that is, the first mapped texture feature mentioned above, with the first local information before mapping as F i ∈R H×W×D×C For example, the first mapped texture feature after mapping can be H is the height of the image block, W is the width of the image block, D is the depth of the image block, and C is the dimension of the image block. l >C.

[0100] After obtaining the first mapped texture feature, the image processing system can reuse the third convolution layer in the convolutional neural network module to restore the first mapped texture feature to the restoration space where the first local information is located to obtain the restored texture feature, that is, the above-mentioned restored texture feature, and finally use the normalization layer in the convolutional neural network module to normalize the restored texture feature to obtain the above-mentioned local texture feature with higher accuracy.

[0101] In an embodiment of the present application, a self-attention module in a texture perception model is used to perform attention processing on local texture features to obtain target texture features of an image, including: using a first convolutional layer in the self-attention module to capture second local information in the local texture features; using a second convolutional layer in the self-attention module to map the second local information to a preset space to obtain a second mapped texture feature; using the self-attention layer in the self-attention module to perform self-attention processing on the second mapped texture feature to obtain a self-attention texture feature; using a feedforward layer in the self-attention module to perform feature interaction on the self-attention texture feature to obtain an interactive texture feature; and using a removal layer in the self-attention module to perform feature fusion on the interactive texture feature to obtain a target texture feature.

[0102] Similar to the first and second convolutional layers in the aforementioned convolutional neural network module, the first convolutional layer in the self-attention module can be a convolutional layer for capturing second local information from local texture features, such as texture information of other regions, and can have a 3×3×3 structure. The second local information can be local information of the initial texture features. The second convolutional layer can be a convolutional layer for mapping the second local information to a high-dimensional preset space to obtain hidden features that can be encoded, and can have a 1×1×1 structure. The self-attention layer can be used to perform self-attention processing on hidden features to obtain self-attention texture features that can express the dependencies between different hidden features. The feedforward layer can be used to interactively process the self-attention texture features to obtain visual and interpretable interactive texture features. The removal layer can be a convolutional layer for deleting and fusing interactive texture features to obtain target texture features with higher accuracy.

[0103] In an optional scheme of this embodiment, in the process of using the self-attention module to process local texture features and obtain target texture features, in order to improve the accuracy of the obtained target texture features, the image processing system can first use the first convolution layer in the above-mentioned self-attention module to capture the local information of the monitoring area and other areas from the above-mentioned normalized local texture features, that is, the above-mentioned second local information, and then use the second convolution layer in the self-attention module to encode and map the second local information to a high-dimensional preset space to obtain the corresponding hidden feature, that is, the above-mentioned second mapped texture feature, and then use the self-attention layer in the self-attention module to perform self-attention processing on the second mapped texture feature to obtain the corresponding self-attention texture feature, and finally use the feedforward layer in the self-attention module to interactively process the self-attention texture feature, so as to obtain an interactive texture feature that can intuitively express and facilitate the understanding of the self-attention texture feature, and use the removal layer in the self-attention module to further delete and fuse the interactive texture feature, so as to obtain a target texture feature with higher accuracy.

[0104] In an embodiment of the present application, at least one texture perception model is used to fuse the global information and local information in the initial texture features to obtain the target texture features, including: using at least one texture perception model to fuse the global information and local information in the initial texture features to obtain the output texture features of the image; performing cross-attention processing on the output texture features of multiple-period images to obtain cross-attention features; and splicing the output texture features and cross-attention features of multiple-period images to obtain the target texture features.

[0105] The output texture features may be generated by dividing the hidden features in the aforementioned preset space, i.e., the second mapped texture features, and processing the divided hidden features through the aforementioned self-attention layer and feedforward layer, i.e., the output features, i.e., the interactive texture features. In an optional solution of this embodiment, the second mapped texture features may be divided into multiple non-overlapping 3D (3-dimensional) feature blocks according to preset height, width, and depth to obtain the output texture features.

[0106] In an optional solution of this embodiment, the divided multiple non-overlapping 3D feature blocks can be the same as the aforementioned image blocks, and the expression form of the 3D feature blocks can be F u ∈R V×N×C , where V represents the volume of the 3D feature block, N represents the number of 3D feature blocks, and C represents the dimension of the second mapped texture feature. The corresponding output texture feature can be expressed in the form of F O ∈R D×nC, where D represents the depth of the 3D feature block and n represents the number of texture-aware models.

[0107] The cross-attention feature can refer to the attention feature obtained by extracting cross-modal information from the output texture features of each of the multiple images and processing the cross-modal information using an additional mask, wherein the additional mask can be expressed in the form of M∈{0,-∞} nC×nC , where n represents the number of texture perception models, C represents the dimension of the output texture features, and the cross-attention features can be expressed as:

[0108] F cross =Softmax(QK T +M)V;

[0109] Among them, F cross represents the output texture features, Q, K, and T are the query matrix, key matrix, and value matrix obtained by linearly projecting the aforementioned output texture features.

[0110] In an optional scheme of this embodiment, when determining the target texture feature, the image processing system can also use the above-mentioned at least one texture perception model to fuse the global information and local information in the initial texture feature, so as to obtain the above-mentioned output texture feature, and then extract the cross-modal information of each of the multiple images from the output texture features of each of the multiple images, and perform cross-attention processing on the cross-modal information to obtain the above-mentioned cross-attention feature, and finally splice the output texture feature and the cross-attention feature. For example, after the output texture feature and the cross-attention feature are connected in series, the preset evaluation aggregation layer is used to splice the connected features to obtain the above-mentioned target texture feature.

[0111] In an embodiment of the present application, cross-attention processing is performed on the output texture features of multiple-period images to obtain cross-attention features, including: using a cross-attention module to perform cross-attention processing on the output texture features of images from different periods to obtain cross-attention features.

[0112] In an optional scheme of this embodiment, a preset cross-attention module can be used to extract respective cross-modal information from the output texture features of images of different periods, and the cross-modal information can be used to perform cross-attention processing on the output texture features to obtain the above-mentioned cross-attention features.

[0113] In an embodiment of the present application, based on the positional relationship between the monitoring area and other areas in the multi-phase image, the target neural distance of the multi-phase image is determined, including: performing image segmentation on the image to obtain the image segmentation result, wherein the segmentation result includes at least: the monitoring area and other areas; based on the segmentation result, determining a first point set located at the boundary of the monitoring area, and a second point set located at the boundary of the other areas; determining a first subset of the first point set that meets a preset condition, and a second subset of the second point set that meets the preset condition; performing cross-attention processing on the first subset and the second subset to obtain the target neural distance.

[0114] The first point set may refer to a point set obtained by sampling the boundary of the monitoring area, and the second point set may refer to a point set obtained by sampling the boundary of other areas.

[0115] In an optional solution of this embodiment, when determining the target nerve distance between the monitoring area and other areas, the image processing system can first use a preset image segmentation module, such as the nnUet model (an image segmentation model), to perform image segmentation processing on the image, thereby obtaining the respective boundaries of the monitoring area and other areas in the image, wherein the other areas may include a variety of different types of blood vessels, such as the portal vein and splenic vein, the superior mesenteric artery, the superior mesenteric vein, and the celiac duct. After obtaining the segmentation results, the image processing system can determine the above-mentioned first point set from the boundary of the monitoring area in the segmentation results, and determine the above-mentioned second point set from the boundary of the other areas, such as the above-mentioned blood vessels.

[0116] X represents a point on the boundary of the monitoring area, and Y represents the boundary of other areas. For example, the distance from the boundary of the monitoring area to the boundary of other areas can be expressed as:

[0117] by represents a point in the first set of points determined from the points on the boundary of the monitoring area, The distances between the points in the first set and the boundaries of other regions, and the distances between the points in the second set and the boundaries of the monitoring region, can be expressed as follows:

[0118] Then, the image processing system determines a first subset from the first point set and a second subset from the second point set according to a preset condition, wherein the preset condition may refer to determining a preset number of points from the point set that are closest to the corresponding boundary, for example, from the above distance The smallest 20 points are selected to construct the corresponding subset. The other boundary can refer to the boundary of another area in the area where the point is located. For example, if the point is in the monitoring area, the other boundary can refer to the boundary corresponding to the other area. Finally, cross-attention processing is performed on multiple points in the first subset and the second subset to obtain the above-mentioned target neural distance.

[0119] In an embodiment of the present application, determining a first subset of the first point set that satisfies a preset condition and a second subset of the second point set that satisfies a preset condition includes: sampling the first point set to obtain a first sampling point set, and sampling the second point set to obtain a second sampling point set; determining a preset number of first sampling points in the first sampling point set that are closest to the second sampling point set to obtain the first subset; and determining a preset number of second sampling points in the second sampling point set that are closest to the first sampling point set to obtain the second subset.

[0120] In an optional solution of this embodiment, in the process of determining the first subset and the second subset, further sampling may be performed on the first point set to obtain a corresponding first sampling point set, and further sampling may be performed on the second point set to obtain a corresponding second sampling point set. Then, a preset number of first sampling points closest to the second sampling point set may be determined from the first sampling point set to construct the above-mentioned first subset. Simultaneously, a preset number of second sampling points closest to the first sampling point set may be determined from the second sampling point set to construct the above-mentioned second subset.

[0121] by Represents the points in the first subset, with Represents the points in the second subset, and the corresponding first subset can be expressed as:

[0122] Among them, K represents the number of points in the first subset.

[0123] The second subset can be expressed as:

[0124] According to the sampling points in the first subset and the sampling points in the second subset, the target neural distance can be expressed as:

[0125] In an embodiment of the present application, a risk index of the monitoring area is generated based on the target texture features and the target nerve distance, including: extracting the structural relationship between the monitoring area and other areas in multiple images to obtain the structural features of the multiple images; splicing the target texture features, the target nerve distance and the structural features to obtain the splicing features; and generating the risk index based on the splicing features.

[0126] In an optional scheme of this embodiment, in the process of generating the risk index of the monitoring area using the target texture features and the target nerve distance, in order to ensure the accuracy of the generated risk index, the image processing system can first use a preset structural analysis model, such as a 3D-CNN model, to extract the structural relationship between the monitoring area and other areas in the multi-phase image, thereby obtaining the structural features of the multi-phase image, such as the connection relationship between the blood vessels in the monitoring area and other areas, and then splice the structural features with the aforementioned target texture features and target nerve distance to obtain the above-mentioned splicing features, and finally use the fully connected layer to generate the above-mentioned risk index based on the splicing features.

[0127] In an optional solution of this embodiment, when using the fully connected layer and splicing feature prediction to generate the above-mentioned risk indicator, the risk indicator can be adjusted by likelihood estimation as risk loss, thereby improving the accuracy of the final output risk indicator.

[0128] In order to facilitate understanding of the above-mentioned process of performing image processing on multiple phase images to obtain corresponding risk indicators, Figure 4 is a schematic diagram of an image processing process according to Example 1 of the present application, wherein 1 represents multiple phase images collected at different times, taking pancreatic cancer as an example, 11 represents images of the non-contrast phase, 12 represents images of the pancreatic phase, 13 represents images of the portal vein phase, 2 represents the process of performing feature extraction on multiple phase images to obtain target texture features, 21 represents a feature extraction module for extracting initial texture features, 22 represents a texture perception model for obtaining target texture features, 221 represents a convolutional neural network module, 222 represents a self-attention module, 23 represents an output layer feature, 24 represents a cross-attention feature, Block 1, 2, 3 represents a texture perception model, Block4 represents a cross-processing module, Block7 represents a self-attention layer, Block8 represents a feedforward layer, Block9 represents a removal layer, 3 represents a distance determination module for determining the target neural distance, 31 represents an image segmentation result of image segmentation of a multi-period image, 32 represents a structural feature of a multi-period image, 33 represents a subset determination module for obtaining a first subset and a second subset, 34 represents the target neural distance, Block5 represents a structural extraction module, Block6 represents a target neural distance determination module, 4 represents a spliced ​​feature obtained by splicing the target neural distance, target texture and features, and structural features, and 5 represents a risk indicator predicted based on the spliced ​​feature. Processing the multi-period image in the direction indicated by the arrow in FIG4 can improve the accuracy of the predicted risk indicator.

[0129] In an embodiment of the present application, a method for predicting the prognosis of pancreatic cancer is also provided, which includes: acquiring multiple medical images acquired at different times, wherein the display content of the multiple medical images at least includes pancreatic cancer tumors and blood vessels; performing texture feature extraction on the multiple medical images to obtain target texture features of the multiple medical images; determining the target nerve distance of the multiple medical images based on the positional relationship between the tumors and blood vessels in the multiple medical images; and determining the survival outcome of the pancreatic cancer based on the target texture features and the target nerve distance.

[0130] The above-mentioned pancreatic cancer is a cancer with a relatively high mortality rate at present. The above-mentioned multi-phase medical images may refer to images containing pancreatic cancer lesion areas, that is, images containing pancreatic cancer tumors and vascular areas, collected at different times. The above-mentioned pancreatic cancer tumor area corresponds to the above-mentioned monitoring area, and the above-mentioned vascular area corresponds to the above-mentioned other areas.

[0131] In an optional solution of this embodiment, since pancreatic cancer has a high mortality rate, being able to accurately predict pancreatic cancer survival outcomes is very important treatment information for patients or medical staff. Therefore, in order to improve the accuracy of the predicted pancreatic cancer survival outcomes, the prognosis prediction system needs to first obtain multi-phase medical images collected at different times, including pancreatic cancer tumor and blood vessel areas, and then perform texture feature extraction on the multi-phase medical images to obtain target texture features of the multi-phase medical images. At the same time, based on the positional relationship between the tumor and blood vessels in the multi-phase medical images, the target nerve distance of each of the multi-phase medical images is determined. Finally, the pancreatic cancer survival outcome is determined based on the target texture features and target nerve distance.

[0132] To demonstrate the feasibility of the above process, a multicenter study was conducted on PDAC patients in this application. The following is the research process and results:

[0133] Specifically, 1,070 PDAC patients were selected and divided into two groups. The first group, consisting of 892 patients, was studied for comparison at Center A. The second group, consisting of 178 patients, was independently tested at three additional centers: Centers B, C, and D. The multi-phase CT images used in this study included non-contrast, pancreatic, and portal venous phases. To improve the comparison, 340 patients from Center A were selected. Radiologists with 18 years of experience in pancreatic cancer diagnosis manually labeled PDAC masks on the multi-phase images of these 178 patients to generate comparison images. A self-learning model was then used to predict PDAC masks for the remaining patients' multi-phase images. The same annotators, mostly radiologists, then reviewed and adjusted the self-learning model to ensure the accuracy of the predictions. For independent testing studies in other centers, the same model, such as semi-supervised generation of other vessel mask segmentation models, was used to separately segment PDAC masks from multiple medical images of other patients.

[0134] In addition, in the implementation of the study, in order to improve the accuracy of the research results, nested 5-fold cross-validation was used, and the training data was enhanced by rotating the volume tumor in the axial direction and randomly selecting cropped areas with random displacements. In order to improve the efficiency of prediction, the output feature size was set to Ct = 64 for the texture perception model, the output feature size was set to Cs = 64 for the structure extraction model, and the output feature size was set to K = 32 for the neural distance. The batch size was set to 16, the maximum iteration was set to 1000 epochs, and during the training for testing, the model with better performance was selected based on the training results on the validation set. The environment selected was PyTorch 1.11 and the model was trained on a single NVIDIA 32G-V100 GPU.

[0135] Research process: First, the performance of the constructed texture perception model (TAT) was evaluated by comparing it with the ResNet18CNN backbone and the ViT transformer backbone. The evaluation results showed that the texture perception model was better at processing local and global information of the pancreas. At the same time, the performance of the cross-attention module was evaluated by comparing it with common methods such as LSTM and early fusion. The evaluation results showed that the processing results of the cross-attention module for the in-phase feature part and the cross-phase feature part were more reasonable than those of other methods. Secondly, the various parts of the image processing method shown in Figure 4 were evaluated, and the evaluation results can be shown in Table 1 below.

[0136] Table 1

[0137] Table 1 shows the evaluation results corresponding to the above-mentioned parts, among which the C index represents the risk indicator.

[0138] As can be seen in Table 1, the use of texture-aware and structure-extraction models can improve the risk index from 0.630 to 0.648, consistent with the finding that tumor invasion significantly impacts the survival rate of PDAC patients. Furthermore, to verify the clinically found correlation between risk indicators and nerve distance, a four-variable regression model using only the bevel distances between the tumor and four vessels, i.e., the target nerve distance, for prognostic prediction was used to verify the relationship between nerve distance and survival rate. This relationship is confirmed by the C-index of 0.611 in the third-to-last row of Table 1, indicating a certain correlation between nerve distance and risk indicators, which is consistent with clinical findings. This means that adding the step of measuring nerve distance can effectively improve the accuracy of the predicted risk indicator. The proposed nerve distance metric, which performs well on traditional surface distance metrics such as bevel distance, is effectively applicable to distinguishing the severity of PDAC, i.e., determining risk indicators.

[0139] Comparison: To further evaluate the performance of the constructed model, the constructed model can be compared with the latest depth prediction methods. The specific comparison results are shown in Table 2 below.

[0140] Table 2

[0141] As can be seen from Table 2, compared with various existing prediction methods, such as the 3DCNN-P model, the early fusion method, and the DeepCT-PDAC model, the prediction results of the C index and AUC index (Area Under Curve, area under the ROC curve) of the present application are closer to the disease situation.

[0142] To improve the performance of the model, this application modified the baseline deep learning model and used a single pancreatic stage or all three stages as input to build the network architecture. Currently, DeepCT-PDAC is the latest method using 3DCNN to consider tumor-related and tumor-vascular relationships. Compared with this method, the texture-aware model and structure extraction model proposed in this application to capture tumor growth patterns and tumor vascular involvement have been proven to be effective in nested 5-fold cross-validation and multi-entry independent test sets with better performance.

[0143] Table 3

[0144] Table 3 uses univariate and multivariate Cox proportional hazard models to evaluate the effectiveness of the target texture features of this application and clinical pathological factors in other independent test groups. As shown in Table 3, risk stratification and other factors, such as pathological TNM stage, are important influencing factors affecting the accuracy of prognostic prediction. In the univariate analysis, after selecting significant variables (p < 0.05), after adjusting important prognostic markers such as pT (HR = 2.438, p < 0.0001) and resection margin (HR = 1.681, p = 0.091), the staging proposed in this application remained strong in the multivariate analysis (HR = 1.847, p = 0.027). It is worth noting that the marker proposed in this application remains the strongest among all preoperative markers, such as tumor size and CA19-9.

[0145] In order to demonstrate the effectiveness of selecting target texture features and target nerve distances as tools for neoadjuvant therapy before surgery, Figure 5 is a schematic diagram of survival curves under different groupings according to Example 1 of the present application, as shown in Figure 5, wherein Figure 5 shows the survival curves of patients under different groupings, and the specific groups are: A is a risk indicator curve without grouping, B is grouped according to tumor size, C is grouped according to CA19-9 values, D is grouped according to both tumor size and CA19-9 values, and E and F are grouped according to patient age. It can be concluded from Figure 5 that patients with high risk and more serious conditions need to use the target texture features and target nerve distances of this application as neoadjuvant therapy.

[0146] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0147] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0148] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0149] Example 2

[0150] According to an embodiment of the present application, an image processing method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0151] FIG6 is a flow chart of an image processing method according to Embodiment 2 of the present application. As shown in FIG6 , the method may include the following steps:

[0152] Step S602 : In response to an input instruction on the operation interface, multiple images acquired at different times are displayed on the operation interface.

[0153] The display content of the multi-phase image at least includes the monitoring area of ​​the target part of the object to be monitored.

[0154] The above-mentioned input instruction may refer to an instruction for displaying multiple phase images in a preset operation interface, and the above-mentioned monitoring object may refer to an animal whose tissues or organs may be diseased, such as humans, cats, hamsters and other animals. The monitoring area of ​​the above-mentioned target part may refer to the area corresponding to the tissue or organ that may be diseased, such as a tumor area. The above-mentioned multiple phase images may refer to image acquisition of the monitoring area at different times, for example, the monitoring area may be scanned and imaged at different times by tomography or magnetic resonance imaging to acquire multiple phase images of the monitoring area at different times.

[0155] In an optional solution of this embodiment, after receiving the input instruction, the image processing unit can display multiple images collected at different times in a preset operation interface.

[0156] Step S604: In response to the image processing instruction applied to the operation interface, the risk index of the monitoring area is displayed on the operation interface.

[0157] Among them, the risk index is generated based on the target texture features and target neural distance of multi-phase images. The target texture features are obtained by extracting texture features from multi-phase images, and the target neural distance is determined based on the positional relationship between the monitoring area and other areas in the multi-phase images.

[0158] The target nerve distance may refer to the distance between the surface of the monitoring area and the surfaces of other areas, for example, the distance between the monitoring area and the surfaces of blood vessels in other areas.

[0159] In an optional scheme of this embodiment, after receiving the image processing instruction, the image processing system can perform texture feature extraction on the multi-phase images to obtain the target texture features of the multi-phase images, and determine the target nerve distance between the monitoring area and other areas based on the positional relationship between the monitoring area and other areas in the multi-phase images, and then determine the risk index of the monitoring area based on the target texture features and the target nerve distance to determine whether there is a risk in the monitoring area for multiple periods.

[0160] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0161] Example 3

[0162] According to an embodiment of the present application, an image processing method that can be applied to virtual reality scenarios such as virtual reality VR devices and augmented reality AR devices is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0163] FIG7 is a flow chart of an image processing method according to Embodiment 3 of the present application. As shown in FIG7 , the method may include the following steps:

[0164] Step S702: Display multiple images collected at different times on a presentation screen of a virtual reality (VR) device or an augmented reality (AR) device.

[0165] The display content of the multi-phase image at least includes the monitoring area of ​​the target part of the object to be monitored.

[0166] The monitoring object may refer to an animal whose tissues or organs may be diseased, such as a human, a cat, a hamster, or other animal. The monitoring area of ​​the target site may refer to the area corresponding to the tissue or organ that may be diseased, such as a tumor area. The multi-phase image may refer to image acquisition of the monitoring area at different times. For example, the monitoring area may be scanned and imaged at different times by tomography or magnetic resonance imaging to acquire multi-phase images of the monitoring area at different times.

[0167] In an optional solution of this embodiment, in order to make the determined risk indicators more accurate, the above-mentioned multiple images including the monitoring area collected at different times can be obtained through a virtual reality VR device or an augmented reality AR device.

[0168] Step S704: extract texture features from the multi-period images to obtain target texture features of the multi-period images.

[0169] The above-mentioned target texture features can be texture features obtained by fusing the global texture features and local texture features presented by the monitoring area, wherein the local texture features can refer to the texture features of the monitoring area, which can include but are not limited to: color, texture, shape, edge, corner point and other features of the monitoring area; the global texture features can refer to the texture features of other areas outside the overall area of ​​the multi-phase image, such as the texture features of the target part, the texture features of the area outside the target part, etc.

[0170] In an optional scheme of this embodiment, considering that one of the main ways to determine whether there is a risk in the monitoring area is based on the image effects presented by the monitoring area, such as image texture, therefore, in order to improve the accuracy of determining whether there is a risk in the monitoring area, the image processing system can, after acquiring multiple images at different times, extract texture features from the multiple images to determine the target texture features of the above multiple images.

[0171] In an alternative embodiment of this embodiment, when extracting texture features from multi-phase images to obtain target texture features, it is considered that in areas other than the target site and target site of the monitoring region, there may be a large number of important tissues and organs. For example, in areas other than the PDAC region, there may be a large number of important blood vessels on and around the pancreas. These important tissues and organs may have a certain impact on the monitoring of the monitoring region. For example, if the color of the blood vessels is similar to that of the PDAC region, it may lead to a misjudgment of PDAC spread. Furthermore, it is considered that the monitoring region may also affect these important tissues and organs when it is diseased. For example, the PDAC region may invade the blood vessels around the pancreas. Therefore, to ensure the accuracy of determining whether the monitoring region is at risk, when extracting texture features from multi-phase images, in addition to monitoring the monitoring region based solely on the texture features presented by the monitoring region, that is, extracting local texture features of the monitoring region, the image processing system may also monitor the texture presented by other areas of the monitoring region, that is, extracting global texture features. The local texture features and the global texture features are then fused to obtain the target texture features, thereby ensuring the accuracy of determining whether the monitoring region is at risk based on the target texture features.

[0172] Step S706 , determining the target nerve distance of the multi-phase image based on the positional relationship between the monitoring area and other areas in the multi-phase image.

[0173] Among them, the other areas are used to represent the areas of the target part other than the monitoring area.

[0174] In an optional solution of this embodiment, in addition to directly using the aforementioned target texture features to determine whether there is a risk in the monitoring area, the distance between the monitoring area and other areas in multiple images, that is, the above-mentioned target nerve distance, can be further combined to determine whether there is a risk in the monitoring area, thereby improving the accuracy of the determination results.

[0175] In an optional solution of this embodiment, the target nerve distances corresponding to different images can be determined based on the positional relationship between the monitoring area and other areas in multiple images, such as the relative position, structural connection and other information between the aforementioned monitoring area and other areas.

[0176] Step S708: Generate a risk index for the monitoring area based on the target texture features and the target nerve distance.

[0177] Among them, the risk index is used to characterize the probability of risk existing in the monitoring area.

[0178] In an optional solution of this embodiment, considering that other regions may affect the accuracy of prognostic prediction for the monitored area, for example, there are many important blood vessels around the pancreas, which are close to the PDAC area. When resecting the PDAC area, there may be mis-resection, which may have a negative impact on the patient. Therefore, in order to accurately predict the prognosis of the monitored area, in addition to directly using the aforementioned target texture features to determine whether the monitored area is at risk, the distance between the monitored area and other areas in multiple image phases, i.e., the aforementioned target nerve distance, can be further combined to determine whether the monitored area is at risk, thereby improving the accuracy of the determination result.

[0179] In an optional solution of this embodiment, the target nerve distances corresponding to different images can be determined based on the positional relationship between the monitoring area and other areas in multiple images, such as the relative position, structural connection and other information between the aforementioned monitoring area and other areas.

[0180] Step S710: driving the VR device or AR device to display the risk indicator.

[0181] In an optional solution of this embodiment, a VR device or an AR device can be driven to display the determined risk indicators to the user, so that the staff can more intuitively monitor the risk indicators corresponding to the area.

[0182] Optionally, in this embodiment, the image processing method can be applied to a hardware environment consisting of a server and a virtual reality device. Multiple images, target texture features, target neural distances, and risk indicators of these images are displayed on a presentation screen of a virtual reality (VR) device or an augmented reality (AR) device. The server can be a server corresponding to a media file operator. The network includes, but is not limited to, a wide area network, a metropolitan area network, or a local area network. The virtual reality device is not limited to a virtual reality helmet, virtual reality glasses, or an all-in-one virtual reality device.

[0183] Optionally, the virtual reality device includes a memory, a processor, and a transmission device. The memory is used to store an application program, which can be used to perform: texture feature extraction on multiple images to obtain target texture features for the multiple images, including: extracting features from the images to obtain initial texture features of the images; and fusing global information and local information in the initial texture features using at least one texture perception model to obtain target texture features.

[0184] In an embodiment of the present application, the application is also used to perform: using at least one texture perception model block to fuse the global information and local information in the initial texture features to obtain target texture features, including: using the convolutional neural network module in the texture perception model to downsample the initial texture features to obtain the local texture features of the image; using the self-attention module in the texture perception model to perform attention processing on the local texture features to obtain the target texture features of the image.

[0185] In an embodiment of the present application, the application is also used to perform: using the convolutional neural network module in the texture perception model to downsample the initial texture features and the local texture features of the image, including: using the first convolutional layer in the convolutional neural network module to capture the first local information in the initial texture features; using the second convolutional layer in the convolutional neural network module to map the first local information to a preset space to obtain a first mapped texture feature; using the third convolutional layer in the convolutional neural network module to restore the mapped texture features to the original space corresponding to the initial texture features to obtain a restored texture feature; using the normalization layer in the convolutional neural network module to normalize the restored texture features to obtain a local texture feature.

[0186] In an embodiment of the present application, the application is also used to execute: using the self-attention module in the texture perception model to perform attention processing on local texture features to obtain target texture features of the image, including: using the first convolution layer in the self-attention module to capture second local information in the local texture features; using the second convolution layer in the self-attention module to map the second local information to a preset space to obtain a second mapped texture feature; using the self-attention layer in the self-attention module to perform self-attention processing on the second mapped texture feature to obtain a self-attention texture feature; using the feedforward layer in the self-attention module to perform feature interaction on the self-attention texture feature to obtain an interactive texture feature; using the removal layer in the self-attention module to perform feature fusion on the interactive texture feature to obtain a target texture feature.

[0187] In an embodiment of the present application, the application is also used to perform: using at least one texture perception model to fuse the global information and local information in the initial texture features to obtain target texture features, including: using at least one texture perception model to fuse the global information and local information in the initial texture features to obtain the output texture features of the image; performing cross-attention processing on the output texture features of multiple-period images to obtain cross-attention features; splicing the output texture features and cross-attention features of multiple-period images to obtain target texture features.

[0188] In an embodiment of the present application, the application is also used to execute: performing cross-attention processing on the output texture features of multiple-period images to obtain cross-attention features, including: using a cross-attention module to perform cross-attention processing on the output texture features of images from different periods to obtain cross-attention features.

[0189] In an embodiment of the present application, the application is also used to perform: determining the target neural distance of multiple images based on the positional relationship between the monitoring area and other areas in the multiple images, including: performing image segmentation on the image to obtain the image segmentation result, wherein the segmentation result includes at least: the monitoring area and other areas; based on the segmentation result, determining a first point set located at the boundary of the monitoring area, and a second point set located at the boundary of other areas; determining a first subset of the first point set that meets the preset conditions, and a second subset of the second point set that meets the preset conditions; performing cross-attention processing on the first subset and the second subset to obtain the target neural distance.

[0190] In an embodiment of the present application, the application is further configured to execute: determining a first subset of the first point set that satisfies a preset condition, and a second subset of the second point set that satisfies a preset condition, including: sampling the first point set to obtain a first sampling point set, and sampling the second point set to obtain a second sampling point set; determining a preset number of first sampling points in the first sampling point set that are closest to the second sampling point set to obtain the first subset; and determining a preset number of second sampling points in the second sampling point set that are closest to the first sampling point set to obtain the second subset.

[0191] In an embodiment of the present application, the application is also used to perform: generating a risk index for the monitoring area based on target texture features and target nerve distance, including: extracting the structural relationship between the monitoring area and other areas in multiple images to obtain structural features of the multiple images; splicing the target texture features, target nerve distance and structural features to obtain splicing features; and generating a risk index based on the splicing features.

[0192] It should be noted that the above-mentioned image processing method applied in the VR device or AR device of this embodiment may include the method of the embodiment shown in Figure 3, so as to achieve the purpose of driving the VR device or AR device to display multiple images, target texture features, target data distance and risk indicators.

[0193] Optionally, the processor of this embodiment can call the application stored in the memory to perform the above steps through a transmission device. The transmission device can receive media files sent by the server through the network, and can also be used for data transmission between the processor and the memory.

[0194] Optionally, in a virtual reality device, a head-mounted display with eye tracking is provided, wherein the screen in the HMD is used to display the displayed video images, the eye tracking module in the HMD is used to obtain the real-time movement trajectory of the user's eyeballs, the tracking system is used to track the user's position information and motion information in the real three-dimensional space, and the computing processing unit is used to obtain the user's real-time position and motion information from the tracking system, and calculate the three-dimensional coordinates of the user's head in the virtual three-dimensional space, as well as the user's field of view direction in the virtual three-dimensional space, etc.

[0195] In an embodiment of the present application, a virtual reality device can be connected to a terminal, and the terminal and the server are connected through a network. The above-mentioned virtual reality device is not limited to: virtual reality helmets, virtual reality glasses, virtual reality all-in-one machines, etc. The above-mentioned terminals are not limited to PCs, mobile phones, tablets, etc. The server can be a server corresponding to a media file operator, and the above-mentioned network includes but is not limited to: wide area network, metropolitan area network or local area network.

[0196] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0197] Example 4

[0198] According to an embodiment of the present application, an image processing method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0199] FIG8 is a flow chart of an image processing method according to Embodiment 4 of the present application. As shown in FIG8 , the method may include the following steps:

[0200] Step S802: Acquire multiple images collected at different times by calling the first interface.

[0201] The first interface includes a first parameter, the parameter value of the first parameter is a multi-phase image, and the display content of the multi-phase image at least includes a monitoring area of ​​a target part of the object to be monitored.

[0202] The monitoring object may refer to an animal whose tissues or organs may be diseased, such as a human, a cat, a hamster, or other animal. The monitoring area of ​​the target site may refer to the area corresponding to the tissue or organ that may be diseased, such as a tumor area. The multi-phase image may refer to image acquisition of the monitoring area at different times. For example, the monitoring area may be scanned and imaged at different times by tomography or magnetic resonance imaging to acquire multi-phase images of the monitoring area at different times.

[0203] In an optional solution of this embodiment, in order to make the determined risk index more accurate, the image processing system may acquire the above-mentioned multiple images including the monitoring area collected at different times by calling the first interface.

[0204] Step S804: extracting texture features of the multi-period images to obtain target texture features of the multi-period images.

[0205] In an optional scheme of this embodiment, considering that one of the main ways to determine whether there is a risk in the monitoring area is based on the image effects presented by the monitoring area, such as image texture, therefore, in order to improve the accuracy of determining whether there is a risk in the monitoring area, the image processing system can, after acquiring multiple images at different times, extract texture features from the multiple images to determine the target texture features of the above multiple images.

[0206] Step S806 , determining the target nerve distance of the multi-phase image based on the positional relationship between the monitoring area and other areas in the multi-phase image.

[0207] Among them, the other areas are used to represent the areas of the target part other than the monitoring area.

[0208] In an optional solution of this embodiment, in addition to directly using the aforementioned target texture features to determine whether there is a risk in the monitoring area, the distance between the monitoring area and other areas in multiple images, that is, the above-mentioned target nerve distance, can be further combined to determine whether there is a risk in the monitoring area, thereby improving the accuracy of the determination results.

[0209] Step S808: Generate a risk index for the monitoring area based on the target texture features and the target nerve distance.

[0210] Among them, the risk index is used to characterize the probability of risk existing in the monitoring area.

[0211] In an optional solution of this embodiment, considering that other regions may affect the accuracy of prognostic prediction for the monitored area, for example, there are many important blood vessels around the pancreas, which are close to the PDAC area. When resecting the PDAC area, there may be mis-resection, which may have a negative impact on the patient. Therefore, in order to accurately predict the prognosis of the monitored area, in addition to directly using the aforementioned target texture features to determine whether the monitored area is at risk, the distance between the monitored area and other areas in multiple image phases, i.e., the aforementioned target nerve distance, can be further combined to determine whether the monitored area is at risk, thereby improving the accuracy of the determination result.

[0212] Step S810: Output the risk indicator by calling the second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter is the risk indicator.

[0213] In an optional solution of this embodiment, the determined risk index can be output by calling the second interface, so that the staff can more intuitively monitor the risk index corresponding to the area.

[0214] Example 5

[0215] According to an embodiment of the present application, a device for implementing the above-mentioned image processing method is also provided, which can be deployed in a target client. Figure 9 is a structural block diagram of an image processing device according to Example 5 of the present application. As shown in Figure 9, the device 900 includes: an acquisition module 902, an extraction module 904, a determination module 906, and a generation module 908.

[0216] Among them, the acquisition module 902 is used to acquire multiple images collected at different times, wherein the display content of the multiple images at least includes the monitoring area of ​​the target part of the object to be monitored; the extraction module 904 is used to extract texture features of the multiple images to obtain target texture features of the multiple images; the determination module 906 is used to determine the target nerve distance of the multiple images based on the positional relationship between the monitoring area and other areas in the multiple images, wherein the other areas are used to characterize the areas of the target part other than the monitoring area; the generation module 908 is used to generate a risk index of the monitoring area based on the target texture features and the target nerve distance, wherein the risk index is used to characterize the probability of the existence of risk in the monitoring area.

[0217] In the above embodiment of the present application, the extraction module 904 includes: an extraction unit, which is used to extract features from the image to obtain the initial texture features of the image; and a fusion unit, which is used to use at least one texture perception model to fuse the global information and local information in the initial texture features to obtain the target texture features.

[0218] In an embodiment of the present application, the fusion unit is also used to: use the convolutional neural network module in the texture perception model to downsample the initial texture features and obtain the local texture features of the image; use the self-attention module in the texture perception model to perform attention processing on the local texture features to obtain the target texture features of the image.

[0219] In an embodiment of the present application, the fusion unit is also used to: use the first convolution layer in the convolutional neural network module to capture the first local information in the initial texture feature; use the second convolution layer in the convolutional neural network module to map the first local information to a preset space to obtain a first mapped texture feature; use the third convolution layer in the convolutional neural network module to restore the mapped texture feature to the original space corresponding to the initial texture feature to obtain a restored texture feature; use the normalization layer in the convolutional neural network module to normalize the restored texture feature to obtain a local texture feature.

[0220] In an embodiment of the present application, the fusion unit is also used to: utilize the first convolution layer in the self-attention module to capture the second local information in the local texture feature; utilize the second convolution layer in the self-attention module to map the second local information to a preset space to obtain a second mapped texture feature; utilize the self-attention layer in the self-attention module to perform self-attention processing on the second mapped texture feature to obtain a self-attention texture feature; utilize the feedforward layer in the self-attention module to perform feature interaction on the self-attention texture feature to obtain an interactive texture feature; utilize the removal layer in the self-attention module to perform feature fusion on the interactive texture feature to obtain a target texture feature.

[0221] In an embodiment of the present application, the fusion unit is also used to: use at least one texture perception model to fuse the global information and local information in the initial texture features to obtain the output texture features of the image; perform cross-attention processing on the output texture features of multiple-period images to obtain cross-attention features; and splice the output texture features and cross-attention features of multiple-period images to obtain target texture features.

[0222] In an embodiment of the present application, the fusion unit is also used to: use a cross-attention module to perform cross-attention processing on the output texture features of images of different periods to obtain cross-attention features.

[0223] In an embodiment of the present application, the determination module 906 includes: a segmentation unit, which is used to perform image segmentation on the image to obtain a segmentation result of the image, wherein the segmentation result includes at least: a monitoring area and other areas; a first determination unit, which is used to determine a first point set located at the boundary of the monitoring area and a second point set located at the boundary of other areas based on the segmentation result; a second determination unit, which is used to determine a first subset of the first point set that meets a preset condition and a second subset of the second point set that meets the preset condition; a distance determination unit, which is used to perform cross-attention processing on the first subset and the second subset to obtain a target neural distance.

[0224] In the embodiment of the present application, the second determining unit is further configured to: sample the first point set to obtain a first sampling point set, and sample the second point set to obtain a second sampling point set; determine a preset number of first sampling points in the first sampling point set that are closest to the second sampling point set to obtain a first subset; and determine a preset number of second sampling points in the second sampling point set that are closest to the first sampling point set to obtain a second subset.

[0225] In an embodiment of the present application, the generation module 908 includes: a structural relationship extraction unit, which is used to extract the structural relationship between the monitoring area and other areas in the multi-phase image to obtain the structural features of the multi-phase image; a feature splicing unit, which is used to splice the target texture features, target neural distance and structural features to obtain splicing features; and an indication generation unit, which is used to generate risk indicators based on the splicing features.

[0226] It should be noted that the acquisition module 902, extraction module 904, determination module 906, and generation module 908 described above correspond to steps S302 to S308 in Example 1. The examples and application scenarios implemented by the four modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the above modules or units can be hardware components or software components stored in a memory and processed by one or more processors. The above modules can also be run as part of the device in the AR / VR device provided in Example 1.

[0227] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0228] Example 6

[0229] According to an embodiment of the present application, a device for implementing the above-mentioned image processing method is also provided. The device can be deployed in a target client. FIG10 is a block diagram of an image processing device according to Embodiment 6 of the present application. As shown in FIG10 , the device 1000 includes: a first display module 1002 and a second display module 1004.

[0230] Among them, the first display module 1002 is used to respond to input instructions acting on the operation interface, and display multiple images collected at different times on the operation interface, wherein the display content of the multiple images at least includes the monitoring area of ​​the target part of the object to be monitored. The second display module 1004 is used to respond to image processing instructions acting on the operation interface, and display the risk index of the monitoring area on the operation interface, wherein the risk index is generated based on the target texture features and target nerve distance of the multiple images, the target texture features are obtained by extracting texture features from the multiple images, and the target nerve distance is determined based on the positional relationship between the monitoring area and other areas in the multiple images.

[0231] It should be noted that the first display module 1002 and the second display module 1004 described above correspond to steps S602 to S604 in Example 2. The examples and application scenarios implemented by the two modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the above modules or units can be hardware components or software components stored in a memory and processed by one or more processors. The above modules can also be run as part of the device in the AR / VR device provided in Example 1.

[0232] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0233] Example 7

[0234] According to an embodiment of the present application, a device for implementing the above-mentioned image processing method is also provided, which can be deployed in a target client. Figure 11 is a block diagram of an image processing device according to Example 7 of the present application. As shown in Figure 11, the device 1100 includes: a first display module 1102, an extraction module 1104, a determination module 1106, a generation module 1108, and a second display module 1110.

[0235] Among them, the first display module 1102 is used to display multiple images collected at different times on the presentation screen of a virtual reality VR device or an augmented reality AR device, wherein the display content of the multiple images at least includes the monitoring area of ​​the target part of the object to be monitored, the extraction module 1104 is used to extract texture features of the multiple images to obtain target texture features of the multiple images, the determination module 1106 is used to determine the target nerve distance of the multiple images based on the positional relationship between the monitoring area and other areas in the multiple images, wherein the other areas are used to characterize the areas of the target part other than the monitoring area, the generation module 1108 is used to generate a risk indicator of the monitoring area based on the target texture features and the target nerve distance, wherein the risk indicator is used to characterize the probability of risk in the monitoring area, and the second display module 1110 is used to drive the VR device or AR device to display the risk indicator.

[0236] It should be noted that the first display module 1102, extraction module 1104, determination module 1106, generation module 1108, and second display module 1110 described above correspond to steps S702 to S710 in Example 3. The examples and application scenarios implemented by the five modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the above modules or units can be hardware components or software components stored in a memory and processed by one or more processors. The above modules can also be run as part of the device in the AR / VR device provided in Example 1.

[0237] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0238] Example 8

[0239] According to an embodiment of the present application, a device for implementing the above-mentioned image processing method is also provided, which can be deployed in a target client. Figure 12 is a structural block diagram of an image processing device according to Example 8 of the present application. As shown in Figure 12, the device 1200 includes: an acquisition module 1202, an extraction module 1204, a determination module 1206, a generation module 1208, and an output module 1210.

[0240] Among them, the acquisition module 1202 is used to obtain multiple images collected at different times by calling the first interface, wherein the first interface includes a first parameter, the parameter value of the first parameter is multiple images, and the display content of the multiple images at least includes the monitoring area of ​​the target part of the object to be monitored. The extraction module 1204 is used to extract texture features from the multiple images to obtain target texture features of the multiple images. The determination module 1206 is used to determine the target nerve distance of the multiple images based on the positional relationship between the monitoring area and other areas in the multiple images, wherein the other areas are used to characterize the areas of the target part other than the monitoring area; the generation module 1208 is used to generate a risk index of the monitoring area based on the target texture features and the target nerve distance, wherein the risk index is used to characterize the probability of risk in the monitoring area; the output module 1210 is used to output the risk index by calling the second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter is the risk index.

[0241] It should be noted that the acquisition module 1202, extraction module 1204, determination module 1206, generation module 1208, and output module 1210 described above correspond to steps S802 to S810 in Example 4. The examples and application scenarios implemented by the five modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the above modules or units can be hardware components or software components stored in a memory and processed by one or more processors. The above modules can also be run as part of the device in the AR / VR device provided in Example 1.

[0242] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0243] Example 9

[0244] According to an embodiment of the present application, a computer-assisted cancer prognosis method is also provided, comprising:

[0245] Acquiring multiple medical images acquired at different times, wherein the display content of the multiple medical images at least includes a cancer region of a target site of the subject to be monitored;

[0246] Extracting texture features from multiple medical images to obtain target texture features of the multiple medical images;

[0247] determining target nerve distances of the multi-phase medical images based on a positional relationship between the cancer region and other regions in the multi-phase medical images, wherein the other regions are used to represent regions of the target site other than the cancer region;

[0248] Based on the target texture features and the target nerve distance, a risk index of the monitoring area is generated, where the risk index is used to characterize the probability of the presence of risk in the cancer area.

[0249] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0250] Example 10

[0251] According to an embodiment of the present application, a computer-assisted pancreatic cancer prognosis method is also provided, comprising:

[0252] Acquiring multiple medical images acquired at different times, wherein the display content of the multiple medical images at least includes a pancreatic cancer region of the subject to be monitored;

[0253] Extracting texture features from multiple medical images to obtain target texture features of the multiple medical images;

[0254] determining target nerve distances of the multi-phase medical images based on a positional relationship between the pancreatic cancer region and other regions in the multi-phase medical images, wherein the other regions are used to represent regions outside the pancreatic cancer region;

[0255] Based on the target texture features and the target nerve distance, a risk index of the monitoring area is generated, wherein the risk index is used to characterize the probability of the existence of risk in the pancreatic cancer area.

[0256] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0257] Example 11

[0258] According to an embodiment of the present application, a computer-assisted cancer prognosis system is further provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. The processor executes the computer program to perform a computer-assisted cancer prognosis method, the method comprising:

[0259] Acquiring multiple medical images acquired at different times, wherein the display content of the multiple medical images at least includes a cancer region of a target site of the subject to be monitored;

[0260] Extracting texture features from multiple medical images to obtain target texture features of the multiple medical images;

[0261] determining target nerve distances of the multi-phase medical images based on a positional relationship between the cancer region and other regions in the multi-phase medical images, wherein the other regions are used to represent regions of the target site other than the cancer region;

[0262] Based on the target texture features and the target nerve distance, a risk index of the monitoring area is generated, where the risk index is used to characterize the probability of the presence of risk in the cancer area.

[0263] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0264] Example 12

[0265] The embodiment of the present application may provide an electronic device, which may be any electronic device in a group of electronic devices. Optionally, in this embodiment, the electronic device may also be replaced by a terminal device such as a mobile terminal.

[0266] Optionally, in this embodiment, the electronic device may be located in at least one grid device among a plurality of grid devices of a computer grid.

[0267] In this embodiment, the above-mentioned electronic device can execute the program code of the following steps in the image segmentation method: obtaining multiple images collected at different times, wherein the display content of the multiple images at least includes the monitoring area of ​​the target part of the object to be monitored; performing texture feature extraction on the multiple images to obtain the target texture features of the multiple images; determining the target nerve distance of the multiple images based on the positional relationship between the monitoring area and other areas in the multiple images, wherein the other areas are used to characterize the area of ​​the target part other than the monitoring area; generating a risk index for the monitoring area based on the target texture features and the target nerve distance, wherein the risk index is used to characterize the probability of risk existing in the monitoring area.

[0268] Optionally, Figure 13 is a block diagram of an electronic device according to Example 12 of the present application. As shown in the figure, the electronic device A may include: a processor 1302 and a memory 1304, wherein an executable program is stored; the processor is configured to run the program, wherein the program, when run, executes the image processing method described in Example 1.

[0269] Optionally, as shown in FIG13 , the electronic device A may further include: a storage controller and a peripheral interface, wherein the peripheral interface is connected to the radio frequency module, the audio module and the display.

[0270] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the image processing method and device in the embodiments of the present application. The processor executes the software programs and modules stored in the memory to perform various functional applications and data processing, that is, to implement the above-mentioned image segmentation method. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely located relative to the processor, and these remote memories may be connected to the terminal A via a grid. Examples of the above-mentioned grid include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0271] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: extract features from the image to obtain initial texture features of the image; use at least one texture perception model to fuse the global information and local information in the initial texture features to obtain target texture features.

[0272] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: using at least one texture perception model block to fuse the global information and local information in the initial texture features to obtain the target texture features, including: using the convolutional neural network module in the texture perception model to downsample the initial texture features to obtain the local texture features of the image; using the self-attention module in the texture perception model to perform attention processing on the local texture features to obtain the target texture features of the image.

[0273] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: using the convolutional neural network module in the texture perception model to downsample the initial texture features and the local texture features of the image, including: using the first convolutional layer in the convolutional neural network module to capture the first local information in the initial texture features; using the second convolutional layer in the convolutional neural network module to map the first local information to a preset space to obtain a first mapped texture feature; using the third convolutional layer in the convolutional neural network module to restore the mapped texture features to the original space corresponding to the initial texture features to obtain a restored texture feature; using the normalization layer in the convolutional neural network module to normalize the restored texture features to obtain a local texture feature.

[0274] The processor can call the information and application stored in the memory through the transmission device to execute the following steps: using the self-attention module in the texture perception model to perform attention processing on the local texture features to obtain the target texture features of the image, including: using the first convolution layer in the self-attention module to capture the second local information in the local texture features; using the second convolution layer in the self-attention module to map the second local information to a preset space to obtain a second mapped texture feature; using the self-attention layer in the self-attention module to perform self-attention processing on the second mapped texture features to obtain a self-attention texture feature; using the feedforward layer in the self-attention module to perform feature interaction on the self-attention texture features to obtain an interactive texture feature; using the removal layer in the self-attention module to perform feature fusion on the interactive texture features to obtain a target texture feature.

[0275] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: using at least one texture perception model to fuse the global information and local information in the initial texture features to obtain the target texture features, including: using at least one texture perception model to fuse the global information and local information in the initial texture features to obtain the output texture features of the image; performing cross-attention processing on the output texture features of multiple-period images to obtain cross-attention features; splicing the output texture features and cross-attention features of multiple-period images to obtain the target texture features.

[0276] The processor can call the information and application stored in the memory through the transmission device to execute the following steps: perform cross-attention processing on the output texture features of multiple periods of images to obtain cross-attention features, including: using the cross-attention module to perform cross-attention processing on the output texture features of images from different periods to obtain cross-attention features.

[0277] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: based on the positional relationship between the monitoring area and other areas in the multiple images, determine the target neural distance of the multiple images, including: performing image segmentation on the image to obtain the image segmentation result, wherein the segmentation result at least includes: the monitoring area and other areas; based on the segmentation result, determine a first point set located at the boundary of the monitoring area, and a second point set located at the boundary of other areas; determine a first subset of the first point set that meets the preset conditions, and a second subset of the second point set that meets the preset conditions; perform cross-attention processing on the first subset and the second subset to obtain the target neural distance.

[0278] The processor may call information and an application stored in the memory through the transmission device to perform the following steps: determining a first subset of the first point set that meets a preset condition, and a second subset of the second point set that meets a preset condition, including: sampling the first point set to obtain a first sampling point set, and sampling the second point set to obtain a second sampling point set; determining a preset number of first sampling points in the first sampling point set that are closest to the second sampling point set to obtain the first subset; and determining a preset number of second sampling points in the second sampling point set that are closest to the first sampling point set to obtain the second subset.

[0279] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: generating a risk index for the monitoring area based on the target texture features and the target nerve distance, including: extracting the structural relationship between the monitoring area and other areas in multiple images to obtain the structural features of the multiple images; splicing the target texture features, target nerve distance and structural features to obtain splicing features; and generating a risk index based on the splicing features.

[0280] In an embodiment of the present application, a method is adopted in which multiple images acquired at different times are acquired; texture features of the multiple images are extracted to obtain target texture features of the multiple images; the target nerve distance of the multiple images is determined based on the positional relationship between the monitoring area and other areas in the multiple images; and a risk index of the monitoring area is generated based on the target texture features and the target nerve distance. The risk index of the monitoring area is generated based on the target texture features of the monitoring area in the multiple images acquired at different times and the target nerve distance between the monitoring area and other areas. In this way, the contact situation between the monitoring area and other areas is fully considered in the risk prediction process of the monitoring area, thereby improving the accuracy of the determined risk index, and further solving the technical problem of low accuracy in determining whether there is a risk in the monitoring area in the related art.

[0281] Those skilled in the art will appreciate that the structure shown in FIG13 is merely illustrative, and that the computer terminal may also be a smartphone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile internet device (MID), a PAD, or other terminal device. FIG13 does not limit the structure of the aforementioned electronic devices. For example, the computer terminal A may include more or fewer components (e.g., a grid interface, a display device, etc.) than those shown in FIG13 , or may have a configuration different from that shown in FIG13 .

[0282] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0283] Example 13

[0284] The embodiment of the present application further provides a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the image segmentation method provided in the embodiment 1 above.

[0285] In this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer grid, or in any mobile terminal in a mobile terminal group.

[0286] In an embodiment of the present application, the storage medium is configured to store program code for executing the following steps: acquiring multiple images acquired at different times, wherein the display content of the multiple images at least includes a monitoring area of ​​a target part of the object to be monitored; performing texture feature extraction on the multiple images to obtain target texture features of the multiple images; determining a target nerve distance of the multiple images based on a positional relationship between the monitoring area and other areas in the multiple images, wherein the other areas are used to characterize areas of the target part other than the monitoring area; generating a risk index for the monitoring area based on the target texture features and the target nerve distance, wherein the risk index is used to characterize the probability that a risk exists in the monitoring area.

[0287] In an embodiment of the present application, the storage medium is configured to store program code for executing the following steps: extracting features from an image to obtain initial texture features of the image; and fusing global information and local information in the initial texture features using at least one texture perception model to obtain target texture features.

[0288] In an embodiment of the present application, the storage medium is configured to store program code for executing the following steps: using at least one texture perception model block to fuse the global information and local information in the initial texture features to obtain target texture features, including: using the convolutional neural network module in the texture perception model to downsample the initial texture features to obtain local texture features of the image; using the self-attention module in the texture perception model to perform attention processing on the local texture features to obtain the target texture features of the image.

[0289] In an embodiment of the present application, the storage medium is configured to store program codes for executing the following steps: using the convolutional neural network module in the texture perception model to downsample the initial texture features and the local texture features of the image, including: using the first convolutional layer in the convolutional neural network module to capture the first local information in the initial texture features; using the second convolutional layer in the convolutional neural network module to map the first local information to a preset space to obtain a first mapped texture feature; using the third convolutional layer in the convolutional neural network module to restore the mapped texture feature to the original space corresponding to the initial texture feature to obtain a restored texture feature; using the normalization layer in the convolutional neural network module to normalize the restored texture feature to obtain a local texture feature.

[0290] In an embodiment of the present application, the storage medium is configured to store program codes for executing the following steps: utilizing the self-attention module in the texture perception model to perform attention processing on the local texture features to obtain the target texture features of the image, including: utilizing the first convolution layer in the self-attention module to capture the second local information in the local texture features; utilizing the second convolution layer in the self-attention module to map the second local information to a preset space to obtain a second mapped texture feature; utilizing the self-attention layer in the self-attention module to perform self-attention processing on the second mapped texture features to obtain a self-attention texture feature; utilizing the feedforward layer in the self-attention module to perform feature interaction on the self-attention texture features to obtain an interactive texture feature; utilizing the removal layer in the self-attention module to perform feature fusion on the interactive texture features to obtain a target texture feature.

[0291] In an embodiment of the present application, the storage medium is configured to store program code for executing the following steps: using at least one texture perception model to fuse the global information and local information in the initial texture features to obtain the target texture features, including: using at least one texture perception model to fuse the global information and local information in the initial texture features to obtain the output texture features of the image; performing cross-attention processing on the output texture features of multiple-period images to obtain cross-attention features; and splicing the output texture features and cross-attention features of multiple-period images to obtain the target texture features.

[0292] In an embodiment of the present application, the storage medium is configured to store program codes for executing the following steps: performing cross-attention processing on the output texture features of multiple-period images to obtain cross-attention features, including: using a cross-attention module to perform cross-attention processing on the output texture features of images from different periods to obtain cross-attention features.

[0293] In an embodiment of the present application, the storage medium is configured to store program code for performing the following steps: determining the target neural distance of multiple images based on the positional relationship between the monitoring area and other areas in the multiple images, including: performing image segmentation on the image to obtain the image segmentation result, wherein the segmentation result includes at least: the monitoring area and other areas; based on the segmentation result, determining a first point set located at the boundary of the monitoring area, and a second point set located at the boundary of the other areas; determining a first subset of the first point set that meets a preset condition, and a second subset of the second point set that meets the preset condition; performing cross-attention processing on the first subset and the second subset to obtain the target neural distance.

[0294] In an embodiment of the present application, a storage medium is configured to store program code for executing the following steps: determining a first subset of a first point set that satisfies a preset condition, and a second subset of a second point set that satisfies a preset condition, including: sampling the first point set to obtain a first sampling point set, and sampling the second point set to obtain a second sampling point set; determining a preset number of first sampling points in the first sampling point set that are closest to the second sampling point set to obtain the first subset; and determining a preset number of second sampling points in the second sampling point set that are closest to the first sampling point set to obtain the second subset.

[0295] In an embodiment of the present application, the storage medium is configured to store program code for executing the following steps: generating a risk indicator for the monitoring area based on the target texture features and the target nerve distance, including: extracting the structural relationship between the monitoring area and other areas in multiple images to obtain the structural features of the multiple images; splicing the target texture features, the target nerve distance and the structural features to obtain the spliced ​​features; and generating a risk indicator based on the spliced ​​features.

[0296] In an embodiment of the present application, a method is adopted in which multiple images acquired at different times are acquired; texture features of the multiple images are extracted to obtain target texture features of the multiple images; the target nerve distance of the multiple images is determined based on the positional relationship between the monitoring area and other areas in the multiple images; and a risk index of the monitoring area is generated based on the target texture features and the target nerve distance. The risk index of the monitoring area is generated based on the target texture features of the monitoring area in the multiple images acquired at different times and the target nerve distance between the monitoring area and other areas. In this way, the contact situation between the monitoring area and other areas is fully considered in the risk prediction process of the monitoring area, thereby improving the accuracy of the determined risk index, and further solving the technical problem of low accuracy in determining whether there is a risk in the monitoring area in the related art.

[0297] Example 14

[0298] An embodiment of the present application further provides a computer program product, including a computer program. When the computer program is executed in a computer, it causes the computer to execute the method provided in the embodiment of the present application.

[0299] Example 15

[0300] An embodiment of the present application further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the method provided in the embodiment of the present application.

[0301] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0302] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0303] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0304] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0305] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0306] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program code.

[0307] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An image processing method, characterized in that: include: Acquire multiple images collected at different times, wherein the display contents of the multiple images at least include a monitoring area of ​​a target part of the object to be monitored; Extracting texture features from the images of the plurality of periods to obtain target texture features of the images of the plurality of periods; Determining the target nerve distance of the multiple phases of images based on the positional relationship between the monitoring area and other areas in the multiple phases of images, wherein the other areas are used to characterize the area of ​​the target part other than the monitoring area; Based on the target texture feature and the target neural distance, a risk index of the monitoring area is generated, wherein the risk index is used to characterize the probability that there is a risk in the monitoring area.

2. The method according to claim 1, characterized in that Extracting texture features of the images of the multiple periods to obtain target texture features of the images of the multiple periods includes: Performing feature extraction on the image to obtain initial texture features of the image; At least one texture perception model is used to fuse the global information and the local information in the initial texture feature to obtain the target texture feature.

3. The method according to claim 2, characterized in that Using at least one texture perception model block to fuse the global information and the local information in the initial texture feature to obtain the target texture feature, including: Using the convolutional neural network module in the texture perception model, down-sampling the initial texture features, the local texture features of the image; The self-attention module in the texture perception model is used to perform attention processing on the local texture features to obtain the target texture features of the image.

4. The method according to claim 3, characterized in that: The initial texture features are downsampled using the convolutional neural network module in the texture perception model, and the local texture features of the image include: Using a first convolutional layer in the convolutional neural network module, capturing first local information in the initial texture feature; Mapping the first local information to a preset space using a second convolutional layer in the convolutional neural network module to obtain a first mapped texture feature; Using the third convolution layer in the convolutional neural network module, the mapped texture feature is restored to the original space corresponding to the initial texture feature to obtain a restored texture feature; The restored texture features are normalized using a normalization layer in the convolutional neural network module to obtain the local texture features.

5. The method according to claim 3, characterized in that: Using the self-attention module in the texture perception model, the local texture features are subjected to attention processing to obtain the target texture features of the image, including: Using the first convolutional layer in the self-attention module, capturing second local information in the local texture feature; Mapping the second local information to a preset space using a second convolutional layer in the self-attention module to obtain a second mapped texture feature; Using the self-attention layer in the self-attention module, performing self-attention processing on the second mapping texture feature to obtain a self-attention texture feature; Using the feedforward layer in the self-attention module, performing feature interaction on the self-attention texture feature to obtain an interactive texture feature; The removal layer in the self-attention module is used to perform feature fusion on the interactive texture features to obtain the target texture features.

6. The method according to claim 2, characterized in that Using at least one texture perception model to fuse the global information and the local information in the initial texture feature to obtain the target texture feature, including: Using at least one texture perception model to fuse the global information and the local information in the initial texture features to obtain output texture features of the image; Performing cross-attention processing on the output texture features of the images of multiple periods to obtain cross-attention features; The output texture features and the cross-attention features of the images of multiple periods are concatenated to obtain the target texture features.

7. The method according to claim 6, characterized in that Performing cross-attention processing on the output texture features of the multiple-phase images to obtain cross-attention features, including: A cross-attention module is used to perform cross-attention processing on the output texture features of the images in different phases to obtain the cross-attention features.

8. The method according to any one of claims 1 to 7, characterized in that: Determining the target nerve distance of the multiple phases of images based on the positional relationship between the monitoring area and other areas in the multiple phases of images includes: Performing image segmentation on the image to obtain a segmentation result of the image, wherein the segmentation result at least includes: the monitoring area and the other areas; Based on the segmentation result, determining a first point set located at a boundary of the monitoring area and a second point set located at a boundary of the other area; Determine a first subset of the first point set that meets a preset condition, and a second subset of the second point set that meets the preset condition; Cross-attention processing is performed on the first subset and the second subset to obtain the target neural distance.

9. The method according to claim 8, characterized in that Determining a first subset of the first point set that meets a preset condition, and a second subset of the second point set that meets the preset condition, includes: Sampling the first point set to obtain a first sampling point set, and sampling the second point set to obtain a second sampling point set; Determine a preset number of first sampling points in the first sampling point set that are closest to the second sampling point set. sampling points, and obtaining the first subset; Determine the preset number of second sampling points in the second sampling point set that are closest to the first sampling point set to obtain the second subset.

10. The method according to any one of claims 1 to 9, characterized in that: Generating a risk index of the monitoring area based on the target texture feature and the target nerve distance includes: Extracting the structural relationship between the monitoring area and the other areas in the images of multiple periods to obtain structural features of the images of multiple periods; Splicing the target texture feature, the target neural distance and the structural feature to obtain a spliced ​​feature; Based on the splicing features, the risk indicator is generated.

11. An image processing method, characterized in that: include: In response to an input instruction on the operation interface, a plurality of images acquired at different times are displayed on the operation interface, wherein the display contents of the plurality of images at least include a monitoring area of ​​a target part of the object to be monitored; In response to the image processing instruction acting on the operation interface, the risk index of the monitoring area is displayed on the operation interface, wherein the risk index is generated based on the target texture features and target nerve distance of the images of multiple periods, the target texture features are obtained by extracting texture features of the images of multiple periods, and the target nerve distance is determined based on the positional relationship between the monitoring area and other areas in the images of multiple periods.

12. An image processing method, characterized in that: include: Acquire multiple images collected at different times by calling a first interface, wherein the first interface includes a first parameter, a parameter value of the first parameter is the multiple images, and display contents of the multiple images at least include a monitoring area of ​​a target part of the object to be monitored; Extracting texture features from the images of the plurality of periods to obtain target texture features of the images of the plurality of periods; Determining the target nerve distance of the multiple phases of images based on the positional relationship between the monitoring area and other areas in the multiple phases of images, wherein the other areas are used to characterize the area of ​​the target part other than the monitoring area; Based on the target texture feature and the target neural distance, generating a risk index for the monitoring area, wherein the risk index is used to characterize the probability that the monitoring area has a risk; The risk indicator is output by calling a second interface, wherein the second interface includes a second parameter, and a parameter value of the second parameter is the risk indicator.

13. A computer-assisted cancer prognosis method, characterized in that: include: Acquire multiple medical images collected at different times, wherein the display contents of the multiple medical images at least include the cancer area of ​​the target part of the subject to be monitored; Extract texture features from multiple medical images to obtain target texture features of multiple medical images. levy; Determining the target nerve distance of the medical images of the multiple phases based on the positional relationship between the cancer region and other regions in the medical images of the multiple phases, wherein the other regions are used to characterize the region of the target part other than the cancer region; Based on the target texture feature and the target nerve distance, a risk index of the monitoring area is generated, wherein the risk index is used to characterize the probability that the cancer area has a risk.

14. A computer-assisted pancreatic cancer prognosis method, characterized in that: include: Acquire multiple medical images collected at different times, wherein the display contents of the multiple medical images at least include the pancreatic cancer area of ​​the subject to be monitored; Extracting texture features from the medical images of the plurality of periods to obtain target texture features of the medical images of the plurality of periods; Determining the target nerve distance of the medical images of multiple phases based on the positional relationship between the pancreatic cancer region and other regions in the medical images of multiple phases, wherein the other regions are used to characterize the region outside the pancreatic cancer region; A risk index for the monitoring area is generated based on the target texture feature and the target nerve distance, wherein the risk index is used to characterize the probability that the pancreatic cancer area has a risk.

15. A computer-assisted cancer prognosis system, characterized in that: The invention comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to perform a computer-assisted cancer prognosis method, the method comprising: Acquire multiple medical images collected at different times, wherein the display contents of the multiple medical images at least include the cancer area of ​​the target part of the subject to be monitored; Extracting texture features from the medical images of the plurality of periods to obtain target texture features of the medical images of the plurality of periods; Determining the target nerve distance of the medical images of the multiple phases based on the positional relationship between the cancer region and other regions in the medical images of the multiple phases, wherein the other regions are used to characterize the region of the target part other than the cancer region; Based on the target texture feature and the target nerve distance, a risk index of the monitoring area is generated, wherein the risk index is used to characterize the probability that the cancer area has a risk.

16. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 14 when running.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 14.

18. A computer program product, characterized in that The method comprises computer executable instructions, which implement the steps of the method according to any one of claims 1 to 14 when executed by a processor.

19. A computer program, 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 14 are implemented.

Images