Hip-preserving surgery preoperative planning method and apparatus

Abstract

The application provides a hip-preserving preoperative planning method and device, the method comprising: acquiring a hip CT image of a single object; constructing a three-dimensional bone model according to the hip CT image; identifying key points of the hip and necrotic areas of the femoral head according to the three-dimensional bone model, and generating osteotomy information and femoral head adjustment information; displaying the osteotomy information and femoral head adjustment information, and fine-tuning according to the operation of the operator. In the application, a three-dimensional bone model is constructed through a preoperative medical image, thereby planning the osteotomy position and adjustment information of the femoral head. Through the preoperative planning, strong support for the osteotomy position of the femoral neck rotational osteotomy can be provided.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and more specifically, to a method and apparatus for preoperative planning of hip-preserving surgery. Background Technology

[0002] Rotational osteotomy of the femoral neck is an orthopedic surgery used to treat hip joint disorders. It aims to redistribute the weight-bearing area of ​​the hip joint by performing a rotational osteotomy on a specific part of the femoral neck, thereby relieving hip pain, restoring function, and improving long-term prognosis.

[0003] Preoperative planning in hip-preserving surgery can provide strong support for the osteotomy location in femoral neck rotation osteotomy, but specific plans in this regard are currently lacking. Summary of the Invention

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

[0005] To address the aforementioned issues, the first aspect of this application provides a method for preoperative planning of hip-preserving surgery, comprising:

[0006] Acquire CT images of the hip joint of a single object;

[0007] Based on the hip joint CT images, a three-dimensional model of the skeleton is constructed.

[0008] Based on the 3D model of the skeleton, key points of the hip joint and necrotic areas of the femoral head are identified, and osteotomy information and femoral head adjustment information are generated.

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

[0010] The second aspect of this application provides a manufacturing system for a preoperative planning method for hip-preserving surgery, comprising:

[0011] Image acquisition module, used to acquire CT images of the hip joint of a single object;

[0012] A 3D construction module is used to construct a 3D model of the skeleton based on the hip joint CT image;

[0013] The osteotomy generation module is used to identify key points of the hip joint and necrotic areas of the femoral head based on 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 to make fine adjustments according to the operator's operation.

[0015] A third aspect of this application provides an electronic device, including: a memory and a processor; the memory being configurable to store a program, and the processor being coupled to the memory for executing the program in the memory for:

[0016] Acquire CT images of the hip joint of a single object;

[0017] Based on the hip joint CT images, a three-dimensional model of the skeleton is constructed.

[0018] Based on the 3D model of the skeleton, key points of the hip joint and necrotic areas of the femoral head are identified, and osteotomy information and femoral head adjustment information are generated.

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

[0020] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, the program being 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 skeleton is constructed using preoperative medical images, thereby planning the osteotomy position and adjustment information of the femoral head. This preoperative planning can provide strong support for the osteotomy position of the femoral neck rotation osteotomy. Attached Figure Description

[0022] Figure 1 This is a flowchart of a preoperative planning method for hip-preserving surgery according to an embodiment of this application;

[0023] Figure 2 This is a model architecture diagram of the preoperative planning method for hip-preserving surgery and necrosis identification according to an embodiment of this application;

[0024] Figure 3 This is a schematic diagram of a three-dimensional skeletal model of the preoperative planning method for hip-preserving surgery according to an embodiment of this application;

[0025] Figure 4 This is a schematic diagram illustrating the osteotomy method for preoperative planning of hip-preserving surgery according to an embodiment of this application;

[0026] Figure 5 This is a schematic diagram illustrating the postoperative hip joint integrity rate of the preoperative planning method for hip-preserving surgery according to an embodiment of this application.

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

[0028] Figure 7 This is an architectural diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0029] To make the above-mentioned objects, features, and advantages of this application more apparent and understandable, specific embodiments of this application will be described in detail below with reference to the accompanying drawings. Although exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0030] It should be noted that, unless otherwise stated, the technical or scientific terms used in this application shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application pertains.

[0031] This application provides a preoperative planning method for hip-preserving surgery as described above. The specific scheme of this method is as follows: Figures 1-4 As shown, this method can be performed by a preoperative planning device for hip-preserving surgery, which can be integrated into electronic devices such as computers, servers, computer clusters, and data centers. Combined with... Figure 1 As shown, the preoperative planning method for hip-preserving surgery includes:

[0032] S101, acquire CT images of the hip joint of a single object;

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

[0034] In this application, after obtaining the hip joint CT image of a single object, the application also includes preprocessing the hip joint CT image.

[0035] Specific preprocessing steps can include: Image denoising: using median filtering or Gaussian filtering to remove noise from CT images. Image enhancement: using histogram equalization to improve image contrast and highlight skeletal structures.

[0036] S102, Construct a three-dimensional model of the skeleton based on the hip joint CT image;

[0037] The specific construction process can be as follows:

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

[0039] 3D Reconstruction: The segmented CT slice data is stacked to generate volumetric data. A 3D surface mesh of the skeleton is generated using surface reconstruction algorithms (such as Marching Cubes). The resulting 3D skeleton model includes the complete morphology and spatial location information of the bones.

[0040] Model optimization: Noise reduction: Use mesh smoothing algorithms (such as Laplacian Smoothing) to reduce surface noise in the model. Mesh simplification: Reduce model complexity and improve the efficiency of subsequent operations through mesh simplification algorithms.

[0041] S103, Based on the three-dimensional skeletal model, identify key points of the hip joint and the necrotic area of ​​the femoral head, and generate osteotomy information and femoral head adjustment information;

[0042] In this application, skeletal morphology feature extraction algorithms (such as curvature analysis) can be used to automatically identify key points. Deep learning models (such as key point detection models) can also be used to enhance the accuracy of key point identification.

[0043] In this application, the bone mineral density threshold (HU value) of CT images can be used to distinguish between healthy bone and necrotic bone. The necrotic region can be segmented using MRI combined with CT images to generate a three-dimensional model of the necrotic region.

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

[0045] In this application, the visualized content may include: a 3D model of the skeleton (femoral head, femoral neck, and acetabulum); the 3D morphology and location of the necrotic area of ​​the femoral head; a 3D display of the osteotomy plane and osteotomy line; and the rotational effect of the femoral head after adjustment.

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

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

[0048] In this application, a three-dimensional model of the skeleton is constructed using preoperative medical images, thereby planning the osteotomy position and adjustment information of the femoral head. This preoperative planning can provide strong support for the osteotomy position of the femoral neck rotation osteotomy.

[0049] In this application, 3D 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 solution meets actual needs.

[0052] This application visually demonstrates the osteotomy and adjustment plans to assist doctors in making decisions.

[0053] This application provides a comprehensive and efficient solution for preoperative planning of rotational osteotomy by combining CT imaging and 3D modeling technology with interactive adjustment tools, which helps to improve the success rate of the surgery and the prognosis of patients.

[0054] In one specific implementation, the key points of the hip joint include at least: the center of the femoral head, the reference point of the femoral neck midline, the center point of the acetabulum, and the center point of the distal intercondylar femur.

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

[0056] In this application, the femoral head center 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 femoral head center can be obtained by fitting a sphere of point cloud on the surface of the femoral head.

[0057] In this application, the acetabular center point is the geometric center of the acetabular spherical concavity and serves as a reference point for the stable position of the femoral head within the acetabulum. The acetabular center is typically located at the center of the weight-bearing area of ​​the acetabulum.

[0058] In this application, the femoral neck midline reference points are a set of key points on the femoral neck midline used to fit the femoral neck midline and determine the osteotomy plane. They typically include: the proximal end of the femoral neck: the starting point near the femoral head; and the distal end of the femoral neck: the ending point near the femoral shaft.

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

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

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

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

[0063] In this application, the distal intercondylar point of the femur and the midline reference point of the femoral neck are used to construct the femoral anatomical axis and assess the deviation of the lower limb biomechanical axis.

[0064] In one specific implementation, based on the three-dimensional skeletal 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:

[0065] Based on the aforementioned 3D skeletal model, identify key points of the hip joint;

[0066] Based on the aforementioned three-dimensional skeletal model, the necrotic area of ​​the femoral head was identified;

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

[0068] The initial osteotomy information and 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, the necrotic area refers to the region within the femoral head where bone tissue has died due to insufficient blood supply. Identifying the necrotic area is crucial for planning rotational osteotomy, which involves rotating healthy bone into the weight-bearing area of ​​the acetabulum.

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

[0071] In this application, the initial femoral head adjustment information involves rotating the healthy femoral head region to the weight-bearing area of ​​the acetabulum. Method: The center of rotation is used as the center of rotation. The rotation axis and rotation angle are calculated to align the healthy bone with the weight-bearing area of ​​the acetabulum. 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 finely adjusted so that healthy bone can better cover the weight-bearing area of ​​the acetabulum, while reducing the overlap between the necrotic area and the medial / lateral columns.

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

[0075] The overlapping area between the necrotic area and the weight-bearing area of ​​the acetabulum is less 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 / lateral column of the femoral head is less than the preset value.

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

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

[0078] In this application, the postoperative hip joint integrity rate is defined as the ratio of the intact area of ​​the femoral head articular surface to the weight-bearing area of ​​the acetabulum on postoperative anteroposterior X-ray films. A key point is determined by drawing a perpendicular line from the acetabular rim and the lowest point of the teardrop towards the acetabular roof (the intersection of the perpendicular line and the acetabular roof). The arc formed by this key point and the acetabular rim represents the weight-bearing area of ​​the acetabulum. An arc drawn from the medial edge of the intact femoral head articular surface to the lateral edge of the load-bearing portion represents the intact area of ​​the femoral head articular surface.

[0079] In this application, the medial column of the femoral head is located in the portion near the medial side of the acetabulum and mainly bears the medial load of the hip joint. It typically includes the medial cortex of the femoral head and the trabecular bone system in the adjacent area.

[0080] Features: Located adjacent to the inner wall of the acetabulum, in contact with the medial weight-bearing area of ​​the acetabulum. Bears vertical compressive forces from the hip joint.

[0081] Function: Provides primary longitudinal support to the hip joint. Protects the femoral head and stabilizes its position within the acetabulum.

[0082] In this application, the lateral column of the femoral head is located in the portion 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: Located near the outer edge of the acetabulum, partially contacting the acetabular rim. It withstands lateral and shear forces, assisting the medial column in maintaining balance.

[0084] Function: Provides lateral support to the femoral head, preventing it from shifting laterally. Maintains the stability of the hip joint during dynamic activities.

[0085] In this application, the overlapping area between the necrotic area and the weight-bearing area of ​​the acetabulum is smaller than a preset value. This avoids the necrotic area bearing the main weight of the hip joint and reduces the risk of postoperative collapse.

[0086] In this application, the postoperative hip joint integrity rate is greater than the preset value. This ensures the postoperative function and stability of the hip joint.

[0087] In this application, the overlapping area between the necrotic area and the medial and lateral columns of the femoral head is less than a preset value. This protects the integrity of the medial / lateral columns and maintains the hip joint's support capacity.

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

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

[0090] In this application, by combining a three-dimensional model of the hip joint, segmentation of the necrotic area, and assessment conditions, precise osteotomy and adjustment information is generated. The surgical plan is then dynamically adjusted and optimized to ensure postoperative hip joint stability and function. This personalized planning approach provides strong support for hip rotational osteotomy, significantly improving surgical success rates and patient outcomes.

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

[0092] In this 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 vertical distribution of the healthy bone region of the femoral head.

[0093] In this application, the sagittal plane rotation angle is the rotation angle of the femoral head in the sagittal plane (vertical direction), used to adjust the anterior-posterior distribution of the healthy bone region of the femoral head.

[0094] In this application, the femoral head adjustment information is the rotation angle along the normal of the osteotomy plane. By decomposing it into coronal plane rotation angle and sagittal plane rotation angle, it is easier for the operator to understand and operate after the demonstration, thereby improving the accuracy of the operation.

[0095] In one specific implementation, based on the three-dimensional skeletal 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, further comprising:

[0096] A mechanical property analysis is performed on the adjusted femoral head. If the mechanical properties are not met, the osteotomy information and femoral head adjustment information are regenerated.

[0097] In this application, through mechanical property analysis, it is ensured that the femoral head and hip joint after rotational osteotomy can withstand normal weight-bearing pressure postoperatively, avoiding fractures, collapses, or mechanical imbalances. This protects the weight-bearing capacity of healthy bone tissue, improves postoperative hip joint functional recovery and stability, prolongs the preservation time of the patient's hip joint, and avoids early joint replacement.

[0098] The specific steps of the mechanical analysis in this application are as follows: The adjusted femoral head model is discretized into a finite element mesh, and the material properties of each element are defined (e.g., elastic modulus and Poisson's ratio of healthy and necrotic bone). The mechanical loads on the hip joint are set to simulate normal human gait and weight-bearing conditions: axial pressure when standing, and dynamic load when walking or running; the pressure distribution in the acetabular weight-bearing area is also applied. Boundary conditions are set: the distal femur is fixed to simulate the stress environment of the hip joint. The loading conditions are ensured to conform to actual anatomy and biomechanics. Stress and strain distribution are solved: finite element analysis (FEA) software (such as ABAQUS or ANSYS) is used to calculate the stress distribution and displacement in the femoral head and femoral neck regions.

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

[0100] Stress distribution: Whether the maximum stress value in bone tissue is lower than the yield strength of bone.

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

[0102] Stress conditions in the necrotic area: Whether the stress borne by the necrotic area is below the critical value for bone collapse.

[0103] Fracture risk assessment: After rotational osteotomy, does the rotational position of the femoral neck reduce the risk of fracture, and is the contact area between the femoral head and the acetabulum sufficiently and evenly distributed?

[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 one specific implementation, identifying the necrotic area of ​​the femoral head based on the three-dimensional bone model includes:

[0106] The 3D skeletal model is input into the feature extraction structure to obtain a feature extraction map. The feature extraction structure includes attention extraction modules and non-attention extraction modules with different visual ranges.

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

[0108] The pooling feature map is subjected to continuous convolution and classification to obtain the necrotic region of the femoral head.

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

[0110] In this application, combined with Figure 2As shown, convolution and pooling are performed on the feature extraction map to obtain the pooled feature map. First, the feature extraction map is processed by convolution and 1×1 convolution, and then 7×7 pooling is performed to obtain the pooled feature map.

[0111] It should be noted that in this application, when the 3D skeletal model is input into the feature extraction structure, the 3D skeletal model is first converted into a 2D image with multiple channels by slicing, and then input into the feature extraction structure.

[0112] In this application, combined with Figure 2 As shown, the pooling feature map is subjected to continuous convolution and classification processing to obtain the necrotic region of the femoral head. The pooling feature map is subjected to two continuous convolution processing, each of which is a convolution process and a 1×1 convolution process; then the necrotic region of the femoral head is output through a softmax classifier.

[0113] In this application, the softmax classifier uses a fully connected layer to map features to the classification dimension, and the softmax function converts the classifier output into the probability of each class. For each location point, the softmax classifier outputs a probability vector, and the class label (whether it belongs to the dead region) is generated by taking the class corresponding to the highest probability at each location point.

[0114] In this application, the process of generating the necrotic region distribution is as follows:

[0115] Point-level classification: Apply the Softmax classifier to each point or voxel on the 3D model to obtain classification labels.

[0116] 3D mapping: Map the necrotic area labels back to the 3D model of the skeleton to generate the necrotic area distribution: necrotic area points are marked as 1, and healthy area points are marked as 0.

[0117] Generate necrotic region model: Extract the points marked as 1 to generate the three-dimensional geometry of the necrotic region.

[0118] In this application, the necrotic area is labeled by projecting the classification results back onto the original 3D bone model and using different colors to mark the necrotic and healthy areas, thus visually displaying the extent of necrosis.

[0119] In this application, the 3D skeletal model is input into the feature extraction structure to obtain the feature extraction map.

[0120] In this application, the feature extraction structure includes attention extraction modules and non-attention extraction modules with different visual ranges. The combination of these two enhances the model's ability to perceive local necrotic regions and the global skeletal structure.

[0121] Attention extraction module: Extracts features from different visual ranges, emphasizing multi-level information from both local and global perspectives. It focuses on highly relevant regions through self-attention mechanisms (such as Transformer or attention-gated networks).

[0122] Non-attention extraction module: Extracts basic geometric features of the skeletal model while preserving the overall structural information of the model. It uses traditional convolutional layers to efficiently process low-level features.

[0123] In this application, combined with Figure 2 As shown, the specific structure of the feature extraction structure includes, in sequence: a 3×3 convolutional layer, an attention extraction module, two consecutive non-attention extraction modules, and eight consecutive attention extraction modules.

[0124] The attention extraction module includes a 1×1 convolutional layer, a depth-separable convolutional layer, an attention mechanism, and a 1×1 convolutional layer arranged sequentially.

[0125] The non-attention extraction module includes a 1×1 convolutional layer, a depth-separable convolutional layer, and a 1×1 convolutional layer arranged sequentially.

[0126] The 1×1 convolutional layer reduces channel dimensions and computational complexity, extracting channel features for each spatial location.

[0127] Among them, depthwise separable convolutional layers: extract local spatial features to reduce the computational complexity of convolution. Process: Spatial convolution extracts spatial features from each channel. Pointwise convolution fuses information from different channels.

[0128] Among these, attention mechanisms enhance the model's focus on highly relevant regions such as necrotic areas. Attention mechanism choices include: channel attention (e.g., the SE module): calculating the importance weights of feature channels; spatial attention: calculating attention weights for spatial locations; and Transformer or attention-gated networks.

[0129] The 1×1 convolutional layer performs dimensionality reduction on the enhanced features and outputs the feature dimension that matches that of subsequent modules.

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

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

[0132] In this application, the attention extraction module enhances the feature representation capability of necrotic regions, thereby improving the model's perception of key areas. The non-attention extraction module provides efficient global feature extraction, compensating for the computational cost of the attention module. Combining these two modules improves both the accuracy and efficiency of necrotic region identification.

[0133] In this application, multiple attention extraction modules are stacked sequentially: each attention module focuses on extracting features at different scales or levels. By stacking multiple modules, the model can progressively expand from local features (such as subtle changes in the necrotic region) to global features (such as the overall distribution of the necrotic region). It can simultaneously handle detailed features of the necrotic region (such as boundaries) and overall structural features (such as area and distribution).

[0134] In this application, multi-level feature fusion is employed: feature enhancement after module stacking: each module further optimizes the features of the previous module, gradually increasing the abstraction level and expressive power of the features. The extracted features not only have spatial correlation but can also capture complex local-global relationships.

[0135] In this application, the non-linear 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 a self-attention mechanism. After stacking multiple modules, the network can capture more complex spatial and channel interactions. It can more accurately focus on the key features of the femoral head necrosis region while ignoring irrelevant background.

[0136] In this application, the cumulative effect of continuous attention modules is as follows: multi-layer attention modules can enhance the salience of necrotic region features and suppress redundant information in healthy regions. It exhibits better discriminative ability for difficult-to-distinguish necrotic regions (such as regions with density similar to healthy bone).

[0137] In this application, the global nature of the continuous attention modules is emphasized: each attention module extracts spatial and channel correlations from a global perspective. By stacking multiple modules, the model can progressively integrate global information based on local feature extraction. This allows for better capture of the overall characteristics of the necrotic region, such as the relative positional relationship between the necrotic region and the weight-bearing area of ​​the acetabulum.

[0138] This application provides a preoperative planning device for hip-preserving surgery, used to execute the preoperative planning method for hip-preserving surgery described above. 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-preserving surgery includes:

[0140] Image acquisition module 101 is used to acquire CT images of the hip joint of a single object;

[0141] The three-dimensional construction module 102 is used to construct a three-dimensional model of the skeleton based on the hip joint CT image;

[0142] The osteotomy generation module 103 is used to identify key points of the hip joint and necrotic areas of the femoral head based on 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 to make 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 reference point of the femoral neck midline, the center point of the acetabulum, and the center point of the distal intercondylar femur.

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

[0146] Based on the 3D skeletal model, key points of the hip joint are identified; based on the 3D skeletal model, necrotic areas of the femoral head are identified; initial osteotomy information and initial femoral head adjustment information are generated; the initial osteotomy information and initial femoral head adjustment information are evaluated based on preset evaluation conditions and adjusted until the preset evaluation conditions are met.

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

[0148] The overlapping area between the necrotic area and the weight-bearing area of ​​the acetabulum is less 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 / lateral column of the femoral head is less than the preset value.

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

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

[0151] A mechanical property analysis is performed on the adjusted femoral head. If the mechanical properties are not met, the osteotomy information and femoral head adjustment information are regenerated.

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

[0153] The 3D model of the skeleton is input into the feature extraction structure to obtain a feature extraction map. The feature extraction structure includes attention extraction modules and non-attention extraction modules with different visual ranges. The feature extraction map is convolved and pooled to obtain a pooled feature map. The pooled feature map is then subjected to continuous convolution and classification to obtain the necrotic area of ​​the femoral head.

[0154] The preoperative planning device for hip preservation surgery provided in the above embodiments of this application corresponds to the preoperative planning method for hip preservation surgery provided in the embodiments of this application. Therefore, the specific content in this system corresponds to the preoperative planning method for hip preservation surgery. The specific content can be referred to the records in the preoperative planning method for hip preservation surgery, which will not be repeated in this application.

[0155] The preoperative planning device for hip preservation surgery provided in the above embodiments of this application and the preoperative planning method for hip preservation surgery provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

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

[0157] Memory 301 can be configured to store a program.

[0158] Additionally, memory 301 can also be configured to store various other data to support operation on the electronic device. Examples of this data include instructions for any application or method used to operate on the electronic device, contact data, phonebook data, messages, pictures, videos, etc.

[0159] Memory 301 can 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 storage, flash memory, magnetic disk, or optical disk. Processor 303, coupled to memory 301, is used to execute programs in memory 301 for:

[0160] Acquire CT images of the hip joint of a single object;

[0161] Based on the hip joint CT images, a three-dimensional model of the skeleton is constructed.

[0162] Based on the 3D model of the skeleton, key points of the hip joint and necrotic areas of the femoral head are identified, and osteotomy information and femoral head adjustment information are generated.

[0163] The osteotomy information and femoral head adjustment information are displayed, and fine adjustments are made 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 reference point of the femoral neck midline, the center point of the acetabulum, and the center point of the distal intercondylar femur.

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

[0166] Based on the 3D skeletal model, key points of the hip joint are identified; based on the 3D skeletal model, necrotic areas of the femoral head are identified; initial osteotomy information and initial femoral head adjustment information are generated; the initial osteotomy information and initial femoral head adjustment information are evaluated based on preset evaluation conditions and adjusted until the preset evaluation conditions are met.

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

[0168] The overlapping area between the necrotic area and the weight-bearing area of ​​the acetabulum is less 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 / lateral column of the femoral head is less than the preset value.

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

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

[0171] A mechanical property analysis is performed on the adjusted femoral head. If the mechanical properties are not met, the osteotomy information and femoral head adjustment information are regenerated.

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

[0173] The 3D model of the skeleton is input into the feature extraction structure to obtain a feature extraction map. The feature extraction structure includes attention extraction modules and non-attention extraction modules with different visual ranges. The feature extraction map is convolved and pooled to obtain a pooled feature map. The pooled feature map is then subjected to continuous convolution and classification to obtain the necrotic area of ​​the femoral head.

[0174] In this application, Figure 7 The diagram only shows some components and does not mean that the electronic device includes only these components. Figure 7 The 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 this application embodiment, and has the same beneficial effects as the methods adopted, run or implemented by the application stored therein.

[0176] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0177] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0178] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0179] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0180] This application also provides a computer-readable storage medium corresponding to the preoperative planning method for hip preservation surgery provided in the foregoing embodiments, wherein a computer program (i.e., a program product) is stored thereon. When the computer program is run by a processor, it executes the interactive image analysis assistance method for 3D aerial imaging provided in any of the foregoing embodiments.

[0181] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

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

[0183] It should be noted that numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known structures and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0184] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0185] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A preoperative planning method for hip preservation surgery, characterized in that, The method comprises the following steps: obtaining a CT image of a single subject's hip joint; constructing a three-dimensional bone model according to the CT image of the hip joint; 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; the key points of the hip joint at least include: the center of the femoral head, the reference point of the middle axis of the femoral neck, the center point of the acetabulum, and the center point of the distal intercondylar center of the femur; displaying the osteotomy information and the femoral head adjustment information, and fine-tuning according to the operation of the operator; 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, comprising: identifying key points of the hip joint according to the three-dimensional bone model; identifying necrotic areas of the femoral head according to the three-dimensional bone model; generating initial osteotomy information and initial femoral head adjustment information; adjusting the initial osteotomy information and the initial femoral head adjustment information based on a preset evaluation condition until the preset evaluation condition is met; the preset evaluation condition at least includes: the overlapping area of the necrotic area and the acetabular weight-bearing area is less than a preset value / the postoperative hip joint integrity rate is greater than a preset value; the overlapping area of the necrotic area and the medial / lateral column of the femoral head is less than a preset value; the femoral head adjustment information includes the coronal plane rotation angle and the sagittal plane rotation angle.

2. The preoperative planning method for hip preservation surgery of claim 1, wherein, 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, further comprising: performing mechanical performance analysis on the adjusted femoral head, and if the mechanical properties are not met, regenerating the osteotomy information and the femoral head adjustment information.

3. The preoperative planning method for hip preservation surgery of claim 1, wherein, According to the three-dimensional bone model, identifying the necrotic area of the femoral head, comprising: inputting the three-dimensional bone model into a feature extraction structure to obtain a feature extraction graph, wherein the feature extraction structure includes different field of view attention extraction modules and non-attention extraction modules; performing convolution and pooling on the feature extraction graph to obtain a pooled feature graph; performing continuous convolution processing and classification processing on the pooled feature graph to obtain the necrotic area of the femoral head.

4. A preoperative planning device for hip preservation surgery, characterized in that The method comprises the following steps: an image acquisition module for acquiring a CT image of a single subject's hip joint; a three-dimensional construction module for constructing a three-dimensional bone model according to the CT image of the hip joint; an osteotomy generation module for identifying key points of the hip joint and necrotic areas of the femoral head according to the bone three-dimensional model, and generating osteotomy information and femoral head adjustment information; the key points of the hip joint at least include: the center of the femoral head, the middle axis reference point of the femoral neck, the center point of the acetabulum, and the center point between the distal intercondylar center of the femur; an osteotomy adjustment module for displaying the osteotomy information and the femoral head adjustment information, and fine-tuning according to the operator's operation; identifying key points of the hip joint and necrotic areas of the femoral head based on the three-dimensional bone model, and generating osteotomy information and femoral head adjustment information, comprising identifying key points of the hip joint according to the three-dimensional bone model; identifying necrosis areas of the femoral head according to the three-dimensional bone model; generating initial osteotomy and initial femoral head adjustment information; adjusting the initial osteotomy information and the initial femorai head adjustment information based on a preset evaluation condition until the preset evaluation condition is met. The initial osteotomy information and the initial femoral head adjustment information are evaluated based on preset evaluation conditions, and are adjusted until the preset evaluation conditions are met; The preset evaluation conditions at least include: the overlapping area of the necrosis area and the acetabular weight-bearing area is less than a preset value / the postoperative hip joint integrity rate is greater than a preset value; the overlapping area of the necrosis area and the medial column / lateral column of the femoral head is less than a preset value; The femoral head adjustment information includes a coronal plane rotation angle and a sagittal plane rotation angle.

5. An electronic device, comprising: Comprise: a memory and a processor; The memory is used for storing a program; The processor is coupled to the memory and is used for executing the program for: obtaining a hip joint CT image of a single object; constructing a bone three-dimensional model according to the hip joint CT image; According to the bone three-dimensional model, the key points of the hip joint and the necrosis area of the femoral head are identified, and the osteotomy information and the femoral head adjustment information are generated; The key points of the hip joint at least include: the center of the femoral head, the reference point of the middle axis of the femoral neck, the center point of the acetabulum, and the center point of the distal intercondylar center of the femur; The osteotomy information and the femoral head adjustment information are displayed, and are fine-tuned according to the operation of the operator; According to the bone three-dimensional model, the key points of the hip joint and the necrosis area of the femoral head are identified, and the osteotomy information and the femoral head adjustment information are generated, comprising: According to the bone three-dimensional model, the key points of the hip joint are identified; According to the bone three-dimensional model, the necrosis area of the femoral head is identified; 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 are adjusted until the preset evaluation conditions are met; The preset evaluation conditions at least include: the overlapping area of the necrosis area and the acetabular weight-bearing area is less than a preset value / the postoperative hip joint integrity rate is greater than a preset value; the overlapping area of the necrosis area and the medial column / lateral column of the femoral head is less than a preset value; The femoral head adjustment information includes a coronal plane rotation angle and a sagittal plane rotation angle.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the preoperative planning method of the hip preservation surgery of any one of claims 1-3.

Images