Preoperative planning method and device for hip protection surgery

Abstract

The invention provides a hip protection surgery preoperative planning method and device. The method comprises the steps that a hip joint CT image of a single object is acquired; constructing a skeleton three-dimensional model according to the hip joint CT image; according to the three-dimensional skeleton model, key points of hip joints and necrosis areas of femoral heads are identified, and osteotomy information and femoral head adjustment information are generated; and displaying the osteotomy information and the femoral head adjustment information, and performing fine adjustment according to the operation of an operator. According to the method and the device, the three-dimensional model of the skeleton is constructed through the preoperative medical image, so that the osteotomy position and the adjustment information of the femoral head are planned, and strong support of the osteotomy position can be provided for the femoral neck rotation osteotomy through the preoperative planning.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and in particular to a method and device for preoperative planning of hip preservation surgery. Background Art

[0002] Femoral neck rotation osteotomy is a corrective surgery used to treat hip joint diseases. It aims to relieve hip pain, restore function and improve long-term prognosis by rotating the femoral neck at a specific location to redistribute the weight-bearing area of ​​the hip joint.

[0003] Preoperative planning in hip-preserving surgery can provide strong support for the osteotomy position of femoral neck rotation osteotomy, but there is currently a lack of specific plans in this regard. Summary of the invention

[0004] The problem addressed by this application is the current lack of preoperative planning for hip preservation surgery.

[0005] In order to solve the above problems, the first aspect of the present application provides a preoperative planning method for hip preservation surgery, which comprises:

[0006] Acquire a single subject's hip CT image;

[0007] constructing a three-dimensional bone model according to the hip joint CT image;

[0008] According to the three-dimensional bone model, identifying key points of the hip joint and necrotic areas of the femoral head, and generating osteotomy information and femoral head adjustment information;

[0009] The osteotomy information and femoral head adjustment information are displayed, and fine-tuned according to the operator's operation.

[0010] The second aspect of the present application provides a manufacturing system for a preoperative planning method for hip preservation surgery, which comprises:

[0011] An image acquisition module, which is used to acquire a hip joint CT image of a single subject;

[0012] A three-dimensional construction module, which is used to construct a three-dimensional bone model according to the hip joint CT image;

[0013] An osteotomy generation module, which is used to identify key points of the hip joint and necrotic areas of the femoral head according to the three-dimensional bone model, and generate osteotomy information and femoral head adjustment information;

[0014] The osteotomy adjustment module is used to display the osteotomy information and femoral head adjustment information, and perform fine adjustments according to the operator's operation.

[0015] The third aspect of the present application provides an electronic device, comprising: a memory and a processor; the memory may be configured to store a program, and the processor is coupled to the memory and is used to execute the program in the memory, so as to:

[0016] Acquire a single subject's hip CT image;

[0017] constructing a three-dimensional bone model according to the hip joint CT image;

[0018] According to the three-dimensional bone model, identifying key points of the hip joint and necrotic areas of the femoral head, and generating osteotomy information and femoral head adjustment information;

[0019] The osteotomy information and femoral head adjustment information are displayed, and fine-tuned according to the operator's operation.

[0020] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the program is executed by a processor to implement the aforementioned preoperative planning method for hip-preserving surgery.

[0021] In this application, a three-dimensional model of the bone is constructed through preoperative medical images, so as to plan the osteotomy position and adjustment information of the femoral head. Through this preoperative planning, strong support for the osteotomy position can be provided for femoral neck rotation osteotomy. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of a method for preoperative planning of hip preservation surgery according to an embodiment of the present application;

[0023] Figure 2 A model architecture diagram of necrosis identification in a preoperative planning method for hip preservation surgery according to an embodiment of the present application;

[0024] Figure 3 A schematic diagram of a three-dimensional bone model of a preoperative planning method for hip preservation surgery according to an embodiment of the present application;

[0025] Figure 4 A schematic diagram showing osteotomy according to a preoperative planning method for hip preservation surgery according to an embodiment of the present application;

[0026] Figure 5 A schematic diagram of the intact rate of hip joint after surgery according to the preoperative planning method for hip preservation surgery in an embodiment of the present application;

[0027] Figure 6 This is a schematic diagram of a preoperative planning device for hip preservation surgery according to an embodiment of the present application;

[0028] Figure 7 is an architectural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application are described in detail below in conjunction with the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0030] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by technicians in the field to which this application belongs.

[0031] The present application embodiment provides the above-mentioned hip preservation surgery preoperative planning method, the specific scheme of the method is as follows: Figure 1-Figure 4 As shown, the method can be performed by a hip preservation surgery preoperative planning device, and the hip preservation surgery preoperative planning device can be integrated into electronic devices such as computers, servers, computers, server clusters, and data centers. Figure 1 As shown, the preoperative planning method for hip preservation surgery includes:

[0032] S101, acquiring a hip joint CT image of a single subject;

[0033] In this application, CT scanning technology is used to obtain cross-sectional imaging data of the patient's hip joint, including the complete structure of the femoral head, femoral neck and acetabulum.

[0034] In the present application, after acquiring the hip joint CT image of a single object, the hip joint CT image is also preprocessed.

[0035] The specific preprocessing can be: Image denoising: Use median filtering or Gaussian filtering to remove noise in CT images. Image enhancement: Use histogram equalization to increase the contrast of the image and highlight the bone structure.

[0036] S102, constructing a three-dimensional bone model according to the hip joint CT image;

[0037] The specific construction process can be:

[0038] Image segmentation: Segment the hip joint region (including the femoral head, femoral neck, and acetabulum) from the CT image. Use a deep learning segmentation model (such as UNet or DeepLab) or traditional segmentation methods (threshold segmentation + region growing). Extract the region of interest (ROI) of the bone.

[0039] 3D reconstruction: Stack the segmented CT slice data to generate volume data. Use surface reconstruction algorithms (such as Marching Cubes) to generate a 3D surface mesh of the bone. The 3D bone model includes the complete morphology and spatial position information of the bone.

[0040] Optimize the model: Denoising: Use mesh smoothing algorithms (such as Laplacian Smoothing) to reduce model surface noise. Mesh simplification: Use mesh simplification algorithms to reduce model complexity and improve subsequent operation efficiency.

[0041] S103, identifying key points of the hip joint and necrotic areas of the femoral head according to the three-dimensional bone model, and generating osteotomy information and femoral head adjustment information;

[0042] In this application, a bone morphology feature extraction algorithm (such as curvature analysis) can be used to automatically identify key points. A deep learning model (such as a key point detection model) can also be used to enhance the accuracy of key point recognition.

[0043] In the present application, the bone density threshold (HU value) of CT images can be used to distinguish healthy bones from necrotic bones. MRI combined with CT images can be used to segment the necrotic area and generate a three-dimensional model of the necrotic area.

[0044] S104, displaying the osteotomy information and femoral head adjustment information, and performing fine adjustments according to the operator's operation.

[0045] In this application, the visualization content may include: a 3D bone model (femoral head, femoral neck and acetabulum), a 3D morphology and position of the femoral head necrosis area, a 3D display of the osteotomy plane and osteotomy line, and a rotation effect of the femoral head after adjustment.

[0046] In this application, the results can be presented using 3D modeling software (such as Mimics, 3D Slicer) or a custom visualization system.

[0047] In this application, the following contents are fine-tuned: Osteotomy plane: The operator can adjust the osteotomy starting point, end point and rotation angle. Femoral head rotation angle: Fine-tune the rotation axis and rotation angle according to the distribution of the healthy area. Overlap area optimization: The operator can ensure maximum overlap between the healthy area and the acetabular weight-bearing area by adjusting the parameters.

[0048] In this application, a three-dimensional model of the bone is constructed through preoperative medical images, so as to plan the osteotomy position and adjustment information of the femoral head. Through this preoperative planning, strong support for the osteotomy position can be provided for femoral neck rotation osteotomy.

[0049] In this application, three-dimensional modeling and key point recognition are combined to accurately locate the necrotic area and osteotomy plane.

[0050] In this application, a customized surgical plan is generated based on the patient's anatomical structure.

[0051] In this application, the operator can fine-tune the planning results to ensure that the plan meets actual needs.

[0052] In this application, osteotomy and adjustment plans are intuitively displayed to assist doctors in making decisions.

[0053] In this application, CT imaging and three-dimensional modeling technology, combined with interactive adjustment tools, provide a comprehensive and efficient solution for preoperative planning of rotational osteotomy, which helps to improve the success rate of surgery and patient prognosis.

[0054] In a specific embodiment, the key points of the hip joint include at least: the center of the femoral head, the femoral neck mid-axis reference point, the acetabulum center point, and the distal femoral condylar center point.

[0055] In this application, in the preoperative planning of hip rotation osteotomy, the key point of the hip joint is the core basis to ensure the accurate analysis of the bone three-dimensional model, the determination of the osteotomy plane and the adjustment of the femoral head.

[0056] In this application, the center of the femoral head refers to the geometric center of the spherical structure of the femoral head, which is usually regarded as the rotation center of the hip joint. In a three-dimensional model, the center of the femoral head can be obtained by fitting a sphere of the point cloud on the surface of the femoral head.

[0057] In the present application, the acetabular center is the geometric center of the spherical concavity of the acetabulum, and is the reference point for the stable position of the femoral head in the acetabulum. The acetabular center is usually located in the center of the weight-bearing area of ​​the acetabulum.

[0058] In this application, the femoral neck mid-axis reference point is a set of key points on the femoral neck mid-axis, which is used to fit the femoral neck mid-axis and determine the osteotomy plane. It usually includes: femoral neck proximal point: the starting point close to the femoral head. Femoral neck distal point: the end point close to the femoral shaft.

[0059] In this application, the boundary point of the necrotic area is the boundary of the femoral head necrotic area.

[0060] In this application, the distal femoral intercondylar center is the geometric center of the distal femoral intercondylar region, which is usually used to define the direction of the femoral force line. This point is usually located in the middle between the medial and lateral condyles of the femur.

[0061] In this application, the center of the femoral head and the center of the acetabulum are used to assess the alignment of the stability and rotational adjustment of the hip joint.

[0062] In this application, the femoral neck mid-axis reference point and the femoral head center are used to plan the osteotomy angle and the range of rotation adjustment.

[0063] In this application, the distal femoral intercondylar center point and the femoral neck mid-axis reference point are used to construct the femoral anatomical axis and evaluate the deviation of the lower limb mechanical axis.

[0064] In a specific implementation, according to the three-dimensional bone model, the key points of the hip joint and the necrotic area of ​​the femoral head are identified, and osteotomy information and femoral head adjustment information are generated, including:

[0065] According to the three-dimensional skeleton model, identifying key points of the hip joint;

[0066] identifying the necrotic area of ​​the femoral head according to the three-dimensional bone model;

[0067] Generate initial osteotomy information and initial femoral head adjustment information;

[0068] The initial osteotomy information and the initial femoral head adjustment information are evaluated based on preset evaluation conditions, and adjustments are made until the preset evaluation conditions are met.

[0069] In this application, necrotic area is the area within the femoral head where bone tissue has died due to insufficient blood supply. Identifying the necrotic area is key to planning a rotational osteotomy to rotate healthy bone into the weight-bearing area of ​​the acetabulum.

[0070] In this application, the osteotomy plane is determined as follows: the osteotomy starting point and end point are determined based on the femoral neck midline and the boundary of the necrotic area. The osteotomy plane is calculated by plane fitting to ensure that healthy bone covers the acetabulum weight-bearing area. The geometric parameters (position, normal vector) of the osteotomy plane are output.

[0071] In this application, the initial femoral head adjustment information is to rotate the healthy femoral head area to the acetabulum weight-bearing area. Method: The center of the femoral head is used as the rotation center. The rotation axis and rotation angle are calculated to align the healthy bone with the acetabulum weight-bearing area. The geometric parameters of the rotation adjustment (rotation axis, rotation angle) are output.

[0072] In this application, the osteotomy information is iteratively adjusted: based on the evaluation results, the position and angle of the osteotomy plane are adjusted to reduce the overlap between the necrotic area and the weight-bearing area.

[0073] In this application, the femoral head rotation information is optimized: the rotation axis and rotation angle are fine-tuned so that the healthy bone can better cover the acetabulum weight-bearing area, while reducing the overlap of the necrotic area with the medial / lateral column.

[0074] In a specific implementation, the preset evaluation conditions at least include:

[0075] The overlapping area between the necrotic area and the acetabulum weight-bearing area is smaller than the preset value / the postoperative hip joint integrity rate is greater than the preset value; the overlapping area between the necrotic area and the medial column / lateral column of the femoral head is smaller than the preset value.

[0076] In the present application, multiple preset values ​​are different and the specific values ​​can be determined through actual operation.

[0077] In this application, the acetabulum weight-bearing area is the key area in the hip joint that bears the body weight, located in the upper and anterolateral part of the acetabulum. It forms a joint contact surface with the femoral head, mainly used to bear the vertical pressure from the upper body of the human body, and transmit these forces to the femur and lower limb bones.

[0078] In this application, the postoperative hip joint intact rate is the ratio of the intact area of ​​the femoral head articular surface to the acetabular load-bearing area on the anteroposterior X-ray film after surgery. A vertical line is drawn from the lowest point of the acetabular edge and the teardrop to the acetabular top to determine the key point (the intersection of the vertical line and the acetabular top). The arc of the key point and the acetabular edge can represent the acetabular load-bearing area; the arc from the inner edge of the intact articular surface of the femoral head to the outer edge of the load-bearing part can represent the intact area of ​​the femoral head articular surface.

[0079] In the present application, the medial column of the femoral head is located near the medial side of the acetabulum, mainly bears the medial load of the hip joint, and generally includes the medial cortical bone of the femoral head and the trabecular bone system in the adjacent area.

[0080] Features: Close to the inner wall of the acetabulum, in contact with the medial weight-bearing area of ​​the acetabulum, and bears the vertical compression force from the hip joint.

[0081] Function: Provides the main longitudinal support of the hip joint and protects the femoral head in a stable position in the acetabulum.

[0082] In the present application, the lateral column of the femoral head is located near the lateral side of the acetabulum and is distributed in the lateral cortical bone and lateral trabecular bone system of the femoral head.

[0083] Features: Close to the outer edge of the acetabulum, partially in contact with the acetabulum rim. Withstands lateral and shear forces and helps the medial column maintain balance.

[0084] Function: Provide lateral support to the femoral head to prevent it from shifting outwards. Maintain the stability of the hip joint during dynamic activities.

[0085] In this application, the overlap area between the necrotic area and the acetabulum weight-bearing area is smaller than the preset value, so as to avoid the necrotic area from bearing the main weight of the hip joint and reduce the risk of postoperative collapse.

[0086] In this application, the intact rate of the hip joint after surgery is greater than the preset value, ensuring the functionality and stability of the hip joint after surgery.

[0087] In the present application, the overlap area between the necrotic area and the medial column and lateral column of the femoral head is less than a preset value, thereby protecting the integrity of the medial / lateral column and maintaining the support capacity of the hip joint.

[0088] In this application, the accuracy of osteotomy and rotation plans is improved by evaluating the relationship between the necrotic area and the weight-bearing area and columnar structure.

[0089] In this application, the scheme was iteratively optimized to ensure that the final scheme met the postoperative functional requirements.

[0090] In this application, by combining the three-dimensional model of the hip joint, the segmentation of the necrotic area and the evaluation conditions, the osteotomy information and adjustment information are accurately generated, and the surgical plan is optimized through dynamic adjustment to ensure the stability and functionality of the hip joint after surgery. This personalized planning method provides strong support for hip rotation osteotomy, greatly improving the success rate of the operation and the prognosis of patients.

[0091] In a specific implementation, the femoral head adjustment information includes a coronal plane rotation angle and a sagittal plane rotation angle.

[0092] In the present application, the coronal plane rotation angle is the rotation angle of the femoral head in the coronal plane (anteroposterior direction), which is used to adjust the upper and lower distribution of the healthy bone area of ​​the femoral head.

[0093] In the present application, the sagittal rotation angle is the rotation angle of the femoral head in the sagittal plane (superior and inferior directions), which is used to adjust the anterior-posterior distribution of the healthy bone area of ​​the femoral head.

[0094] In the present application, the femoral head adjustment information is the rotation angle along the normal of the osteotomy plane, which is decomposed into the coronal plane rotation angle and the sagittal plane rotation angle, thereby facilitating the operator's understanding and operation after the display, thereby improving the accuracy of the operation.

[0095] In a specific implementation, according to the three-dimensional bone model, the key points of the hip joint and the necrotic area of ​​the femoral head are identified, and osteotomy information and femoral head adjustment information are generated, and the method further includes:

[0096] The mechanical properties of the adjusted femoral head are analyzed, and if the mechanical properties are not satisfied, the osteotomy information and the femoral head adjustment information are regenerated.

[0097] In this application, mechanical performance analysis is used to ensure that the femoral head and hip joint after rotational osteotomy can withstand normal weight-bearing pressure after surgery to avoid fracture, collapse or mechanical imbalance. This protects the load-bearing capacity of healthy bone tissue, improves the functional recovery and stability of the hip joint after surgery, prolongs the preservation time of the patient's hip joint, and avoids early joint replacement.

[0098] In this application, the specific steps of mechanical analysis are: discretize the adjusted femoral head model into a finite element mesh, and define the material properties of each unit (such as the elastic modulus and Poisson's ratio of healthy bone and necrotic bone). Simulate the normal gait and weight-bearing conditions of the human body, and set the mechanical load of the hip joint: axial pressure when standing, dynamic load when walking or running; load the pressure distribution of the acetabulum weight-bearing area. Set boundary conditions: fix the distal end of the femur to simulate the force environment of the hip joint. Ensure that the loading conditions are consistent with the actual anatomy and biomechanics. Solve the stress and strain distribution: Use finite element analysis (FEA) software (such as ABAQUS, ANSYS) to calculate the stress distribution and displacement of the femoral head and femoral neck area.

[0099] In this application, the mechanical analysis evaluation indicators are:

[0100] Stress distribution: Is the maximum stress value of bone tissue lower than the yield strength of bone?

[0101] Healthy bone weight distribution: Ensure that healthy bone areas bear the majority of the weight-bearing pressure on the hip joint.

[0102] Stress condition of the necrotic area: Is the stress on the necrotic area lower than the critical value of bone collapse?

[0103] Fracture risk assessment: After rotational osteotomy, whether the rotational position of the femoral neck reduces the risk of fracture, and whether the contact area between the femoral head and acetabulum is evenly distributed enough.

[0104] In this application, if the analysis results show that the adjusted femoral head model meets all mechanical performance indicators, the current osteotomy information and adjustment information are output to complete the preoperative planning.

[0105] In a specific embodiment, identifying the necrotic area of ​​the femoral head according to the three-dimensional bone model includes:

[0106] Inputting the skeleton three-dimensional model into a feature extraction structure to obtain a feature extraction graph, wherein the feature extraction structure includes attention extraction modules and non-attention extraction modules in different visual field ranges;

[0107] Convolution and pooling are performed on the feature extraction map to obtain a pooled feature map;

[0108] The pooled feature map is subjected to continuous convolution and classification processing to obtain the necrotic area of ​​the femoral head.

[0109] Combination Figure 2 As shown, the feature extraction structure is the data set to the backneck×8 part; the convolution and pooling are the subsequent to the 7×7pool part; the continuous convolution and classification processing are the subsequent to the output part.

[0110] In this application, combined Figure 2As shown in the figure, the feature extraction map is convolved and pooled to obtain the pooled feature map. First, the feature extraction map is convolved and 1×1 convolved, and then 7×7 pooling is performed to obtain the pooled feature map.

[0111] It should be noted that in the present application, when the skeletal three-dimensional model is input into the feature extraction structure, the skeletal three-dimensional model is first converted into a two-dimensional image with multiple channels by slicing, and then input into the feature extraction structure.

[0112] In this application, combined Figure 2 As shown in the figure, the pooled feature map is subjected to continuous convolution processing and classification processing to obtain the necrotic area of ​​the femoral head. The pooled feature map is subjected to two continuous convolution processings, and each continuous convolution processing is a convolution processing and a 1×1 convolution processing; then the necrotic area of ​​the femoral head is output through the softmax classifier.

[0113] In this application, a fully connected layer is used in the softmax classifier to map features to classification dimensions, and the classifier output is converted into the probability of each category through the Softmax function. For each position point, the Softmax classifier outputs a probability vector, and generates a category label (whether it belongs to the necrotic area) by taking the category corresponding to the maximum probability of each position point.

[0114] In this application, the necrotic area distribution generation process:

[0115] Point-level classification: For each point or voxel on the 3D model, apply the Softmax classifier to obtain the classification label.

[0116] Three-dimensional mapping: Map the necrotic area labels back to the bone three-dimensional model to generate the necrotic area distribution: the necrotic area points are marked as 1, and the healthy area points are marked as 0.

[0117] Generate a necrotic region model: extract the points marked as 1 to generate the three-dimensional geometric shape of the necrotic region.

[0118] In this application, the necrotic area is labeled by projecting the classification results back to the original bone 3D model; using different colors to mark the necrotic area and healthy area to intuitively display the scope of necrosis.

[0119] In this application, the skeletal three-dimensional model is input into the feature extraction structure to obtain a feature extraction graph.

[0120] In the present application, the feature extraction structure includes attention extraction modules and non-attention extraction modules in different visual ranges. The combination of the two enhances the model's perception of local necrotic areas and global bone structures.

[0121] Attention Extraction Module: Extract features from different fields of view, emphasizing local and global multi-level information. Focus on highly relevant areas through self-attention mechanisms (such as Transformer or attention gating network).

[0122] Non-attention extraction module: extracts the basic geometric features of the skeleton model and retains the overall structural information of the model. Uses traditional convolutional layers to efficiently process low-level features.

[0123] In this application, combined Figure 2 As shown, the specific structure of the feature extraction structure includes: 3×3 convolutional layers, attention extraction modules, non-attention extraction modules (two in a row), and attention extraction modules (8 in a row) arranged in sequence.

[0124] Among them, the attention extraction module includes a 1×1 convolution layer, a depth-separable convolution layer, an attention mechanism and a 1×1 convolution layer arranged in sequence.

[0125] Among them, the non-attention extraction module includes a 1×1 convolutional layer, a depth-separable convolutional layer and a 1×1 convolutional layer arranged in sequence.

[0126] Among them, the 1×1 convolution layer: reduces the channel dimension and reduces the computational complexity. It extracts the channel features of each spatial position.

[0127] Among them, the depthwise separable convolution layer: extracts local spatial features to reduce the complexity of convolution calculation. Process: Spatial convolution (depthwise convolution) extracts the spatial features of each channel. Channel convolution (pointwise convolution) fuses information from different channels.

[0128] Among them, the attention mechanism: improves the model's attention to highly relevant areas such as necrotic areas. Attention mechanism selection: channel attention (such as SE module): calculates the importance weight of feature channels, spatial attention: calculates the attention weight of spatial positions, Transformer or attention gated network.

[0129] Among them, the 1×1 convolution layer: performs dimensionality reduction processing on the enhanced features and outputs feature dimensions that match the subsequent modules.

[0130] In this application, the attention extraction module aims to strengthen the model's attention to key areas (such as necrotic areas) through the self-attention mechanism.

[0131] In this application, the non-attention extraction module aims to extract the basic features of the skeleton model through efficient convolution operations and supplement the local information missing in the attention module.

[0132] In this application, the attention extraction module improves the feature expression ability of the necrotic area and enhances the model's perception of the key area. The non-attention extraction module provides efficient global feature extraction to make up for the computational cost of the attention module. The combination of the two modules improves the accuracy and efficiency of necrotic area recognition.

[0133] In this application, the stacking effect of multiple attention extraction modules is set up continuously: each attention module focuses on extracting features of different scales or levels. By stacking multiple modules, the model can gradually expand from local features (such as small changes in necrotic areas) to global features (such as the overall distribution of necrotic areas). It can simultaneously process the detailed features (such as boundaries) and overall structural features (such as area and distribution) of necrotic areas.

[0134] In this application, multi-level feature fusion: feature enhancement after module stacking: each module will further optimize the features of the previous module, gradually increasing the abstract level and expression ability of the features. The extracted features are not only spatially correlated, but also can capture complex local-global relationships.

[0135] In this application, the nonlinear effect of the multi-layer attention mechanism is as follows: each attention module re-weights the spatial distribution and channel importance of the input features through the self-attention mechanism. After stacking multiple modules, the network can capture more complex spatial and channel interactions. It can focus more accurately on the key features of the femoral head necrosis area while ignoring irrelevant background.

[0136] In this application, the cumulative effect of the continuous attention module is that the multi-layer attention module can enhance the saliency of the features of the necrotic area and suppress the redundant information of the healthy area. It has better ability to distinguish the necrotic areas that are difficult to distinguish (such as areas with density similar to healthy bones).

[0137] In this application, the globality of the continuous attention module: each attention module extracts spatial and channel correlations from the global scope. After stacking multiple modules, the model can gradually integrate global information based on local feature extraction. It can better capture the overall characteristics of the necrotic area, such as the relative position relationship between the necrotic area and the acetabular weight-bearing area.

[0138] An embodiment of the present application provides a preoperative planning device for hip preserving surgery, which is used to execute the preoperative planning method for hip preserving surgery described in the above content of the present application. The preoperative planning device for hip preserving surgery is described in detail below.

[0139] like Figure 6 As shown, the preoperative planning device for hip preservation surgery comprises:

[0140] An image acquisition module 101 is used to acquire a hip joint CT image of a single subject;

[0141] A three-dimensional construction module 102, which is used to construct a three-dimensional bone model according to the hip joint CT image;

[0142] An osteotomy generation module 103, which is used to identify key points of the hip joint and necrotic areas of the femoral head according to the three-dimensional bone model, and generate osteotomy information and femoral head adjustment information;

[0143] The osteotomy adjustment module 104 is used to display the osteotomy information and femoral head adjustment information, and perform fine adjustments according to the operator's operation.

[0144] In one embodiment, the key points of the hip joint include at least: the center of the femoral head, the femoral neck mid-axis reference point, the acetabulum center point, and the distal femoral condylar center point.

[0145] In one embodiment, the osteotomy generation module 103 is further configured to:

[0146] According to the three-dimensional bone model, key points of the hip joint are identified; according to the three-dimensional bone model, necrotic areas of the femoral head are identified; initial osteotomy information and initial femoral head adjustment information are generated; based on preset evaluation conditions, the initial osteotomy information and the initial femoral head adjustment information are evaluated and adjusted until the preset evaluation conditions are met.

[0147] In one embodiment, the preset evaluation conditions at least include:

[0148] The overlapping area between the necrotic area and the acetabulum weight-bearing area is smaller than the preset value / the postoperative hip joint integrity rate is greater than the preset value; the overlapping area between the necrotic area and the medial column / lateral column of the femoral head is smaller than the preset value.

[0149] In one embodiment, the femoral head adjustment information includes a coronal plane rotation angle and a sagittal plane rotation angle.

[0150] In one embodiment, the osteotomy generation module 103 is further configured to:

[0151] The mechanical properties of the adjusted femoral head are analyzed, and if the mechanical properties are not satisfied, the osteotomy information and the femoral head adjustment information are regenerated.

[0152] In one embodiment, the osteotomy generation module 103 is further configured to:

[0153] The three-dimensional bone model is input into the feature extraction structure to obtain a feature extraction map, wherein the feature extraction structure includes attention extraction modules and non-attention extraction modules in different field of view ranges; convolution and pooling are performed on the feature extraction map to obtain a pooled feature map; continuous convolution processing and classification processing are performed on the pooled feature map to obtain the necrotic area of ​​the femoral head.

[0154] The hip-preserving surgery preoperative planning device provided in the above-mentioned embodiment of the present application has a corresponding relationship with the hip-preserving surgery preoperative planning method provided in the embodiment of the present application. Therefore, the specific content in the system has a corresponding relationship with the hip-preserving surgery preoperative planning method. The specific content can refer to the records in the hip-preserving surgery preoperative planning method, and will not be repeated in this application.

[0155] The hip-preserving surgery preoperative planning device provided in the above-mentioned embodiment of the present application and the hip-preserving surgery preoperative planning method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0156] The above describes the internal functions and structure of the preoperative planning device for hip preservation surgery, such as Figure 7 As shown, in practice, the preoperative planning device for hip preservation surgery can be realized as an electronic device, including: a memory 301 and a processor 303 .

[0157] The memory 301 may be configured to store programs.

[0158] In addition, the memory 301 may also be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device, contact data, phone book data, messages, pictures, videos, etc.

[0159] The memory 301 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The processor 303, coupled to the memory 301, is used to execute the program in the memory 301, so as to:

[0160] Acquire a single subject's hip CT image;

[0161] constructing a three-dimensional bone model according to the hip joint CT image;

[0162] According to the three-dimensional bone model, identifying key points of the hip joint and necrotic areas of the femoral head, and generating osteotomy information and femoral head adjustment information;

[0163] The osteotomy information and femoral head adjustment information are displayed, and fine-tuned according to the operator's operation.

[0164] In one embodiment, the key points of the hip joint include at least: the center of the femoral head, the femoral neck mid-axis reference point, the acetabulum center point, and the distal femoral condylar center point.

[0165] In one implementation, the processor 303 is further configured to:

[0166] According to the three-dimensional bone model, key points of the hip joint are identified; according to the three-dimensional bone model, necrotic areas of the femoral head are identified; initial osteotomy information and initial femoral head adjustment information are generated; based on preset evaluation conditions, the initial osteotomy information and the initial femoral head adjustment information are evaluated and adjusted until the preset evaluation conditions are met.

[0167] In one embodiment, the preset evaluation conditions at least include:

[0168] The overlapping area between the necrotic area and the acetabulum weight-bearing area is smaller than the preset value / the postoperative hip joint integrity rate is greater than the preset value; the overlapping area between the necrotic area and the medial column / lateral column of the femoral head is smaller than the preset value.

[0169] In one embodiment, the femoral head adjustment information includes a coronal plane rotation angle and a sagittal plane rotation angle.

[0170] In one implementation, the processor 303 is further configured to:

[0171] The mechanical properties of the adjusted femoral head are analyzed, and if the mechanical properties are not satisfied, the osteotomy information and the femoral head adjustment information are regenerated.

[0172] In one implementation, the processor 303 is further configured to:

[0173] The three-dimensional bone model is input into the feature extraction structure to obtain a feature extraction map, wherein the feature extraction structure includes attention extraction modules and non-attention extraction modules in different field of view ranges; convolution and pooling are performed on the feature extraction map to obtain a pooled feature map; continuous convolution processing and classification processing are performed on the pooled feature map to obtain the necrotic area of ​​the femoral head.

[0174] In this application, Figure 7 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 7 Components shown.

[0175] The electronic device provided in this embodiment is based on the same inventive concept as the preoperative planning method for hip preservation surgery provided in the embodiment of the present application, and has the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0176] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0177] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the functions specified in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0178] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0179] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory (Flash RAM). The memory is an example of a computer-readable medium.

[0180] The present application also provides a computer-readable storage medium corresponding to the preoperative planning method for hip preservation surgery provided in the aforementioned embodiment, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the interactive image analysis auxiliary method for 3D aerial imaging provided in any of the aforementioned embodiments.

[0181] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0182] The computer-readable storage medium provided in the above-mentioned embodiment of the present application and the interactive image analysis auxiliary method for 3D aerial imaging provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0183] It should be noted that in the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.

[0184] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0185] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for preoperative planning of hip preservation surgery, characterized in that: include: Acquire a single subject's hip CT image; constructing a three-dimensional bone model according to the hip joint CT image; According to the three-dimensional bone model, identifying key points of the hip joint and necrotic areas of the femoral head, and generating osteotomy information and femoral head adjustment information; The osteotomy information and femoral head adjustment information are displayed, and fine-tuned according to the operator's operation.

2. The preoperative planning method for hip preservation surgery according to claim 1, characterized in that: The key points of the hip joint include at least: the center of the femoral head, the reference point of the femoral neck mid-axis, the center point of the acetabulum, and the center point between the distal femoral condyles.

3. The preoperative planning method for hip preservation surgery according to claim 1, characterized in that: According to the three-dimensional bone model, key points of the hip joint and the necrotic area of ​​the femoral head are identified, and osteotomy information and femoral head adjustment information are generated, including: According to the three-dimensional skeleton model, identifying key points of the hip joint; identifying the necrotic area of ​​the femoral head according to the three-dimensional bone model; Generate initial osteotomy information and initial femoral head adjustment information; The initial osteotomy information and the initial femoral head adjustment information are evaluated based on preset evaluation conditions, and adjustments are made until the preset evaluation conditions are met.

4. The preoperative planning method for hip preservation surgery according to claim 3, characterized in that: The preset evaluation conditions at least include: The overlapping area between the necrotic area and the acetabulum weight-bearing area is smaller than the preset value / the postoperative hip joint integrity rate is greater than the preset value; the overlapping area between the necrotic area and the medial column / lateral column of the femoral head is smaller than the preset value.

5. The preoperative planning method for hip preservation surgery according to claim 3, characterized in that: The femoral head adjustment information includes a coronal plane rotation angle and a sagittal plane rotation angle.

6. The method for preoperative planning of hip preservation surgery according to claim 5, characterized in that: According to the three-dimensional bone model, the key points of the hip joint and the necrotic area of ​​the femoral head are identified, and osteotomy information and femoral head adjustment information are generated, and the method further includes: The mechanical properties of the adjusted femoral head are analyzed, and if the mechanical properties are not satisfied, the osteotomy information and the femoral head adjustment information are regenerated.

7. The preoperative planning method for hip preservation surgery according to claim 3, characterized in that: According to the three-dimensional bone model, the necrotic area of ​​the femoral head is identified, including: Inputting the skeleton three-dimensional model into a feature extraction structure to obtain a feature extraction graph, wherein the feature extraction structure includes attention extraction modules and non-attention extraction modules in different visual field ranges; Convolution and pooling are performed on the feature extraction map to obtain a pooled feature map; The pooled feature map is subjected to continuous convolution and classification processing to obtain the necrotic area of ​​the femoral head.

8. A preoperative planning device for hip preservation surgery, characterized in that: include: An image acquisition module, which is used to acquire a hip joint CT image of a single subject; A three-dimensional construction module, which is used to construct a three-dimensional bone model according to the hip joint CT image; An osteotomy generation module, which is used to identify key points of the hip joint and necrotic areas of the femoral head according to the three-dimensional bone model, and generate osteotomy information and femoral head adjustment information; The osteotomy adjustment module is used to display the osteotomy information and femoral head adjustment information, and perform fine adjustments according to the operator's operation.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store programs; The processor, coupled to the memory, is configured to execute the program to: Acquire a single subject's hip CT image; constructing a three-dimensional bone model according to the hip joint CT image; According to the three-dimensional bone model, identifying key points of the hip joint and necrotic areas of the femoral head, and generating osteotomy information and femoral head adjustment information; The osteotomy information and femoral head adjustment information are displayed, and fine-tuned according to the operator's operation.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the preoperative planning method for hip preservation surgery described in any one of claims 1-6.

Images