Grinding area planning method and device, electronic equipment and storage medium

Abstract

The application relates to a grinding area planning method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: obtaining medical image data of a hip joint part of a target object; inputting the medical image data into a pre-trained deep learning model to obtain bone tissue data and position information of a hip socket center point output by the deep learning model; generating a pelvis model to be ground based on the bone tissue data; determining a grinding area of the pelvis model according to the pelvis model, the position information and a preset acetabular cup model, and visually displaying the pelvis model and the grinding area. Through the application, the problem that manual segmentation based on pelvis tissue depends on the experience and proficiency of operators in the related art, resulting in low segmentation efficiency and low segmentation accuracy, is solved, automatic segmentation of medical image data based on a pre-trained deep learning model is realized, the segmentation accuracy and efficiency can be improved, and the pelvis model and the grinding area can be visually displayed.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to methods, apparatus, electronic devices and storage media for planning abrasive areas. Background Technology

[0002] Currently, before performing hip surgery, doctors mostly plan the procedure based on X-rays and computed tomography (CT) images, then determine the depth and extent of the acetabular fossa based on experience. However, X-rays are two-dimensional images, providing only observation of a single direction and angle, and cannot determine the true depth of the acetabular fossa; CT images are three-dimensional, but the morphology of the acetabulum is based on the result of manual segmentation of pelvic tissue. This manual segmentation process requires the use of third-party software to manually locate and identify the acetabulum on each multi-planar reconstruction (MPR) image, which is tedious and inefficient. Moreover, the segmentation accuracy is highly dependent on the operator's experience and skill; inaccurate segmentation results will directly lead to incorrect identification of the acetabular fossa.

[0003] There is currently no effective solution to the problem that manual segmentation of pelvic tissue in related technologies relies on the operator's experience and skill, resulting in low segmentation efficiency and accuracy. Summary of the Invention

[0004] This embodiment provides a method, apparatus, electronic device, and storage medium for planning abrasive areas, in order to solve the problems in related technologies where manual segmentation based on pelvic tissue relies on the operator's experience and skill, resulting in low segmentation efficiency and low segmentation accuracy.

[0005] Firstly, this embodiment provides a grinding area planning device, comprising:

[0006] Acquire medical image data of the hip joint area of ​​the target object;

[0007] The medical image data is input into a pre-trained deep learning model to obtain bone tissue data and the location information of the center point of the acetabulum output by the deep learning model.

[0008] Based on the bone tissue data, a pelvic bone model to be ground and filed is generated;

[0009] Based on the pelvic model, the position information, and the preset acetabular cup model, the grinding area of ​​the pelvic model is determined, and the pelvic model and the grinding area are visualized.

[0010] In some embodiments, determining the grinding area of ​​the pelvic model based on the pelvic model, the position information, and a preset acetabular cup model includes:

[0011] Using the location information as the center and the acetabular cup size in the preset acetabular cup model as the diameter, a hemispherical model is generated;

[0012] The grinding area is determined based on the intersection of the hemispherical model and the pelvic model.

[0013] In some embodiments, determining the abrasion area based on the intersection of the hemispherical model and the pelvic model includes:

[0014] Transform the hemispherical model and the pelvic model to the world coordinate system;

[0015] In the world coordinate system, based on the coordinates of the points constituting the hemispherical model and the coordinates of the points constituting the pelvic model, it is determined whether the hemispherical model and the pelvic model intersect.

[0016] If the hemispherical model and the pelvic model intersect, the set of intersecting points is determined, and an intersection model is generated as the filing area based on the set of points.

[0017] In some embodiments, the grinding area planning method further includes:

[0018] The medical image data is reconstructed and then rendered to obtain a multi-layered reconstructed view.

[0019] In some embodiments, the grinding area planning method further includes:

[0020] Based on the coordinates of the points in the filing area, obtain the voxels at the corresponding coordinate positions, and label the voxels according to preset tags;

[0021] The multi-layered reconstructed view is rendered. If there are voxels with preset labels on the multi-layered reconstructed view, a filing outline is drawn at the corresponding voxel on the multi-layered reconstructed view.

[0022] In some embodiments, the grinding area planning method further includes:

[0023] The difference between the hemispherical model and the filed area is calculated to obtain the difference model, which is then visualized.

[0024] In some embodiments, generating a pelvic model to be ground based on the bone tissue data includes:

[0025] The bone tissue data is converted to a different format.

[0026] Using a 3D modeling tool, the bone tissue data after format conversion is smoothed and subdivided to obtain a pelvic bone model to be ground.

[0027] Secondly, this embodiment provides a grinding area planning device, including: an acquisition module, a segmentation module, a processing module, and a determination and display module;

[0028] The acquisition module is used to acquire medical image data of the hip joint of the target object;

[0029] The segmentation module is used to input the medical image data into a pre-trained deep learning model to obtain bone tissue data and the location information of the center point of the acetabulum output by the deep learning model.

[0030] The processing module is used to generate a pelvic bone model to be ground and filed based on the bone tissue data.

[0031] The determination and display module is used to determine the grinding area of ​​the pelvic model based on the pelvic model, the position information, and the preset acetabular cup model, and to visually display the pelvic model and the grinding area.

[0032] Thirdly, this embodiment provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the grinding area planning method described in the first aspect above.

[0033] Fourthly, this embodiment provides a storage medium storing a computer program that, when executed by a processor, implements the grinding area planning method described in the first aspect above.

[0034] Compared with related technologies, the grinding area planning method, device, electronic device, and storage medium provided in this embodiment acquire medical image data of the hip joint of the target object; input the medical image data into a pre-trained deep learning model to obtain bone tissue data and the position information of the acetabular fossa center point output by the deep learning model; generate a pelvic model to be ground based on the bone tissue data; determine the grinding area of ​​the pelvic model according to the pelvic model, the position information, and a preset acetabular cup model, and visualize the pelvic model and the grinding area; solve the problem in related technologies where manual segmentation based on pelvic tissue relies on the operator's experience and proficiency, resulting in low segmentation efficiency and low segmentation accuracy, and realize automatic segmentation of medical image data based on a pre-trained deep learning model, which can improve segmentation accuracy and efficiency, and visualize the pelvic model and the grinding area.

[0035] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0036] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0037] Figure 1 This is a hardware structure block diagram of a terminal device for a grinding area planning method provided in an embodiment of this application;

[0038] Figure 2 This is a flowchart of a grinding area planning method provided in an embodiment of this application;

[0039] Figure 3 This is a flowchart of an embodiment of the present application providing the process for determining the filing area;

[0040] Figure 4 This is a flowchart illustrating a preferred embodiment of the grinding area planning method provided in this application;

[0041] Figure 5 This is a structural block diagram of a grinding and filing area planning device provided in an embodiment of this application.

[0042] In the diagram: 210, Acquisition module; 220, Segmentation module; 230, Processing module; 240, Display determination module. Detailed Implementation

[0043] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0044] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning as understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0045] The method embodiments provided in this example can be executed on a terminal, computer, or similar computing device. For example, it can run on a terminal. Figure 1 This is a hardware structure block diagram of the terminal of the grinding area planning method in this embodiment. For example... Figure 1 As shown, a terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 and a memory 104 for storing data are also included. The processor 102 may be, but is not limited to, a microprocessor (MCU) or a programmable logic device (FPGA). The terminal may also include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal described above. For example, the terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0046] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the grinding area planning method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0047] The transmission device 106 is used to receive or send data via a network. This network includes a wireless network provided by the terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 can be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0048] This embodiment provides a method for planning a grinding area. Figure 2 This is a flowchart of the grinding and filing area planning method in this embodiment, as follows: Figure 2 As shown, the process includes the following steps:

[0049] Step S210: Obtain medical image data of the hip joint of the target object;

[0050] Step S220: Input medical image data into a pre-trained deep learning model to obtain bone tissue data and the location information of the center point of the acetabulum output by the deep learning model;

[0051] Step S230: Based on bone tissue data, generate a pelvic bone model to be ground and filed;

[0052] Step S240: Based on the pelvic model, position information, and preset acetabular cup model, determine the grinding area of ​​the pelvic model and visualize the pelvic model and grinding area.

[0053] Specifically, the target object can be a human or an animal such as a monkey. Medical image data can be CT scan images; CT scan images of the hip joint are obtained in DICOM (Digital Imaging and Communications in Medicine) format during CT scans of the hip joint. This hip joint CT scan image data includes, but is not limited to, CT scan images of the pelvis and femur at the hip joint. The deep learning model is pre-trained. The training and test sets of the deep learning model can be a large amount of labeled CT scan image data, which will label bone tissue data (e.g., left and right pelvic bones, left and right femurs) and the features of the acetabular fossa center location, thus completing the training of the deep learning model. Therefore, by inputting the medical image data of the target object's hip joint into the pre-trained deep learning model, the deep learning model can identify the bone tissue data and the location information of the acetabular fossa center point. Deep learning models include, but are not limited to, recurrent neural networks (RNNs), recursive neural networks (RNNs), convolutional neural networks (CNNs), and deep generative models (DGMs).

[0054] To improve accuracy, a pelvic model to be filed is generated based on bone tissue data. Specifically, the converted bone tissue data needs to be smoothed and subdivided to obtain the pelvic model. Further smoothing and subdivision can be performed using 3D modeling tools to process the bone tissue data and obtain the pelvic model. These 3D modeling tools include, but are not limited to, software such as Mimics, MeshMixer, and MeshLab. Since the segmented bone tissue data is in Mask format (referred to as Mask data), and Mask data only carries label information, it cannot be visualized and rendered on the interface. Moreover, Mask data represents different tissues within the same dataset using different labels, with different tissues coupled together, making individual operation inconvenient. Therefore, it is necessary to convert the Mask data into Mesh format (referred to as Mesh data) to smooth and subdivide the bone tissue data in Mesh format. In other embodiments, a femoral model, etc., can also be generated based on the bone tissue data.

[0055] Through the above steps, medical image data is first automatically segmented based on a pre-trained deep learning model, and then a pelvic model to be reshaped is generated based on bone tissue data, thereby improving segmentation accuracy and efficiency. Finally, the reshaping area is determined based on the pelvic model, the location information of the acetabular fossa center point, and the preset acetabular cup model, and the pelvic model and reshaping area are visualized to complete the planning of the reshaping area; without manual intervention, this solves the problem in related technologies where manual segmentation based on pelvic tissue relies on the operator's experience and skill, resulting in low segmentation efficiency and low segmentation accuracy.

[0056] The following is a detailed explanation of each step:

[0057] In some of these embodiments, such as Figure 3 As shown, defining the filing area includes the following steps:

[0058] Step S241: Using the position information as the center and the acetabular cup size in the preset acetabular cup model as the diameter, generate a hemispherical model;

[0059] Step S242: Determine the grinding area based on the intersection of the hemispherical model and the pelvic model.

[0060] Specifically, the hemispherical model is used to determine the refining area in the pelvic model. It is a hemispherical surface mesh model generated with the position information of the center point of the acetabular fossa as the center and the acetabular cup size in the preset acetabular cup model as the diameter. The acetabular cup model is preset, and each acetabular cup model has corresponding size parameters, with the acetabular cup size being one of them. Therefore, after selecting an acetabular cup model, the acetabular cup size can be determined. Thus, the refining area can be determined based on the intersection of the hemispherical model and the pelvic model. In this embodiment, the refining area is the intersection model of the hemispherical model and the pelvic model.

[0061] Specifically, step S242 includes the following steps:

[0062] Transform the hemispherical and pelvic models to the world coordinate system;

[0063] In the world coordinate system, based on the coordinates of the points that constitute the hemispherical model and the coordinates of the points that constitute the pelvic model, determine whether the hemispherical model and the pelvic model intersect.

[0064] If the hemispherical model and the pelvic model intersect, the set of intersecting points is determined, and the intersection model is generated as the grinding area based on the set of points.

[0065] Specifically, both the hemispherical and pelvic models are mesh data, containing the coordinate positions and number of points and faces. The hemispherical and pelvic models can be transformed to the world coordinate system using a transformation matrix. In the world coordinate system, the distance between the points constituting the hemispherical model and the points constituting the pelvic model is calculated to determine whether the hemispherical and pelvic models intersect. If the hemispherical and pelvic models intersect, the set of intersecting points is determined, and the CGAL library is used to perform triangular meshing on the intersecting set to generate the intersection model as the filing area.

[0066] In some embodiments, the provided method for planning the abrasive area further includes the following steps:

[0067] The difference between the hemispherical model and the filed area is calculated to obtain the difference model, which is then visualized.

[0068] Specifically, the difference set model is obtained by calculating the difference between the points constituting the hemispherical model and the points constituting the filing region through difference set operations. In other words, after removing the points in the filing region from the points in the hemispherical model, the remaining points are meshed using the CGAL library to generate the difference set model for visualization. The difference set model can also be considered as the residual model.

[0069] In some embodiments, the provided method for planning the filing area further includes:

[0070] After reconstructing the medical image data, a multi-layered reconstructed view is obtained.

[0071] Specifically, rendering can be achieved based on a pre-configured image rendering engine library. For medical image data (DICOM data), the rendered image is presented on the interface as a multi-plane reconstruction (MPR) view. The MPR view includes three views: coronal reconstruction, sagittal reconstruction, and transverse reconstruction. For pelvic model (mesh data), the rendered image is presented on the interface as a 3D mesh view. The image rendering engine library can also be implemented using a GIS+BIM 3D visualization rendering engine; there are no restrictions on which one is used.

[0072] To facilitate user browsing, the multi-layered reconstruction views and 3D mesh views are displayed according to a preset page layout format; specifically, in a left-right layout. That is, a large 3D mesh view is placed on the left, and three smaller multi-layered reconstruction views (coronal plane reconstruction view, sagittal plane reconstruction view, and cross-sectional reconstruction view) are placed in a column on the right. Figure 3 (View from different angles). For example: display in a 1x3 page layout format; a 1x3 page can be a side-by-side layout or a top-bottom layout.

[0073] For example, in a left-right layout: a large 3D mesh view is placed on the left, and three smaller multi-layered reconstruction views (coronal plane reconstruction view, sagittal plane reconstruction view, and cross-sectional reconstruction view) are placed in a column on the right. Figure 3 (Views in all directions). Additionally, if the user wants to focus on viewing the coronal, sagittal, and transverse reconstructed views... Figure 3 One of these images, in a 1x3 layout, can be switched using a toggle button to move the smaller image on the right to the larger view on the left for easier observation. Alternatively, a large 3D mesh view can be placed on the right, with three smaller multi-layered reconstruction views (coronal plane reconstruction, sagittal plane reconstruction, and cross-sectional reconstruction) arranged in a column on the left. Figure 3 (View from all directions).

[0074] For example, in a top-bottom layout: a large 3D mesh view is placed on the top, and three smaller multi-layered reconstruction views (coronal plane reconstruction view, sagittal plane reconstruction view, and cross-sectional reconstruction view) are placed in a row on the bottom. Figure 3 (Views from various angles). In other embodiments, the page layout format may also take other forms, such as a 2x2 page layout format, which will not be elaborated here.

[0075] In some embodiments, the grinding area planning method further includes:

[0076] Based on the coordinates of the points in the filing area, obtain the voxels at the corresponding coordinate positions, and label the voxels according to the preset labels;

[0077] Render the multi-layered reconstructed view. If there are voxels with preset labels on the multi-layered reconstructed view, draw the filing outline at the corresponding voxel on the multi-layered reconstructed view.

[0078] In this model, the points forming the hemispherical model and the points forming the pelvic model intersect, and the set of points in the grinding region is the set of points. The coordinates of these points refer to the coordinates of the points in this grinding region. These point sets form grids, and each point can be considered a grid point. Coordinate transformation can be used to find the coordinates of the corresponding voxels based on the grid point coordinates, thus obtaining the corresponding voxels. For example, the grid point coordinates can be transformed to the world coordinate system, and then from the world coordinate system to the voxel coordinate system to match the grid point coordinates and voxel coordinates, thereby obtaining the corresponding voxels. When rendering multi-layered reconstructed views, different colors can be assigned to voxels with different labels.

[0079] Specifically, the coordinates of the grid points corresponding to the point set in the filing region can be used to obtain the coordinates of the corresponding voxels, thereby obtaining the corresponding voxels. Then, preset labels are selected to label the obtained voxels. When rendering the plane of a multi-layered reconstructed view, since the multi-layered reconstructed view includes the coronal plane reconstructed view, the sagittal plane reconstructed view, and the cross-sectional reconstructed view... Figure 3 The view is presented from three different angles. This means that three planes need to be rendered. Therefore, it's necessary to determine whether there are voxels corresponding to the point set of the grinding region on these three planes of the multi-layered reconstructed view, and to identify these voxels. If they exist, the grinding outline of the grinding region on the corresponding plane in the multi-layered reconstructed view is drawn based on that voxel. During drawing, a specific color corresponding to a preset label can be used. The drawn area is the filled area where the corresponding grinding regions intersect in the multi-layered reconstructed view. This embodiment can more accurately locate the planned grinding region in the acetabular tissue.

[0080] In this embodiment, the grinding area is a three-dimensional mesh, but this is not convenient for precise positioning. Therefore, the boundaries of the three-dimensional mesh need to be drawn as contour lines (grinding contour lines) on the multi-layer reconstruction view, which makes it easier for users to identify the location of the grinding area in the acetabular tissue. The specific steps are as follows:

[0081] 1. Based on a specific orientation, first determine a specific view (such as the coronal plane reconstruction view) from the multi-layered reconstruction view (coronal plane reconstruction view, sagittal plane reconstruction view, and cross-sectional reconstruction view); obtain the corresponding normal vector and points on the plane of the coronal plane reconstruction view;

[0082] 2. Calculate the distance between a point on the filing area and a point on the plane. If the distance is less than 1e-5, then determine that the point is on the plane.

[0083] 3. Record the point on the current plane where the filing area is located;

[0084] 4. Based on the coordinates of the points in the recorded filing area, obtain the voxels at the corresponding coordinate positions, and label the voxels according to the preset labels;

[0085] 5. Render the coronal plane reconstruction view. If there are voxels with preset labels on the coronal plane reconstruction view, draw the filing outline at the corresponding voxel in the coronal plane reconstruction view.

[0086] 6. Other multi-layered reconstructed views are processed in sequence according to steps 1-5.

[0087] Through the above steps, the boundaries of the 3D mesh are drawn onto the multi-layered reconstructed view as outlines.

[0088] In some of these embodiments, after obtaining the bone tissue data, the bone tissue data is converted to a different format; and a 3D modeling tool is used to smooth and subdivide the converted bone tissue data to obtain a pelvic bone model to be ground.

[0089] Since the segmented bone tissue data is masked data, it can be converted into mesh data and saved as STL format bone tissue data for easier subsequent calculations. This allows 3D modeling tools to directly use the data without requiring further data processing, simplifying the smoothing and subdivision steps.

[0090] like Figure 4 As shown, the following describes and illustrates this embodiment through preferred embodiments.

[0091] Acquire medical image data of the hip joint of the target object; use a pre-trained deep learning model to segment the medical image data to obtain bone tissue data and the location information of the center point of the acetabulum; convert the bone tissue data into Mesh data and save it as STL format bone tissue data according to bone tissue; use 3D modeling tools (such as Mimics, MeshMixer, MeshLab) to smooth and subdivide the format-converted bone tissue data to obtain the pelvic bone model to be ground.

[0092] Simultaneously, the medical image data is rendered using an image rendering engine library to produce a multi-layered reconstructed view; the pelvic model is also rendered using the same library to produce a 3D mesh view, which is then displayed in a 1x3 page layout format. Next, using the location information of the acetabular fossa center as the center and the acetabular cup size in the preset acetabular cup model as the diameter, a hemispherical model with a surface mesh is automatically generated. This hemispherical model is similar to the acetabular reamer used in actual surgery and is only used for calculation, not for display. Subsequently, the intersection and difference between the hemispherical model and the pelvic model are calculated. The intersection model is considered the reaming region, and the difference is considered the remaining model.

[0093] The reamer view allows users to see the location of the reamer region in the acetabular fossa on the surgical side from a 3D perspective. Simultaneously, based on the grid point coordinates of the intersection model of the reamer region, voxels at the corresponding coordinate positions are obtained. These voxels are then used to render the original medical image data on the transverse, coronal, and sagittal planes. For example, voxels at the corresponding coordinate positions are labeled with specific tags. When rendering the transverse, coronal, and sagittal planes, it is determined whether a voxel with a specific tag for the reamer region exists on the plane. If it does, the reamer outline of the reamer region on that plane is simultaneously drawn on the multi-plane reconstruction (MPR) view, thereby more accurately locating the planned reamer region within the acetabular tissue.

[0094] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures 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 may be executed in a different order than that shown here.

[0095] This embodiment also provides a grinding area planning device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as described above. The terms "module," "unit," "subunit," etc., used below can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0096] Figure 5 This is a structural block diagram of the grinding and filing area planning device in this embodiment, as shown below. Figure 5 As shown, the device includes: an acquisition module 210, a segmentation module 220, a processing module 230, and a determination and display module 240;

[0097] The acquisition module 210 is used to acquire medical image data of the hip joint of the target object;

[0098] The segmentation module 220 is used to input medical image data into a pre-trained deep learning model to obtain bone tissue data and the location information of the center point of the acetabulum output by the deep learning model.

[0099] Processing module 230 is used to generate a pelvic bone model to be ground based on bone tissue data;

[0100] The display module 240 is used to determine the grinding area of ​​the pelvic model based on the pelvic model, position information, and a preset acetabular cup model, and to visualize the pelvic model and the grinding area.

[0101] The aforementioned abrasion area planning device solves the problem in related technologies where manual segmentation of pelvic tissue relies on the operator's experience and skill, resulting in low segmentation efficiency and accuracy. It enables automatic segmentation of medical image data based on a pre-trained deep learning model, improving segmentation accuracy and efficiency, and visually displaying the pelvic model and abrasion area.

[0102] In some embodiments, the display module 240 includes a calculation unit and an intersection processing unit;

[0103] The calculation unit is used to generate a hemispherical model with the position information as the center and the acetabular cup size in the preset acetabular cup model as the diameter;

[0104] The intersection processing unit is used to determine the grinding area based on the intersection of the hemispherical model and the pelvic model.

[0105] In some embodiments, the intersection processing unit is also used to transform the hemispherical model and the pelvic model to the world coordinate system;

[0106] In the world coordinate system, based on the coordinates of the points that constitute the hemispherical model and the coordinates of the points that constitute the pelvic model, determine whether the hemispherical model and the pelvic model intersect.

[0107] If the hemispherical model and the pelvic model intersect, the set of intersecting points is determined, and the intersection model is generated as the grinding area based on the set of points.

[0108] In some embodiments, the display module 240 further includes a rendering unit;

[0109] The rendering unit is used to render reconstructed medical image data to obtain a multi-layered reconstructed view.

[0110] In some of these embodiments, the rendering unit is also used to obtain the voxel at the corresponding coordinate position based on the coordinates of the point in the filing area, and to label the voxel according to a preset label.

[0111] Render the multi-layered reconstructed view. If there are voxels with preset labels on the multi-layered reconstructed view, draw the filing outline at the corresponding voxel on the multi-layered reconstructed view.

[0112] In some embodiments, the display module 240 further includes a difference processing unit;

[0113] The difference processing unit is used to perform a difference operation between the hemispherical model and the filed area to obtain the difference model, and then visualize the difference model.

[0114] In some embodiments, the processing module 230 is also used to convert the bone tissue data into a format; and to smooth and subdivide the converted bone tissue data using a 3D modeling tool to obtain a pelvic bone model to be ground.

[0115] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0116] This embodiment also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0117] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0118] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0119] S1, acquire medical image data of the hip joint of the target object;

[0120] S2, input medical image data into a pre-trained deep learning model to obtain bone tissue data and the location information of the center point of the acetabulum output by the deep learning model;

[0121] S3, based on bone tissue data, generates a pelvic model to be ground and filed;

[0122] S4. Based on the pelvic model, position information, and the preset acetabular cup model, determine the grinding area of ​​the pelvic model and visualize the pelvic model and the grinding area.

[0123] The aforementioned electronic device solves the problem in related technologies where manual segmentation of pelvic tissue relies on the operator's experience and skill, resulting in low segmentation efficiency and accuracy. It enables automatic segmentation of medical image data based on a pre-trained deep learning model, which can improve segmentation accuracy and efficiency, and visualize the pelvic model and the abrasion area.

[0124] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0125] Furthermore, in conjunction with the filing area planning method provided in the above embodiments, this embodiment can also provide a storage medium for implementation. The storage medium stores a computer program; when executed by a processor, the computer program implements any of the filing area planning methods in the above embodiments.

[0126] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0127] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0128] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0129] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. 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 scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A method for planning a grinding area, characterized in that, include: Acquire medical image data of the hip joint area of ​​the target object; The medical image data is input into a pre-trained deep learning model to obtain bone tissue data and the location information of the center point of the acetabulum output by the deep learning model. Based on the bone tissue data, a pelvic bone model to be ground and filed is generated; Based on the pelvic model, the position information, and the preset acetabular cup model, the grinding area of ​​the pelvic model is determined, and the pelvic model and the grinding area are visualized; wherein, determining the grinding area of ​​the pelvic model based on the pelvic model, the position information, and the preset acetabular cup model includes: Using the location information as the center and the acetabular cup size in the preset acetabular cup model as the diameter, a hemispherical model is generated; The grinding area is determined based on the intersection of the hemispherical model and the pelvic model.

2. The method for planning the grinding and filing area according to claim 1, characterized in that, The step of determining the abrasion area based on the intersection of the hemispherical model and the pelvic model includes: Transform the hemispherical model and the pelvic model to the world coordinate system; In the world coordinate system, based on the coordinates of the points constituting the hemispherical model and the coordinates of the points constituting the pelvic model, it is determined whether the hemispherical model and the pelvic model intersect. If the hemispherical model and the pelvic model intersect, the set of intersecting points is determined, and an intersection model is generated as the filing area based on the set of points.

3. The method for planning the grinding and filing area according to claim 1, characterized in that, Also includes: The medical image data is reconstructed and then rendered to obtain a multi-layered reconstructed view.

4. The grinding and filing area planning method according to claim 3, characterized in that, Also includes: Based on the coordinates of the points in the filing area, obtain the voxels at the corresponding coordinates, and label the voxels according to preset labels; If there are voxels carrying preset labels on the multi-layered reconstructed view, then a filing outline is drawn at the corresponding voxel on the multi-layered reconstructed view.

5. The method for planning the grinding and filing area according to claim 1, characterized in that, Also includes: The difference between the hemispherical model and the filed area is calculated to obtain the difference model, which is then visualized.

6. The method for planning the grinding and filing area according to claim 1, characterized in that, The process of generating a pelvic model to be ground based on the bone tissue data includes: The bone tissue data is converted to a different format. Using a 3D modeling tool, the bone tissue data after format conversion is smoothed and subdivided to obtain a pelvic bone model to be ground.

7. A grinding and filing area planning device, characterized in that, include: The module includes an acquisition module, a segmentation module, a processing module, and a display determination module. The acquisition module is used to acquire medical image data of the hip joint of the target object; The segmentation module is used to input the medical image data into a pre-trained deep learning model to obtain bone tissue data and the location information of the center point of the acetabulum output by the deep learning model. The processing module is used to generate a pelvic bone model to be ground and filed based on the bone tissue data. The determination and display module is used to determine the grinding area of ​​the pelvic model based on the pelvic model, the position information, and the preset acetabular cup model, and to visually display the pelvic model and the grinding area. The determination display module is further configured to generate a hemispherical model with the position information as the center and the acetabular cup size in the preset acetabular cup model as the diameter; and to determine the grinding area based on the intersection of the hemispherical model and the pelvic model.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the grinding area planning 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 the processor, it implements the steps of the abrasive area planning method as described in any one of claims 1 to 6.

Images