Fracture type identification and reduction path planning method

Abstract

The invention discloses a fracture type identification and reduction path planning method, and relates to the technical field of medical image identification. The method comprises the following steps: S1, acquiring medical image data of a fracture area of a patient; s2, constructing a three-dimensional model of the fracture part of the patient based on the medical image data of the fracture area; s3, the fracture type recognition model recognizes a fracture contour on the three-dimensional model of the fracture part of the patient; s4, splicing fracture fractures of the fracture part; s5, the offset distance of the bones on the two sides of the fracture crack is calculated; and S6, carrying out reduction path visualization display on the three-dimensional model of the fracture part of the patient. According to the method, the three-dimensional model of the fracture part of the patient is constructed by acquiring the medical image data of the fracture area of the patient, the fracture type and the fracture contour of the patient are identified by using the fracture type identification model, the offset distance of the bone is calculated to generate the reduction path for visual display, a doctor is assisted in performing a fracture operation, and the precision of the three-dimensional model is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical image recognition, and in particular relates to a method for fracture type recognition and reduction path planning. Background Art

[0002] Intraoperative navigation technology is an important technology used in modern medical surgery. It combines preoperative images (such as CT, MRI, etc.) with real-time patient anatomical position information during surgery to provide surgeons with accurate three-dimensional spatial guidance, thereby improving the accuracy, safety and efficiency of surgery. This technology has shown great value in neurosurgery, orthopedics, thoracic surgery and other fields. For example, traditional fracture surgery relies on the surgeon's experience and two-dimensional image guidance (such as X-rays), which has limitations in locating the fracture site, determining the implant position and avoiding damage to surrounding important structures. With the advancement of computer technology, imaging technology and robotics technology, intraoperative navigation systems have emerged, providing more accurate three-dimensional visualization and positioning methods for orthopedic surgery. In fracture surgery, intraoperative navigation can help doctors monitor the position of surgical instruments in real time, accurately reposition the fracture ends, optimize internal fixation implants, reduce surgical complications and shorten the recovery period. Preoperative planning is one of the key steps in the intraoperative navigation process. At this stage, the patient's imaging data is usually used for three-dimensional reconstruction to create a high-precision virtual model of the patient's anatomical structure. This model can not only help surgeons have an in-depth understanding of the surgical area before surgery, but can also be used to simulate surgical pathways, assess surgical risks, design personalized surgical plans, etc., thereby optimizing surgical strategies and improving surgical success rates. However, fracture 3D reconstruction technology still faces many challenges in its implementation. For example, it is a major challenge to accurately align the preoperative 3D reconstruction model with the patient's actual anatomical structure. Factors such as changes in body position and tissue deformation during surgery may lead to deviations between the preoperative plan and the actual situation. Soft tissue impact: The soft tissues around the fracture (such as muscles, blood vessels, and nerves) are difficult to display clearly in two-dimensional or three-dimensional images, which affects the comprehensiveness of surgical planning, especially when the protection of these structures needs to be considered. Summary of the invention

[0003] The purpose of the present invention is to provide a method for fracture type identification and reduction path planning. By acquiring medical imaging data of the patient's fracture area, a three-dimensional model of the patient's fracture part is constructed. The fracture type identification model is used to identify the patient's fracture type and fracture contour, and the bone offset distance is calculated to generate a reduction path. This solves the problem that the existing three-dimensional reconstruction model is difficult to accurately align with the patient's actual situation and the fracture crack area is difficult to clearly display.

[0004] In order to solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is a method for fracture type identification and reduction path planning, comprising the following steps: Step S1: Acquire medical imaging data of the fracture area of ​​the patient, wherein the medical imaging data includes CT images, X-ray images and MRI images; Step S2: constructing a three-dimensional model of the patient's fractured part based on the medical imaging data of the fractured area; Step S3: The fracture type recognition model recognizes the fracture contour on the three-dimensional model of the patient's fracture part; Step S4: splicing the fracture cracks of the fractured part; Step S5: calculating the offset distance of the bones on both sides of the fracture crack; Step S6: Visually display the reduction path on the three-dimensional model of the patient's fracture.

[0005] As a preferred technical solution, in step S1, the acquired medical image data needs to be preprocessed, and the specific preprocessing process is as follows: Step S11: performing noise reduction processing on the medical image data by Gaussian filtering; Gaussian filtering can smooth the medical image, reduce the noise of the medical image by blurring, and create a clearer contour basis for edge detection; Step S12: Use the Sobel algorithm to calculate the gradient value of each pixel on the medical image, obtain the edge strength and direction of the pixel in the horizontal and vertical directions, and realize the monitoring of the edge of the medical image. The specific formula of the gradient amplitude is: ; In the formula, Respectively represent the gradient value of the pixel in the horizontal and vertical directions, is the gradient amplitude; The formula for the specific gradient direction is: ; In the formula, is the inverse tangent function, is the gradient direction; The Sobel algorithm can effectively detect the edge structure of each graphic in a medical image and calculate the gradient values ​​of the medical image in the horizontal and vertical directions. By calculating the gradients in these two directions, the gradient amplitude and direction of each pixel can be obtained, thereby achieving accurate detection of the edges of medical images. Step S13: using a non-maximum suppression algorithm to enhance the contour clarity of the medical image; only retaining the pixel points with the local maximum gradient value in the gradient image, and suppressing other non-local maximum pixel points, so that the edge part of the obtained medical image becomes more delicate and sharp, and the clarity of the edge contour of the medical image is enhanced; Step S14: using a dual threshold detection algorithm to classify pixels in the medical image; the classification is divided into strong edges and weak edges according to the size of the gradient threshold; the strong edges and weak edges are judged by a pre-set threshold, and the gradient amplitude exceeding the threshold is identified as a strong edge, and the gradient amplitude below the threshold is identified as a weak edge, which provides an important basis for the accurate extraction of edge contours; Step S15: connecting strong edge pixels to form the edge contour of the bone, and connecting weak edge pixels to form cracks of bone fractures; Step S16: Classify and annotate the medical images, compare the similarity of multiple medical image features, use artificial intelligence algorithms for deep learning, establish a fracture type recognition model, and form a fracture database.

[0006] As a preferred technical solution, in step S16, the specific process of establishing the fracture type identification model is as follows: Step S161: The medical image fracture region category and its corresponding sub-block image constitute a label and training sample set; Step S162: introducing the labels and training sample sets into the YOLOv5 network for network training; Step S163: The YOLOv5 network uses convolution kernels of different sizes to achieve fusion of features of different scales; Step S164: extract features through convolution and pooling, using three consecutive Inception modules to perform convolution and pooling in parallel; Step S165: Integrate the features after multiple convolutions and pooling, and connect them to the output layer through a fully connected method; Step S166: Output the fracture classification results according to the task requirements.

[0007] As a preferred technical solution, in step S162, the trained original data is used to obtain the mean and the covariance matrix of the Gaussian density estimate , and obtain the following Gaussian probability density function for each category: ; In the formula, n is the number of training samples, D is the number of dimensions, is the mean vector, is the covariance matrix of the distribution, is a Gaussian probability density function.

[0008] As a preferred technical solution, in step S165, during the YOLOv5 network training process, the loss function corresponding to the classifier is as follows: ; In the formula, , is the activation function, , are the internal weights, inputs, and biases of its nodes.

[0009] As a preferred technical solution, in step S2, the specific process of constructing the three-dimensional model of the patient's fracture part is as follows: Step S21: The patient needs to undergo a thin-slice spiral CT scan to obtain a high-resolution two-dimensional tomographic image sequence; Step S22: using the preprocessing method in step S1 to process the medical image; Step S23: converting the two-dimensional sequence into a three-dimensional data set using three-dimensional reconstruction technology; Step S24: Use mask editing tools for complex areas to manually remove adhesions or irrelevant tissues; Step S25: Apply a smoothing algorithm to reduce 3D surface jaggedness; Step S26: Adjust color rendering and transparency, and export to a standard format for 3D printing or surgical planning system.

[0010] As a preferred technical solution, in step S4, the fracture cracks of the same fracture part are connected, and the two end points of the fracture crack are respectively and , calculate the slope of the two endpoints respectively Use the point slope method to fit the straight line between the two endpoints. The specific formula is as follows: ; Calculate the slope , use the point-slope formula and loop statements in MATLAB to find the points on the straight line and connect them with smooth curves.

[0011] As a preferred technical solution, in step S5, the calculation process of the offset distance of the bones on both sides of the fracture crack is as follows: Step S51: Select three continuous rectangular areas with the same length and width from the leftmost vertex of the bone above the fracture crack as the origin, and name them A, B, and C respectively, and the corresponding area distribution is ; Step S52: Select three continuous rectangular areas with the same length and width on the left side of the bone below the fracture crack, and name them D, E, and F respectively, and the corresponding area distribution is ; Step S53: Use the cv2.contour function in OpenCV to select the bone crack and the selected 6 contour areas for calculation, and obtain the area of ​​the three rectangles above and the area composed of the fracture crack. , and the area of ​​the three rectangles below and the area of ​​the fracture crack ; Step S54: Determine the offset distance of the bones on both sides of the fracture crack according to the length and area data of the fracture crack.

[0012] As a preferred technical solution, in step S54, the Spearman correlation coefficient method is used to analyze the medical images after different fractures to obtain relevant image feature data to determine the offset distance of the bones on both sides of the fracture crack. The specific calculation formula of the Spearman correlation coefficient method is as follows: ; In the formula, Observations after sorting at different angles The rank of are the average ranks of the variables, and N is the total amount of data.

[0013] The present invention has the following beneficial effects: (1) The present invention constructs a three-dimensional model of the patient's fracture area by acquiring medical imaging data of the patient's fracture area, uses a fracture type recognition model to identify the patient's fracture type and fracture contour, and calculates the bone offset distance to generate a reduction path, thereby assisting doctors in performing fracture surgery and improving the accuracy of the three-dimensional model.

[0014] (2) The present invention identifies the two endpoints of the fracture crack and calculates the slopes of the two endpoints respectively. Use the point slope formula to fit a straight line between two endpoints and calculate the slope In MATLAB, the point-slope formula and loop statements are used to find the points on the straight line, and then connected with smooth curves to fill the fracture cracks and improve the accuracy of the operation.

[0015] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 A flow chart of a fracture type identification and reduction path planning method of the present invention; Figure 2 Schematic diagram of the offset distance of bones on both sides of the fracture crack. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0020] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-2 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0021] See also Figure 1 As shown, the present invention is a method for fracture type identification and reduction path planning, comprising the following steps: Step S1: Acquire medical imaging data of the fracture area of ​​the patient, wherein the medical imaging data includes CT images, X-ray images and MRI images; Step S2: constructing a three-dimensional model of the patient's fractured part based on the medical imaging data of the fractured area; Step S3: The fracture type recognition model recognizes the fracture contour on the three-dimensional model of the patient's fracture part; Step S4: splicing the fracture cracks of the fractured part; Step S5: calculating the offset distance of the bones on both sides of the fracture crack; Step S6: Visually display the reduction path on the three-dimensional model of the patient's fracture.

[0022] In step S1, the acquired medical image data needs to be preprocessed. The specific preprocessing process is as follows: Step S11: performing noise reduction processing on the medical image data by Gaussian filtering; Gaussian filtering can smooth the medical image, reduce the noise of the medical image by blurring, and create a clearer contour basis for edge detection; Step S12: Use the Sobel algorithm to calculate the gradient value of each pixel on the medical image, obtain the edge strength and direction of the pixel in the horizontal and vertical directions, and realize the monitoring of the edge of the medical image. The specific formula of the gradient amplitude is: ; In the formula, Respectively represent the gradient value of the pixel in the horizontal and vertical directions, is the gradient amplitude; The formula for the specific gradient direction is: ; In the formula, is the inverse tangent function, is the gradient direction; The Sobel algorithm can effectively detect the edge structure of each graphic in a medical image and calculate the gradient values ​​of the medical image in the horizontal and vertical directions. By calculating the gradients in these two directions, the gradient amplitude and direction of each pixel can be obtained, thereby achieving accurate detection of the edges of medical images. Step S13: using a non-maximum suppression algorithm to enhance the contour clarity of the medical image; only retaining the pixel points with the local maximum gradient value in the gradient image, and suppressing other non-local maximum pixel points, so that the edge part of the obtained medical image becomes more delicate and sharp, and the clarity of the edge contour of the medical image is enhanced; Step S14: Use a dual threshold detection algorithm to classify pixels in medical images; the classification is divided into strong edges and weak edges according to the size of the gradient threshold; strong edges and weak edges are judged by pre-set thresholds, and gradient amplitudes exceeding the threshold are identified as strong edges, and gradient amplitudes below the threshold are identified as weak edges, providing an important basis for accurate extraction of edge contours; because the gaps between bones usually present a high and uniform gradient amplitude due to clear anatomical structures and obvious density differences, the gradient amplitudes above the threshold are identified as gaps between two bones; and the gradient amplitudes of fracture cracks may have local sudden changes or lower areas due to irregular fracture surfaces or edema of surrounding tissues, especially at blurred fracture edges, so the gradient amplitudes below the threshold are identified as crack gaps formed after bone fractures. The specific gradient amplitude judgment is as shown in the following table: In addition to the above judgment steps, the edge morphology can also be used to judge whether it is the edge contour of the bone or the crack of the bone fracture; The edges of bone gaps are mostly continuous and smooth curves, which conform to the characteristics of anatomical structures. Their continuity can be enhanced through improved methods such as shear wave transform. Because fracture cracks often appear discontinuous, jagged or bifurcated, the gradient direction consistency is low, and non-maximum suppression technology is needed to analyze the breakpoints.

[0023] Step S15: connecting strong edge pixels to form the edge contour of the bone, and connecting weak edge pixels to form cracks of bone fractures; Step S16: Classify and annotate the medical images, compare the similarity of multiple medical image features, use artificial intelligence algorithms for deep learning, establish a fracture type recognition model, and form a fracture database.

[0024] The model training in this embodiment is carried out under the Windows 11 Professional Workstation Edition operating system. The processor model is Intel Core i7-10700 @ 2.9 GHz, the graphics card model is Nvidia RTX 4090 24 GB, the memory is DDR 4 2400 MHz 48 GB, the framework is Pytorch 2.1, Python 3.10, CUDA 11.7, Anaconda 23.1.0, MMDetection 3.10, and the IED tool is VS Code. To ensure the controllability of variables, all experiments are tested in this environment.

[0025] In step S16, the specific process of establishing the fracture type recognition model is as follows: Step S161: The medical image fracture region category and its corresponding sub-block image constitute a label and training sample set; Step S162: introducing the labels and training sample sets into the YOLOv5 network for network training; The YOLOv5 network is mainly composed of data input layer, convolution layer, pooling layer, fully connected layer and output layer; the specific functions of each layer are as follows: Data input layer: receives data such as images, usually a multidimensional array, such as a color image which is a three-dimensional array (height, width, color channels).

[0026] Convolution layer: The convolution kernel is used to perform convolution operations on the input data to extract local features of the image. The convolution kernel slides over the image and performs weighted summation on each local area to obtain a feature map.

[0027] Pooling layer: Downsample the feature map obtained by convolution to reduce the data dimension and the amount of calculation while retaining the main features as much as possible. Common pooling methods include maximum pooling and average pooling.

[0028] Fully connected layer: Integrates the features after multiple convolutions and pooling, and connects them to the output layer through a fully connected method to achieve tasks such as image classification or regression.

[0029] Output layer: The output layer outputs classification results or predicted values ​​according to task requirements.

[0030] Step S163: The YOLOv5 network uses convolution kernels of different sizes to achieve fusion of features of different scales; Step S164: extract features through convolution and pooling, using three consecutive Inception modules to perform convolution and pooling in parallel; Step S165: Integrate the features after multiple convolutions and pooling, and connect them to the output layer through a fully connected method; Step S166: Output the fracture classification results according to the task requirements.

[0031] In step S162, the trained original data is used to obtain the mean and the covariance matrix of the Gaussian density estimate , and obtain the following Gaussian probability density function for each category: ; In the formula, n is the number of training samples, D is the number of dimensions, is the mean vector, is the covariance matrix of the distribution, is the Gaussian probability density function The loss value is used to measure the difference between the model's predicted value and the true value. The loss value is calculated using the cross entropy loss function. Its purpose is to optimize the model's parameters by minimizing the loss function so that the model can better fit the training data. The training dataset is divided into two parts, one is the original dataset and the other is the enhanced dataset. The original dataset is obtained as the true value of the training set. The original and enhanced datasets are combined into a training set and input into the YOLOv5 network model for training. The loss function corresponding to the classifier is as follows: ; In the formula, , is the activation function, , are the internal weights, inputs, and biases of its nodes.

[0032] In step S2, the specific process of constructing the three-dimensional model of the patient's fracture part is as follows: Step S21: The patient needs to undergo a thin-slice spiral CT scan (slice thickness ≤ 1 mm) to obtain a high-resolution two-dimensional tomographic image sequence. Bone CT needs to use bone window parameters (window width 2000HU, window position 500HU) to enhance the contrast between bones and soft tissues; Step S22: Perform image enhancement, noise reduction and contrast adjustment on the original CT data to optimize the clarity of the bone edge. For example, the algorithm can be used to reduce artifact interference and improve the boundary recognition between cortical bone and cancellous bone; Step S23: using 3D reconstruction technology (such as surface rendering, voxel modeling) to convert the 2D sequence into a 3D data set, such as automatically segmenting continuous bone regions through a seed point expansion algorithm; Step S24: Use the mask editing tool to manually remove adhesions or irrelevant tissues in complex areas. You can also use the Magic Wand tool to quickly remove non-target bones such as the shoulder blade and sternum. Step S25: Apply a smoothing algorithm (such as smooth3D+) to reduce 3D surface jaggedness and improve the visual effect of the model; Step S26: Adjust color rendering and transparency to enhance anatomical structure recognition, rotate the 3D model at multiple angles to confirm that the bone morphology is consistent with clinical needs, and export the standard format for 3D printing or surgical planning system.

[0033] In step S4, due to the angle of medical image acquisition, it is sometimes inconvenient to perform 360-degree spiral photography of the fracture site. Therefore, when generating the three-dimensional bone model, the fracture cracks appear intermittently. Therefore, it is necessary to connect the fracture cracks of the same fracture part after generating the three-dimensional bone model. Assume that the two end points of the fracture crack are and , calculate the slope of the two endpoints respectively Use the point slope method to fit the straight line between the two endpoints. The specific formula is as follows: ; Calculate the slope , in MATLAB, the point-slope formula and loop statements are used to find the points on the straight line, and then connected with smooth curves to achieve artificial interactive fracture crack connection.

[0034] See also Figure 2 As shown, in step S5, the calculation process of the offset distance of the bones on both sides of the fracture crack is as follows: Step S51: Select three continuous rectangular areas with the same length and width from the leftmost vertex of the bone above the fracture crack as the origin, and name them A, B, and C respectively, and the corresponding area distribution is ; Step S52: Select three continuous rectangular areas with the same length and width on the left side of the bone below the fracture crack, and name them D, E, and F respectively, and the corresponding area distribution is ; Step S53: Use the cv2.contour function in OpenCV to select the bone crack and the selected 6 contour areas for calculation, and obtain the area of ​​the three rectangles above and the area composed of the fracture crack. , and the area of ​​the three rectangles below and the area of ​​the fracture crack ; Step S54: Determine the offset distance of the bones on both sides of the fracture crack according to the length and area data of the fracture crack.

[0035] In step S54, the Spearman correlation coefficient method is used to analyze the medical images after different fractures to obtain relevant image feature data to determine the offset distance of the bones on both sides of the fracture crack. The specific calculation formula of the Spearman correlation coefficient method is as follows: ; In the formula, Observations after sorting at different angles The rank of are the average ranks of the variables, and N is the total amount of data.

[0036] Assume that the observed values ​​in the two variables are The rank difference of ,but: .

[0037] It is worth noting that in the above system embodiment, the various units included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0038] In addition, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiments can be completed by instructing related hardware through a program, and the corresponding program can be stored in a computer-readable storage medium.

[0039] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for fracture type identification and reduction path planning, characterized in that: The steps include: Step S1: Acquire medical imaging data of the fracture area of ​​the patient, wherein the medical imaging data includes CT images, X-ray images and MRI images; Step S2: constructing a three-dimensional model of the patient's fractured part based on the medical imaging data of the fractured area; Step S3: The fracture type recognition model recognizes the fracture contour on the three-dimensional model of the patient's fracture part; Step S4: splicing the fracture cracks of the fractured part; Step S5: calculating the offset distance of the bones on both sides of the fracture crack; Step S6: Visually display the reduction path on the three-dimensional model of the patient's fracture.

2. A method for fracture type identification and reduction path planning according to claim 1, characterized in that: In step S1, the acquired medical image data needs to be preprocessed, and the specific preprocessing process is as follows: Step S11: performing noise reduction processing on the medical image data by Gaussian filtering; Step S12: Use the Sobel algorithm to calculate the gradient value of each pixel on the medical image, obtain the edge strength and direction of the pixel in the horizontal and vertical directions, and realize the monitoring of the edge of the medical image. The specific formula of the gradient amplitude is: ； In the formula, Respectively represent the gradient value of the pixel in the horizontal and vertical directions, is the gradient amplitude; The formula for the specific gradient direction is: ； In the formula, is the inverse tangent function, is the gradient direction; Step S13: using a non-maximum suppression algorithm to enhance the contour clarity of the medical image; Step S14: using a dual threshold detection algorithm to classify pixels in the medical image; the pixels are classified into strong edges and weak edges according to the size of the gradient threshold; Step S15: connecting strong edge pixels to form the edge contour of the bone, and connecting weak edge pixels to form cracks of bone fractures; Step S16: Classify and annotate the medical images, compare the similarity of multiple medical image features, use artificial intelligence algorithms for deep learning, establish a fracture type recognition model, and form a fracture database.

3. A method for fracture type identification and reduction path planning according to claim 2, characterized in that: In step S16, the specific process of establishing the fracture type identification model is as follows: Step S161: The medical image fracture region category and its corresponding sub-block image constitute a label and training sample set; Step S162: introducing the labels and training sample sets into the YOLOv5 network for network training; Step S163: The YOLOv5 network uses convolution kernels of different sizes to achieve fusion of features of different scales; Step S164: extract features through convolution and pooling, using three consecutive Inception modules to perform convolution and pooling in parallel; Step S165: Integrate the features after multiple convolutions and pooling, and connect them to the output layer through a fully connected method; Step S166: Output the fracture classification results according to the task requirements.

4. A method for fracture type identification and reduction path planning according to claim 3, characterized in that: In step S162, the trained original data is used to obtain the mean and the covariance matrix of the Gaussian density estimate , and obtain the following Gaussian probability density function for each category: ； In the formula, n is the number of training samples, D is the number of dimensions, is the mean vector, is the covariance matrix of the distribution, is a Gaussian probability density function.

5. A method for fracture type identification and reduction path planning according to claim 3, characterized in that: In step S165, during the YOLOv5 network training process, the loss function corresponding to the classifier is as follows: ； In the formula, , is the activation function, , are the internal weights, inputs, and biases of its nodes.

6. A fracture type identification and reduction path planning method according to claim 1, characterized in that: In step S2, the specific process of constructing the three-dimensional model of the patient's fracture part is as follows: Step S21: The patient needs to undergo a thin-slice spiral CT scan to obtain a high-resolution two-dimensional tomographic image sequence; Step S22: using the preprocessing method in step S1 to process the medical image; Step S23: converting the two-dimensional sequence into a three-dimensional data set using three-dimensional reconstruction technology; Step S24: Use mask editing tools for complex areas to manually remove adhesions or irrelevant tissues; Step S25: Apply a smoothing algorithm to reduce 3D surface jaggedness; Step S26: Adjust color rendering and transparency, and export to a standard format for 3D printing or surgical planning systems.

7. A method for fracture type identification and reduction path planning according to claim 1, characterized in that: In step S3, the fracture type recognition model identifies each bone block and other tissues in the medical image, extracts the edge feature points of each bone block and compares them with the feature points in the fracture database to obtain the spatial position, boundary and shape of the fractured bone block, and marks each bone block with a corresponding color.

8. A method for fracture type identification and reduction path planning according to claim 1, characterized in that: In step S4, the fracture cracks of the same fracture part are connected, and the two end points of the fracture crack are respectively and , calculate the slope of the two endpoints respectively Use the point slope method to fit the straight line between the two endpoints. The specific formula is as follows: ； Calculate the slope , use the point-slope formula and loop statements in MATLAB to find the points on the straight line and connect them with smooth curves.

9. A method for fracture type identification and reduction path planning according to claim 1, characterized in that: In step S5, the calculation process of the offset distance of the bones on both sides of the fracture crack is as follows: Step S51: Select three continuous rectangular areas with the same length and width from the leftmost vertex of the bone above the fracture crack as the origin, and name them A, B, and C respectively, and the corresponding area distribution is ; Step S52: Select three continuous rectangular areas with the same length and width on the left side of the bone below the fracture crack, and name them D, E, and F respectively, and the corresponding area distribution is ; Step S53: Use the cv2.contour function in OpenCV to select the bone crack and the selected 6 contour areas for calculation, and obtain the area of ​​the three rectangles above and the area composed of the fracture crack. , and the area of ​​the three rectangles below and the area of ​​the fracture crack ; Step S54: Determine the offset distance of the bones on both sides of the fracture crack according to the length and area data of the fracture crack.

10. A method for fracture type identification and reduction path planning according to claim 9, characterized in that: In step S54, the Spearman correlation coefficient method is used to analyze the medical images after different fractures to obtain relevant image feature data to determine the offset distance of the bones on both sides of the fracture crack. The specific calculation formula of the Spearman correlation coefficient method is as follows: ； In the formula, Observations after sorting at different angles The rank of are the average ranks of the variables, and N is the total amount of data.

Images