Medical image processing method and device, computer device and storage medium

Abstract

The application relates to the technical field of image processing, and provides a medical image processing method and device, computer equipment and a storage medium, the method comprising the following steps: performing image segmentation on an acquired original medical image to obtain automatic delineation data corresponding to a target region; generating a three-dimensional rendering model containing an automatic delineation contour of the target region according to the original medical image and the automatic delineation data; listening to an interactive operation event corresponding to the three-dimensional rendering model, acquiring a correction track corresponding to the automatic delineation contour; and obtaining an update result of the automatic delineation contour based on the correction track.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a medical image processing method, apparatus, computer device, and storage medium. Background Technology

[0002] Currently, in order to ensure the accuracy of tumor radiotherapy plans, before formulating a tumor radiotherapy plan, it is necessary to delineate the target areas, such as organs at risk and tumor target areas, in the acquired medical images, such as CT localization images.

[0003] In practice, medical images used for delineation often contain a large number of tomographic images, and the automatically delineated results for the target region in each tomographic image need to be confirmed and modified by a physician individually. Furthermore, since the scanning positions of each tomographic image often overlap, confirming and modifying the automatically delineated results for the same region may require multiple rounds of repeated confirmation and modification. Therefore, current technologies for confirming and modifying automatically delineated results for target regions in medical images suffer from low efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a medical image processing method, apparatus, computer equipment, and storage medium to address the aforementioned technical problems.

[0005] In a first aspect, this application provides a medical image processing method, the method comprising:

[0006] The acquired raw medical images are segmented to obtain automatically drawn data corresponding to the target region;

[0007] Based on the original medical image and the automatically delineated data, a 3D rendering model containing the automatically delineated outline of the target region is generated;

[0008] Listen to the interactive operation events corresponding to the 3D rendering model and obtain the correction trajectory corresponding to the automatically drawn outline;

[0009] Based on the corrected trajectory, the updated result of the automatically drawn contour is obtained.

[0010] In one embodiment, obtaining the updated result of the automatically drawn contour based on the corrected trajectory includes:

[0011] Based on the corrected trajectory, an initial updated trajectory for automatically drawing the outline is generated; if it is confirmed that the distance between corresponding points between the initial updated trajectory and the corrected trajectory reaches a preset value, the initial updated trajectory is determined as the update result; the distance is adjusted based on the distance weight corresponding to the initial updated trajectory.

[0012] In one embodiment, the correction trajectory includes at least one of correcting key points and correcting key lines; the step of listening to the interactive operation events corresponding to the 3D rendering model and obtaining the correction trajectory corresponding to the automatically drawn outline includes:

[0013] Based on the screen coordinates of the click event corresponding to the 3D rendering model, the correction key points corresponding to the automatically drawn outline are obtained; based on the drag trajectory generated by the drag event corresponding to the 3D rendering model, the correction key lines corresponding to the automatically drawn outline are obtained.

[0014] In one embodiment, the method further includes: when there is a large shape difference between the automatically drawn contour and the target drawn contour, generating a correction trajectory corresponding to the automatically drawn contour based on the correction key points and the correction key lines.

[0015] In one embodiment, the step of performing image segmentation on the acquired original medical image to obtain automatically delineated data corresponding to the target region includes:

[0016] In the original medical image, the location information corresponding to the organs at risk and the tumor target area is obtained; based on the location information, the original medical image is segmented to obtain the first automatic delineation data corresponding to the organs at risk and the second automatic delineation data corresponding to the tumor target area.

[0017] In one embodiment, generating a 3D rendering model containing the automatically delineated outline of the target region based on the original medical image and the automatically delineated data includes:

[0018] Based on augmented reality technology, the original medical image, the first automatically drawn data, and the second automatically drawn data are processed to generate the three-dimensional rendering model. In the three-dimensional rendering model, different rendering color values ​​are used to render the regions corresponding to the first automatically drawn data and the second automatically drawn data respectively to obtain the automatically drawn outline.

[0019] Secondly, this application also provides a medical image processing apparatus, the apparatus comprising:

[0020] The delineation data generation module is used to perform image segmentation on the acquired raw medical images to obtain automatic delineation data corresponding to the target region;

[0021] The rendering model generation module is used to generate a three-dimensional rendering model containing the automatically drawn outline of the target region based on the original medical image and the automatically drawn data.

[0022] The trajectory acquisition module is used to listen to the interactive operation events corresponding to the 3D rendering model and acquire the correction trajectory corresponding to the automatically drawn outline.

[0023] The update result output module is used to obtain the updated result of the automatically drawn contour based on the corrected trajectory.

[0024] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described method.

[0025] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.

[0026] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described method.

[0027] The aforementioned medical image processing method, apparatus, computer equipment, and storage medium first perform image segmentation on the acquired original medical image to obtain automatically delineated data corresponding to the target region. Then, based on the original medical image and the automatically delineated data, a 3D rendering model containing the automatically delineated contour of the target region is generated. Next, interactive operation events corresponding to the 3D rendering model are monitored to obtain the correction trajectory corresponding to the automatically delineated contour. Finally, based on the correction trajectory, an updated result of the automatically delineated contour is obtained. This application, based on augmented reality technology, generates a 3D rendering model containing the automatically delineated contour of the target region and obtains the correction trajectory for updating the automatically delineated contour of the target region by monitoring the interactive operation events corresponding to the 3D rendering model. This not only reduces the operational difficulty of modifying the delineation result of the target region in the medical image but also effectively improves the efficiency of delineating the target region in the medical image. Attached Figure Description

[0028] Figure 1 This is a flowchart illustrating a medical image processing method provided in one embodiment;

[0029] Figure 2 This is a flowchart illustrating a specific method for obtaining updated results of automatically drawn outlines in one embodiment;

[0030] Figure 3 This is a flowchart illustrating a specific method for obtaining and correcting key points and key lines in one embodiment.

[0031] Figure 4 This is a flowchart illustrating a specific method for obtaining first automatically delineated data corresponding to organs at risk and second automatically delineated data corresponding to tumor target areas, as provided in one embodiment.

[0032] Figure 5 This is a flowchart illustrating a specific method for obtaining automatically drawn outlines in one embodiment;

[0033] Figure 6 This is a schematic diagram illustrating a specific representation of a 3D rendering model provided in one embodiment.

[0034] Figure 7 This is a structural block diagram of a medical image processing device provided in one embodiment;

[0035] Figure 8 This is an internal structural diagram of a computer device provided in one embodiment. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0037] The medical image processing method provided in this application can be executed on a terminal. The terminal can communicate with the server via a network; the data storage system can store the data that the server needs to process; the data storage system can be integrated on the server, or it can be located on the cloud or other network servers; the terminal can be, but is not limited to, various personal computers, laptops, and tablets; the server can be a standalone server or a server cluster composed of multiple servers.

[0038] In one embodiment, such as Figure 1 As shown, a medical image processing method is provided. Taking the application of this method to a terminal as an example, the method includes the following steps:

[0039] Step S110: Perform image segmentation on the acquired original medical image to obtain the automatic delineation data corresponding to the target region.

[0040] In this step, the original medical images can be several tomographic images obtained by performing thin-slice scanning on the target object. The specific method for image segmentation of the acquired original medical images can be based on artificial intelligence technology to segment the acquired original medical images to obtain automatically delineated data corresponding to the target region. The target region can be the image region where the organs at risk and the tumor target area are located in the original medical images when formulating a tumor radiotherapy plan. Based on this, the specific form of the automatically delineated data corresponding to the target region can be the automatically delineated data corresponding to the organs at risk in the original medical images and the automatically delineated data corresponding to the tumor target area in the original medical images.

[0041] In practical applications, scanning devices used for thin-slice scanning of target objects can include digital subtraction angiography (DSA) devices, computed tomography (CT) devices, and magnetic resonance imaging (MRI) devices.

[0042] Step S120: Based on the original medical image and the automatically drawn data, generate a 3D rendering model containing the automatically drawn outline of the target area.

[0043] In this step, the original medical image can be several tomographic images obtained by performing thin-slice scanning on the target object; the automatically delineated data is the automatically delineated data corresponding to the target region; the target region can be the image region where the organs at risk and the tumor target area are located in the original medical image when formulating a tumor radiotherapy plan. Based on this, the specific form of the automatically delineated data corresponding to the target region can be the automatically delineated data corresponding to the organs at risk in the original medical image and the automatically delineated data corresponding to the tumor target area in the original medical image; the automatically delineated contour of the target region refers to the automatically delineated contour of the target region generated based on the automatically delineated data in the 3D rendering model; the 3D rendering model refers to the 3D rendering model containing the automatically delineated contour of the target region obtained based on the original medical image and the automatically delineated data. The specific rendering part of this 3D rendering model in the original medical image can be determined based on the target region (i.e., the image region where the organs at risk and the tumor target area are located in the original medical image when formulating a tumor radiotherapy plan).

[0044] Step S130: Listen for interactive operation events corresponding to the 3D rendering model and obtain the correction trajectory corresponding to the automatically drawn outline.

[0045] In this step, the 3D rendering model refers to the 3D rendering model containing the automatically drawn outline of the target region, obtained based on the original medical image and the automatically drawn data; the interactive operation event, i.e. the interactive operation event corresponding to the 3D rendering model, refers to the interactive operation event used to modify the automatically drawn outline of the target region in the 3D rendering model accordingly; the automatically drawn outline refers to the automatically drawn outline of the target region; the correction trajectory corresponding to the automatically drawn outline refers to the correction trajectory obtained based on the monitoring of the interactive operation events corresponding to the 3D rendering model, used to modify the automatically drawn outline accordingly.

[0046] In practical applications, interactive operation events can be specifically manifested as interactive operation events performed on the screen, or interactive operation events performed on interactive projection areas generated based on VR (Virtual Reality) technology or AR (Augmented Reality) technology; interactive operation events performed on the screen can include screen operation events such as mouse click events and mouse drag events.

[0047] Step S140: Based on the corrected trajectory, obtain the updated result of automatically drawn outline.

[0048] In this step, the correction trajectory, i.e. the correction trajectory corresponding to the automatically drawn contour, refers to the correction trajectory obtained based on the listening of the interactive operation events corresponding to the 3D rendering model, which is used to make corresponding modifications to the automatically drawn contour; the automatically drawn contour refers to the automatically drawn contour of the target area; the update result of the automatically drawn contour refers to the update result of the automatically drawn contour obtained based on the correction trajectory corresponding to the automatically drawn contour.

[0049] In practical applications, if it is confirmed that there are still some differences between the corresponding points of the current update result of the automatically drawn contour and the target drawn contour (i.e., the correct drawn contour corresponding to the target area) (i.e., there are still some parts in the current update result of the automatically drawn contour that need to be modified), then by repeating the above steps S130 to S140, based on the listening situation of the interactive operation events corresponding to the 3D rendering model, a correction trajectory can be added or an existing correction trajectory can be modified until the update result of the automatically drawn contour obtained based on the correction trajectory and the corresponding points of the target drawn contour all coincide with each other.

[0050] The aforementioned medical image processing method first performs image segmentation on the acquired original medical image to obtain automatically delineated data corresponding to the target region. Then, based on the original medical image and the automatically delineated data, a 3D rendering model containing the automatically delineated contour of the target region is generated. Next, interactive operation events corresponding to the 3D rendering model are monitored to obtain the correction trajectory corresponding to the automatically delineated contour. Finally, based on the correction trajectory, the updated result of the automatically delineated contour is obtained. This application, based on augmented reality technology, generates a 3D rendering model containing the automatically delineated contour of the target region and obtains the correction trajectory for updating the automatically delineated contour of the target region by monitoring the interactive operation events corresponding to the 3D rendering model. This not only reduces the operational difficulty of modifying the delineation result of the target region in the medical image but also effectively improves the efficiency of delineating the target region in the medical image.

[0051] Regarding the specific method for obtaining the updated results of the automatically drawn outline, in one embodiment, such as... Figure 2 As shown, step S140 specifically includes:

[0052] Step S210: Generate an initial updated trajectory for automatically drawing the outline based on the corrected trajectory.

[0053] In this step, the correction trajectory, i.e. the correction trajectory corresponding to the automatically drawn outline, refers to the correction trajectory obtained based on the listening of the interactive operation events corresponding to the 3D rendering model, which is used to make corresponding modifications to the automatically drawn outline; the automatically drawn outline refers to the automatically drawn outline of the target area; the initial update trajectory, i.e. the initial update trajectory of the automatically drawn outline, refers to the initial update trajectory of the automatically drawn outline generated according to the correction trajectory corresponding to the automatically drawn outline.

[0054] In practical applications, the specific method for generating the initial update trajectory of the automatically drawn contour based on the corrected trajectory can be to input the corrected trajectory corresponding to the automatically drawn contour into a pre-trained neural network model to obtain the initial update trajectory of the automatically drawn contour generated by the neural network model based on the corrected trajectory corresponding to the automatically drawn contour. During the training process of the aforementioned neural network model, the 3D rendering model data, the automatically drawn contour of the target area, and the corrected trajectory corresponding to the automatically drawn contour can be used as training sample data input to the model, so that the model can update the automatically drawn contour of the target area based on the corrected trajectory, thereby obtaining the initial update trajectory of the automatically drawn contour.

[0055] Step S220: If it is confirmed that the distance between corresponding points between the initial updated trajectory and the corrected trajectory reaches a preset value, then the initial updated trajectory is determined as the update result; the aforementioned distance is adjusted based on the distance weight corresponding to the initial updated trajectory.

[0056] In this step, the initial update trajectory is the initial update trajectory for automatically drawing the outline; the correction trajectory is the correction trajectory corresponding to the automatically drawn outline, which is the correction trajectory obtained based on the listening of the interactive operation events corresponding to the 3D rendering model and used to make corresponding modifications to the automatically drawn outline; the preset value is the corresponding value used to confirm whether the distance between corresponding points between the initial update trajectory and the correction trajectory meets the preset standard; and the update result is the update result of the automatically drawn outline.

[0057] In practical applications, assuming the preset value is set to 0 (i.e., the corresponding points between the initial updated trajectory and the corrected trajectory should coincide as much as possible), the distance weights corresponding to the initial updated trajectory can be adjusted in the neural network model that generates the initial updated trajectory (for example, by setting the distance weights corresponding to the initial updated trajectory to a large value) so that the corresponding points between the corrected trajectory that automatically draws the contour and the initial updated trajectory generated by the neural network model can coincide.

[0058] The above embodiments generate an initial update trajectory for automatically outlining the contour based on the correction trajectory, and determine the initial update trajectory as the update result when it is confirmed that the distance between corresponding points between the initial update trajectory and the correction trajectory reaches a preset value. This reduces the difficulty of modifying the outline of the target area in the medical image, thereby effectively improving the efficiency of outlining the target area in the medical image.

[0059] Regarding the specific method for obtaining and correcting key points and key lines, in one embodiment, such as... Figure 3 As shown, the above-mentioned correction trajectory includes at least one of correcting key points and correcting key lines; the above-mentioned step S130 specifically includes:

[0060] Step S310: Based on the screen coordinates of the click event corresponding to the 3D rendering model, obtain the correction key points corresponding to the automatically drawn outline.

[0061] In this step, the 3D rendering model refers to the automatically drawn outline of the target area, obtained from the original medical image and the automatically drawn data. The click event corresponding to the 3D rendering model refers to the manual click event used to modify the automatically drawn outline of the target area in the 3D rendering model. The correction key points, i.e., the correction key points corresponding to the automatically drawn outline, refer to the correction key points corresponding to the automatically drawn outline obtained based on the occurrence coordinates of the manual click event corresponding to the 3D rendering model. The specific method for obtaining the correction key points corresponding to the automatically drawn outline based on the screen coordinates of the click event corresponding to the 3D rendering model can be to generate correction key points for modifying the automatically drawn outline at the corresponding positions in the 3D rendering model based on the occurrence coordinates of the manual click event corresponding to the 3D rendering model.

[0062] Specifically, the coordinates of the click event corresponding to the 3D rendered model should be located above the correctly drawn outline of the target area of ​​the 3D rendered model; the correctly drawn outline of the target area can be obtained by observing the visual display effect of the 3D rendered model.

[0063] In practical applications, users can obtain multiple correction key points corresponding to the automatically drawn outline of the target area by repeatedly clicking on the correctly drawn outline of the target area of ​​the 3D rendering model.

[0064] Step S320: Based on the drag trajectory generated by the drag event corresponding to the 3D rendering model, obtain the correction key lines corresponding to the automatically drawn outline.

[0065] In this step, the 3D rendering model refers to the automatically drawn outline of the target area, obtained from the original medical image and the automatically drawn data. The drag event corresponding to the 3D rendering model refers to the manual drag event used to modify the automatically drawn outline of the target area in the 3D rendering model. The correction key lines, i.e., the correction key lines corresponding to the automatically drawn outline, refer to the correction key lines corresponding to the automatically drawn outline obtained based on the drag trajectory generated by the manual drag event corresponding to the 3D rendering model. The specific method of obtaining the correction key lines corresponding to the automatically drawn outline based on the drag trajectory generated by the drag event corresponding to the 3D rendering model can be to generate correction key lines for modifying the automatically drawn outline at the corresponding positions in the 3D rendering model based on the drag trajectory generated by the manual drag event corresponding to the 3D rendering model.

[0066] Specifically, the drag trajectory generated by the drag event corresponding to the 3D rendering model should be located on the correct outline of the target area of ​​the 3D rendering model; the correct outline of the target area can be obtained by observing the visual display effect of the 3D rendering model.

[0067] The above embodiments effectively reduce the difficulty of modifying the drawing results of target areas in medical images by obtaining the correction key points corresponding to the automatically drawn outline based on the screen coordinates of the click event corresponding to the 3D rendering model, and obtaining the correction key lines corresponding to the automatically drawn outline based on the drag trajectory generated by the drag event corresponding to the 3D rendering model.

[0068] In one embodiment, the method for generating a correction trajectory corresponding to the automatically drawn contour when there is a significant morphological difference between the automatically drawn contour and the target drawn contour includes:

[0069] When there is a large difference in shape between the automatically drawn outline and the target drawn outline, a correction trajectory corresponding to the automatically drawn outline is generated based on the correction key points and correction key lines.

[0070] Among them, automatic contour drawing refers to the automatic contour drawing of the target area; target contour drawing can be used to represent the correct contour drawing corresponding to the target area; the target area can be the image area where the organs at risk and the tumor target area are located in the original medical image when formulating a tumor radiotherapy plan; correction key points refer to the correction key points corresponding to the automatic contour drawing, which are obtained based on the occurrence coordinates of the manual click event corresponding to the 3D rendering model; correction key lines refer to the correction key lines corresponding to the automatic contour drawing, which are obtained based on the drag trajectory generated by the manual drag event corresponding to the 3D rendering model; correction trajectory corresponding to the automatic contour drawing refers to the correction trajectory, which includes correction key points and correction key lines, obtained based on the monitoring of the manual click event and manual drag event corresponding to the 3D rendering model, and is used to make corresponding modifications to the automatic contour drawing.

[0071] In practical applications, the correct outline corresponding to the target area can be obtained by observing the visual display effect of the 3D rendering model. A specific manifestation of a large difference in shape between the automatically drawn outline and the target outline is that the degree of overlap between the automatically drawn outline and the target outline is low (that is, the area of ​​overlap between the automatically drawn outline and the target outline is small).

[0072] The above embodiments effectively reduce the difficulty of modifying the delineation results of target areas in medical images by generating a correction trajectory based on correcting key points and key lines when there is a large difference in shape between the automatically drawn contour and the target delineation contour, thereby improving the efficiency of delineating target areas in medical images.

[0073] In one embodiment, the specific method for obtaining the first automatically delineated data corresponding to the organs at risk and the second automatically delineated data corresponding to the tumor target area is as follows: Figure 4 As shown, step S110 specifically includes:

[0074] Step S410: In the original medical image, obtain the localization information corresponding to the organs at risk and the tumor target area.

[0075] In this step, the original medical image can be several tomographic images obtained by performing thin-slice scanning on the target object; the organs at risk and tumor target areas can be the organs at risk and tumor target areas that need to be delineated in the original medical image when formulating a tumor radiotherapy plan; the localization information corresponding to each organ at risk and tumor target area can be used to characterize the image area where each organ at risk and tumor target area is located in the original medical image.

[0076] Step S420: Based on the positioning information, perform image segmentation on the original medical image to obtain the first automatic delineation data corresponding to the organs at risk and the second automatic delineation data corresponding to the tumor target area.

[0077] In this step, the location information, namely the location information corresponding to the organs at risk and the tumor target area, can be used to characterize the image regions where the organs at risk and the tumor target area are located in the original medical image. Based on the location information, the specific method of image segmentation of the original medical image can be based on artificial intelligence technology to segment the image regions where the organs at risk and the tumor target area are located in the original medical image to obtain the first automatic delineation data corresponding to the organs at risk and the second automatic delineation data corresponding to the tumor target area.

[0078] The above embodiments, by segmenting the original medical image according to the location information corresponding to the organs at risk and the tumor target area, obtain the first automatic delineation data corresponding to the organs at risk and the second automatic delineation data corresponding to the tumor target area. This lays a solid data foundation for the subsequent generation of a 3D rendering model containing the automatic delineation contour of the target area, thereby ensuring the efficiency of delineating the target area in the medical image.

[0079] Regarding the specific method for obtaining the automatically drawn outline, in one embodiment, such as Figure 5As shown, step S120 specifically includes:

[0080] Step S510: Based on augmented reality technology, process the original medical image, the first automatic delineation data, and the second automatic delineation data to generate a three-dimensional rendering model.

[0081] In this step, the original medical image can be several tomographic images obtained by performing a thin-slice scan on the target object; the first automatic delineation data is the first automatic delineation data corresponding to the organs at risk; the second automatic delineation data is the second automatic delineation data corresponding to the tumor target area; the three-dimensional rendering model refers to the three-dimensional rendering model generated by processing the original medical image, the first automatic delineation data corresponding to the organs at risk, and the second automatic delineation data corresponding to the tumor target area based on augmented reality technology.

[0082] Step S520: In the 3D rendering model, different rendering color values ​​are used to render the areas corresponding to the first and second automatic drawing data respectively to obtain the automatic drawing outline.

[0083] In this step, the 3D rendering model refers to a 3D rendering model generated by processing the original medical image, the first automatically delineated data corresponding to the organs at risk, and the second automatically delineated data corresponding to the tumor target area based on augmented reality technology. The first automatically delineated data is the first automatically delineated data corresponding to the organs at risk; the second automatically delineated data is the second automatically delineated data corresponding to the tumor target area; the automatic delineation outline refers to the automatically delineated outlines corresponding to the organs at risk and the tumor target area in the 3D rendering model obtained by using different rendering color values ​​to color render the areas corresponding to the first automatically delineated data corresponding to the organs at risk and the second automatically delineated data corresponding to the tumor target area, respectively.

[0084] In practical applications, the specific representation of a 3D rendering model with automatic outline drawing can be as follows: Figure 6The method described above involves using different rendering color values ​​to color-render the regions corresponding to the first and second automatically drawn data, respectively. This can be achieved by using different rendering color values ​​for regions corresponding to different organs at risk and different tumor target areas in the 3D rendering model, thus enabling visual differentiation of these regions based on different rendering colors. Alternatively, different rendering color values ​​can be used for each region in the 3D rendering model, specifically for the regions corresponding to organs at risk and tumor target areas, to achieve the same visual differentiation. Furthermore, during the correction of the automatically drawn contours corresponding to the target areas of the 3D rendering model, different rendering color values ​​can also be used. This ensures that the visual display effects of the regions corresponding to organs at risk to be modified, tumor target areas to be modified, modified organs at risk, and modified tumor target areas are all different, thereby allowing users to distinguish these four different regions based on different rendering colors.

[0085] The above embodiments improve the visual distinction between organs at risk and tumor target areas in the 3D rendering model by using different rendering color values ​​to color render the areas corresponding to the first and second automatically drawn data respectively, thereby obtaining the automatically drawn outlines corresponding to organs at risk and tumor target areas. This effectively improves the efficiency of drawing target areas in medical images.

[0086] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0087] Based on the same inventive concept, this application also provides a medical image processing apparatus for implementing the medical image processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more medical image processing apparatus embodiments provided below can be found in the limitations of the medical image processing method described above, and will not be repeated here.

[0088] In one embodiment, such as Figure 7 As shown, a medical image processing apparatus is provided, the apparatus comprising:

[0089] The delineation data generation module 710 is used to perform image segmentation on the acquired raw medical image to obtain automatic delineation data corresponding to the target area;

[0090] The rendering model generation module 720 is used to generate a three-dimensional rendering model containing the automatically drawn outline of the target region based on the original medical image and the automatically drawn data.

[0091] The trajectory acquisition module 730 is used to listen to the interactive operation events corresponding to the 3D rendering model and acquire the correction trajectory corresponding to the automatically drawn outline.

[0092] The update result output module 740 is used to obtain the updated result of the automatically drawn contour based on the corrected trajectory.

[0093] In one embodiment, the update result output module 740 is specifically used to generate an initial update trajectory for automatically drawing the outline based on the corrected trajectory; if it is confirmed that the distance between corresponding points between the initial update trajectory and the corrected trajectory reaches a preset value, the initial update trajectory is determined as the update result; the distance is adjusted based on the distance weight corresponding to the initial update trajectory.

[0094] In one embodiment, the correction trajectory includes at least one of correction key points and correction key lines; the correction trajectory acquisition module 730 is specifically used to acquire the correction key points corresponding to the automatically drawn contour based on the screen coordinates of the click event corresponding to the 3D rendering model; and to acquire the correction key lines corresponding to the automatically drawn contour based on the drag trajectory generated by the drag event corresponding to the 3D rendering model.

[0095] In one embodiment, the correction trajectory acquisition module 730 is further configured to generate a correction trajectory corresponding to the automatically drawn contour based on the correction key points and the correction key lines when the shape difference between the automatically drawn contour and the target drawn contour is large.

[0096] In one embodiment, the delineation data generation module 710 is specifically used to obtain the location information corresponding to the organs at risk and the tumor target area in the original medical image; and to perform image segmentation on the original medical image according to the location information to obtain the first automatic delineation data corresponding to the organs at risk and the second automatic delineation data corresponding to the tumor target area.

[0097] In one embodiment, the rendering model generation module 720 is specifically used to process the original medical image, the first automatically drawn data, and the second automatically drawn data based on augmented reality technology to generate the three-dimensional rendering model; in the three-dimensional rendering model, different rendering color values ​​are used to perform color rendering on the regions corresponding to the first automatically drawn data and the second automatically drawn data respectively to obtain the automatically drawn outline.

[0098] Each module in the aforementioned medical image processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0099] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a medical image processing method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0100] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0101] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0102] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0103] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0104] 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, data stored, data displayed, 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 the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0105] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0106] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0107] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A medical image processing method, characterized in that, The method includes: The acquired raw medical images are segmented to obtain automatically drawn data corresponding to the target region; Based on the original medical image and the automatically delineated data, a 3D rendering model containing the automatically delineated outline of the target region is generated; Listen to the interactive operation events corresponding to the 3D rendering model and obtain the correction trajectory corresponding to the automatically drawn outline; Based on the corrected trajectory, the updated result of the automatically drawn contour is obtained; The step of obtaining the updated result of the automatically drawn contour based on the corrected trajectory includes: The corrected trajectory corresponding to the automatically drawn contour is input into a pre-trained neural network model to obtain the initial updated trajectory of the automatically drawn contour generated by the neural network model based on the corrected trajectory corresponding to the automatically drawn contour.

2. The method according to claim 1, characterized in that, The process of obtaining the updated result of the automatically drawn contour based on the corrected trajectory includes: Based on the corrected trajectory, the initial updated trajectory for automatically drawing the outline is generated; If it is confirmed that the distance between corresponding points between the initial updated trajectory and the corrected trajectory reaches a preset value, then the initial updated trajectory is determined as the update result; the distance is adjusted based on the distance weight corresponding to the initial updated trajectory.

3. The method according to claim 1, characterized in that, The correction trajectory includes at least one of correcting key points and correcting key lines; The process of listening to the interactive operation events corresponding to the 3D rendering model and obtaining the correction trajectory corresponding to the automatically drawn outline includes: Based on the screen coordinates of the click event corresponding to the 3D rendering model, obtain the correction key points corresponding to the automatically drawn outline; Based on the drag trajectory generated by the drag event corresponding to the 3D rendering model, the corrected key lines corresponding to the automatically drawn outline are obtained.

4. The method according to claim 3, characterized in that, The method further includes: When there is a large difference in shape between the automatically drawn contour and the target drawn contour, a correction trajectory corresponding to the automatically drawn contour is generated based on the correction key points and the correction key lines.

5. The method according to claim 1, characterized in that, The step of segmenting the acquired raw medical image to obtain automatically delineated data corresponding to the target region includes: From the original medical images, obtain the localization information corresponding to the organs at risk and the tumor target areas; Based on the location information, the original medical image is segmented to obtain first automatic delineation data corresponding to the organ at risk and second automatic delineation data corresponding to the tumor target area.

6. The method according to claim 5, characterized in that, The step of generating a 3D rendering model containing the automatically delineated outline of the target region based on the original medical image and the automatically delineated data includes: Based on augmented reality technology, the original medical image, the first automatically drawn data, and the second automatically drawn data are processed to generate the three-dimensional rendering model; In the three-dimensional rendering model, different rendering color values ​​are used to render the regions corresponding to the first and second automatically drawn data respectively, so as to obtain the automatically drawn outline.

7. A medical image processing device, characterized in that, The device includes: The delineation data generation module is used to perform image segmentation on the acquired raw medical images to obtain automatic delineation data corresponding to the target region; The rendering model generation module is used to generate a three-dimensional rendering model containing the automatically drawn outline of the target region based on the original medical image and the automatically drawn data. The trajectory acquisition module is used to listen to the interactive operation events corresponding to the 3D rendering model and acquire the correction trajectory corresponding to the automatically drawn outline. The update result output module is used to obtain the updated result of the automatically drawn contour based on the corrected trajectory; The update result output module is further configured to input the corrected trajectory corresponding to the automatically drawn contour into a pre-trained neural network model to obtain the initial update trajectory of the automatically drawn contour generated by the neural network model based on the corrected trajectory corresponding to the automatically drawn contour.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images