A system and method for dividing the acetabulum and femur and identifying the femoral head

Abstract

The present invention relates to the technical field of medical image processing, and provides a system for segmenting the acetabulum and femur and identifying the femoral head, including a memory; an image acquisition device; a processor; the processor includes: an image reading module for reading an acetabulum-femur image; an image segmentation module for segmenting the acetabulum-femur image by using a region growing algorithm according to the range of pixel values of pixel points, and the region surrounded by the pixel points within the range of pixel values is an acetabulum position segmentation map or a femur position segmentation map; a femoral head identification module for identifying the femoral head by using a femur identification algorithm based on the femur position segmentation map, and calculating the center position and the maximum radius of the femoral head. The system execution process is clear and simple, the input parameters of the algorithm can be automatically adjusted by the user according to the data situation, it is applicable to different types of lesion images, saves the development cost and improves the development efficiency under the condition of achieving the same effect, and provides a guarantee for the rapid verification of preoperative planning.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and particularly to a system and method for segmenting the acetabulum and femur and identifying the femoral head. Background Art

[0002] In image-guided arthroscopic hip minimally invasive surgery, it is usually necessary to preprocess the three-dimensional CT images obtained before surgery, segment the acetabulum and femur, find the center position of the femoral head sphere, and calculate its maximum radius. Thereby, subsequent preoperative grinding area planning is carried out for use in intraoperative navigation.

[0003] In the prior art, the mainstream approach for identifying the femoral head of the hip joint is to segment the acetabulum and femur, then select a femoral head area, obtain most of the point sets where the femoral head area is located, and then use a spherical fitting algorithm to identify the femoral head and calculate the center position and radius of the sphere.

[0004] However, the common practices in the prior art generally encounter two problems. One problem is that when encountering actual diseased images with uneven bone density distribution and relatively narrow acetabulum and femoral head regions, traditional image processing algorithms cannot successfully segment the acetabulum and femur, while using deep learning segmentation algorithms requires a large number of training samples and manual annotation, which is time-consuming and inefficient; another problem is that when performing spherical fitting of the femur after segmentation, since the femoral head data is not actually distributed on a sphere, there are significant differences between the fitting results and the actual position of the femur, and the fitting algorithm takes a long time. Summary of the Invention

[0005] In view of the above problems, the purpose of the present invention is to provide a system and method for segmenting the acetabulum and femur and identifying the femoral head. The system execution process is clear and simple, the effect is obvious, the input parameters of the algorithm can be automatically adjusted by the user according to the data situation, and it is applicable to different types of diseased images. Under the condition of achieving the same effect, the development cost is saved and the development efficiency is improved, providing a guarantee for the rapid verification of subsequent operations such as preoperative planning.

[0006] The above object of the present invention is achieved by the following technical solutions:

[0007] A system for segmenting the acetabulum and femur and identifying the femoral head, comprising:

[0008] A memory that stores the obtained acetabulum-femur images that need to be segmented for the acetabulum and femur and identify the femoral head, as well as the segmented acetabulum position segmentation map, femur position segmentation map, calculated center position of the femoral head, and maximum radius;

[0009] An image acquisition device for acquiring the acetabular femoral image including acetabular and femoral tissues before the image-guided minimally invasive arthroscopic hip surgery;

[0010] A processor for segmenting the acetabulum and femur of the acetabular femoral image presenting the diseased bone tissue acquired before the image-guided minimally invasive arthroscopic hip surgery during the image-guided minimally invasive arthroscopic hip surgery, and identifying the femoral head for navigation use in the subsequent image-guided minimally invasive arthroscopic hip surgery, and segmenting the acetabulum and femur and identifying the femoral head through the following modules:

[0011] An image reading module for reading the acetabular femoral image that needs to be segmented for the acetabulum and femur and identify the femoral head, where the acetabular femoral image is an image including acetabular and femoral tissues acquired by the image acquisition device before the image-guided minimally invasive arthroscopic hip surgery;

[0012] An image segmentation module for segmenting the acetabular femoral image by using a region growing algorithm according to the range of pixel values of pixel points, and the region enclosed by the pixel points within the range of the pixel values is an acetabular position segmentation map or a femoral position segmentation map;

[0013] A femoral head identification module for identifying the femoral head based on the femoral position segmentation map by using a femoral identification algorithm, and calculating the center position and the maximum radius of the femoral head.

[0014] Further, the processor further includes a gradient image calculation module;

[0015] The gradient image calculation module is used to calculate the gradient of the acetabular femoral image, obtain the gradient image of the acetabular femoral image, and superimpose the gradient image on the original acetabular femoral image before segmenting the acetabulum and femur by using the image segmentation module, where the target region is the region where the acetabulum or the femur is located, and the non-target region is the region other than the regions where the acetabulum and the femur are located.

[0016] Further, in the gradient image calculation module, calculating the gradient of the acetabular femoral image, obtaining the gradient image of the acetabular femoral image, and superimposing the gradient image on the original acetabular femoral image specifically includes:

[0017] Obtaining the gradient image by using a Gaussian function for image filtering and edge detection;

[0018] Select the Gaussian function parameter σ, where the Gaussian function parameter σ is selected according to data conditions including the image noise level, image resolution, image contrast and brightness, and the size of the target area of the acetabular femoral image. The higher the image noise level, the larger the Gaussian function parameter σ; the lower the image resolution, the larger the Gaussian function parameter σ; the lower the image contrast and brightness, the larger the Gaussian function parameter σ; and the smaller the target area, the larger the Gaussian function parameter σ.

[0019] Substitute the Gaussian function parameter σ into the Gaussian function to calculate the first-order partial derivative of the Gaussian function, thereby obtaining the first-order gradient function of the acetabular femoral image.

[0020] Discretize the first-order gradient function to obtain a first-order gradient operator, and use the first-order gradient operator to convolve with the acetabular femoral image to calculate the gradient magnitude of each pixel point, and obtain the gradient image representing the image gradient magnitude.

[0021] Further, in the image segmentation module, adopt the region growing algorithm to segment the acetabular femoral image according to the range of pixel values of the pixel points. The region enclosed by the pixel points within the range of the pixel values is the acetabular position segmentation map or the femoral position segmentation map. Specifically:

[0022] Click n + 1 pixel points on the acetabular femoral image as seed points. The first n clicked seed points are on the target area, and the (n + 1)th seed point is on the non-target area.

[0023] Calculate the upper bound threshold and the lower bound threshold for segmenting the acetabular femoral image through the pixel values of the n + 1 clicked seed points.

[0024] Starting from the seed points, use the upper bound threshold and the lower bound threshold as boundaries to perform a breadth-first search on the acetabular femoral image to obtain the target segmentation result. Among them, the breadth-first search is an algorithm for traversing the image storage structure, traversing each vertex in the acetabular femoral image one by one from six directions: up, down, left, right, front, and back, and obtaining all pixel points that meet the upper bound threshold and the lower bound threshold as the target segmentation result. The image corresponding to the target segmentation result is the acetabular position segmentation map or the femoral position segmentation map.

[0025] Further, in the image segmentation module, calculate the upper bound threshold and the lower bound threshold for segmenting the acetabular femoral image through the pixel values of the n + 1 clicked seed points. Specifically:

[0026] Calculate the mean value of the pixel values of the first n seed points.

[0027] Add the first preset value to the average pixel value of the first n of the seed points as the upper bound threshold;

[0028] Subtract the second preset value from the average pixel value of the first n of the seed points as the lower bound preset value, compare the lower bound preset value with the pixel value of the (n + 1)-th seed point, and take the larger value of the lower bound preset value and the pixel value of the (n + 1)-th seed point as the lower bound threshold.

[0029] Further, in the image segmentation module, it further includes: smoothing the edge of the target segmentation result, specifically:

[0030] Obtain the edge region of the target segmentation result through edge detection algorithms including Sobel and Canny;

[0031] Perform a dilation operation on the obtained edge region to expand the edge region by a preset number of pixels to ensure that the edge information of the target segmentation result is not lost in subsequent smoothing operations;

[0032] Apply a smoothing filter including Gaussian filter and bilateral filter to the dilated edge region for smoothing to reduce edge noise and discontinuity and make the edge smooth;

[0033] Perform an erosion operation on the smoothed edge region to restore the edge region to its original size, retain the main information of the edge, and remove unnecessary pixels introduced during the smoothing process;

[0034] Merge the smoothed edge region with the original target segmentation result to obtain the finally smoothed target segmentation result.

[0035] Further, in the femoral head recognition module, calculate the position of the center of the ball, specifically:

[0036] Mark the pixel values of the pixel points in the segmented femoral position segmentation map in the image segmentation module with 1 and 0, where 1 represents the femur and 0 represents the non-target area;

[0037] Take slice data from the positive z-axis direction towards the origin, sum the pixel values in the slice data, and when encountering the first slice data whose sum of pixel values is not 0, the average value of the x-axis coordinate values of the non-zero pixel points in the slice data is the x-coordinate of the center of the ball position, denoted as x, the average value of the y-axis coordinate values of the non-zero pixel points in the slice data is the y-coordinate of the center of the ball position, denoted as y, and at the same time, record the z-axis coordinate of the slice data at this time as z1;

[0038] Take slice data from the positive x-axis direction towards the origin, sum the pixel values in the slice data, and when encountering the first slice data where the sum of the pixel values is not 0, the average value of the z-axis coordinate values of the non-zero pixel points in the slice data is the z-coordinate of the center position of the sphere, denoted as z. At the same time, record the x-axis coordinate of the slice data at this time as x1.

[0039] Further, in the image segmentation module, calculate the maximum radius, specifically:

[0040] Obtain the maximum value in z1 - z and x1 - x, and this maximum value is the maximum radius.

[0041] A method for segmenting the acetabulum and femur and identifying the femoral head using the system for segmenting the acetabulum and femur and identifying the femoral head as described above includes:

[0042] S1: Read the acetabulum and femur image that needs to be segmented for the acetabulum and femur and identify the femoral head, where the acetabulum and femur image is an image including acetabulum and femoral tissues obtained by a medical imaging device before the preoperative image-guided arthroscopic minimally invasive surgery for the hip joint.

[0043] S2: Use the region growing algorithm to segment the acetabulum and femur image according to the range of pixel values of the pixel points. The region surrounded by the pixel points within the range of the pixel values is to obtain the acetabulum position segmentation map or the femur position segmentation map.

[0044] S3: Based on the femur position segmentation map, use the femur recognition algorithm to identify the femoral head and calculate the center position and the maximum radius of the femoral head.

[0045] A computer-readable storage medium stores computer code, and when the computer code is executed, the method as described above is executed.

[0046] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0047] (1) By providing a system for segmenting the acetabulum and femur and identifying the femoral head, including a memory that stores the acquired acetabulum-femur image that needs to be segmented and the femoral head identified, as well as the segmented acetabulum position segmentation map, femur position segmentation map, calculated center position of the femoral head, and maximum radius; an image acquisition device for acquiring the acetabulum-femur image including acetabulum and femur tissues before the image-guided arthroscopic minimally invasive surgery; and a processor for segmenting the acetabulum and femur of the preoperatively acquired acetabulum-femur image presenting the diseased bone tissue during the image-guided arthroscopic minimally invasive surgery, and identifying the femoral head for use in navigation during the subsequent image-guided arthroscopic minimally invasive surgery, and segmenting the acetabulum and femur and identifying the femoral head through the following modules: an image reading module for reading the acetabulum-femur image that needs to be segmented and the femoral head identified, where the acetabulum-femur image is an image including acetabulum and femur tissues acquired by the image acquisition device before the image-guided arthroscopic minimally invasive surgery; an image segmentation module for segmenting the acetabulum-femur image using a region growing algorithm based on the range of pixel values of pixel points, and the region enclosed by the pixel points within the range of pixel values is the acetabulum position segmentation map or the femur position segmentation map; a femoral head identification module for identifying the femoral head using a femur identification algorithm based on the femur position segmentation map, and calculating the center position of the femoral head and the maximum radius. The above technical solution is a simple process for segmenting the acetabulum and femur and identifying the femoral head, which can achieve rapid segmentation of the acetabulum and femur, as well as rapid positioning of the femur position and size, and has the characteristics of short time consumption and good effect.

[0048] (2) When the gap between the femur and the acetabulum is narrow, or the pixel value difference between the non-target area and the target area is not obvious, calculate the gradient of the acetabulum-femur image, obtain the gradient image of the acetabulum-femur image, and superimpose the gradient image on the original acetabulum-femur image, where the target area is the area where the acetabulum or the femur is located, and the non-target area is the area other than the area where the acetabulum and the femur are located. The above technical solution can well segment the acetabulum and femur, as well as segment the target area and the non-target area for the actual diseased images with uneven bone density distribution and images with relatively narrow areas of the acetabulum and femoral head by superimposing the gradient map on the original image. Brief Description of the Drawings

[0049] Figure 1 It is the overall algorithm diagram executed by the processor in the system for segmenting the acetabulum and femur and identifying the femoral head of the present invention;

[0050] Figure 2 It is the flowchart of the gradient calculation algorithm of the present invention;

[0051] Figure 3 Schematic diagram of the gradient image of the present invention;

[0052] Figure 4 Flowchart of the region growing algorithm of the present invention;

[0053] Figure 5 Segmentation map of the femoral position of the present invention;

[0054] Figure 6 Segmentation map of the acetabular position of the present invention;

[0055] Figure 7 Flowchart of the femoral recognition algorithm of the present invention, where 7a and 7b are the flowchart and schematic diagram for calculating the x and y coordinates of the center of the sphere, and 7c and 7d are the flowchart and schematic diagram for calculating the z coordinate of the center of the sphere;

[0056] Figure 8 Result map of the center and radius of the femoral head of the present invention;

[0057] Figure 9 Overall flowchart of the method for segmenting the acetabulum and femur and identifying the femoral head of the present invention. Detailed implementation manners

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0059] Those skilled in the art of the present technology can understand that unless specifically stated otherwise, the singular forms "a", "an", "the", and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present invention means the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or their groups.

[0060] First embodiment

[0061] This embodiment provides a system for segmenting the acetabulum and femur and identifying the femoral head. After reading in the acetabulum-femur image, it is possible to customize whether to calculate the image gradient and customize the choice of whether to overlay the gradient image on the original image; apply the region growing algorithm to the read acetabulum-femur image, manually input the seed points by the user to segment the acetabulum and femur, and apply the femoral head recognition algorithm to the femur alone to calculate the center position and maximum radius of the femoral head. The system specifically includes:

[0062] A memory that stores the acquired acetabular femoral images that need to be segmented and the femoral head identified, as well as the segmented acetabular position segmentation map, femoral position segmentation map, calculated center position and maximum radius of the femoral head;

[0063] An image acquisition device for acquiring the acetabular femoral images including acetabular and femoral tissues before the image-guided arthroscopic hip minimally invasive surgery;

[0064] A processor for segmenting the acetabulum and femur of the acetabular femoral images presenting diseased bone tissues acquired before the image-guided arthroscopic hip minimally invasive surgery, and identifying the femoral head for use in navigation during the subsequent image-guided arthroscopic hip minimally invasive surgery, and through the following modules using the process as Figure 1 shown to segment the acetabulum and femur and identify the femoral head:

[0065] An image reading module for reading the acetabular femoral images that need to be segmented and the femoral head identified, where the acetabular femoral images are images including acetabular and femoral tissues acquired by the image acquisition device before the image-guided arthroscopic hip minimally invasive surgery.

[0066] Specifically, first, it is necessary to read the acetabular femoral images of the diseased tissues for the image-guided arthroscopic hip minimally invasive surgery. The acetabular femoral images can be three-dimensional CT images or two-dimensional X-ray images, etc., any one of the commonly used images in medicine. The working process of the present invention is applicable to any one of the commonly used images in medicine.

[0067] An image segmentation module for segmenting the acetabular femoral images using a region growing algorithm according to the range of pixel values of pixel points, and the region enclosed by the pixel points within the range of the pixel values is the acetabular position segmentation map or the femoral position segmentation map.

[0068] Specifically, as Figure 2 shown, the processor further includes a gradient image calculation module. Before segmenting the acetabulum and femur using the image segmentation module, considering that when the gap between the femur and the acetabulum in some of the read acetabular femoral images is narrow, or the pixel value difference between the non-target area and the target area is not obvious, in order to distinguish the femoral edge, acetabular edge, and non-target area, the gradient algorithm is defined to be optionally enabled by the user according to the actual situation of the acetabular femoral images. The gradient algorithm is to calculate the gradient of the acetabular femoral images, obtain the gradient image of the acetabular femoral images, and superimpose the gradient image on the original acetabular femoral images. The gradient algorithm specifically includes:

[0069] The gradient image is obtained by using a Gaussian function for image filtering and edge detection. The Gaussian function parameter σ is selected according to the data conditions of the acetabular femoral image, where the Gaussian function parameter σ is selected according to the data conditions including the image noise level, image resolution, image contrast and brightness, and the size of the target area of the acetabular femoral image. The higher the image noise level, the larger the Gaussian function parameter σ; the lower the image resolution, the larger the Gaussian function parameter σ; the lower the image contrast and brightness, the larger the Gaussian function parameter σ; and the smaller the target area, the larger the Gaussian function parameter σ.

[0070] Substitute the Gaussian function parameter σ into the Gaussian function to calculate the first-order partial derivative of the Gaussian function, thereby obtaining the first-order gradient function of the acetabular femoral image. Discretize the first-order gradient function to obtain a first-order gradient operator, and use the first-order gradient operator to convolve with the acetabular femoral image to calculate the gradient magnitude of each pixel point, and obtain the gradient image representing the image gradient magnitude. The Gaussian function parameter σ is selected by the user according to the actual situation of the acetabular femoral image. As Figure 3 shown, it is the gradient map of the acetabular femoral image when σ = 5.

[0071] The principle of obtaining the gradient image by using the Gaussian function is as follows: The Gaussian function adopted in the present invention is a technique commonly used in image filtering and edge detection. Gaussian filtering is a typical low-pass filter and has a smoothing effect on the image. At the same time, the first-order and second-order derivatives of the Gaussian function can also be used for high-pass filtering. For example, the first-order derivative of the Gaussian function is used in the canny operator, and the second-order derivative of the Gaussian function is used in the LOG operator. The following successively sorts out the definitions of the one-dimensional and two-dimensional Gaussian functions and the formulas of the first-order and second-order derivatives.

[0072] One-dimensional Gaussian function:

[0073]

[0074] Two-dimensional Gaussian function:

[0075]

[0076] The first-order partial derivative of the second-order Gaussian function is:

[0077]

[0078] The second-order partial derivative of the two-dimensional Gaussian function is:

[0079]

[0080] In image processing, the definitions of the first-order gradient and second-order gradient of the two-dimensional Gaussian function are:

[0081]

[0082] The directional gradient is (where the angle θ is in radians):

[0083]

[0084] By discretizing the gradient function, first-order and second-order gradient operators can be obtained. Using these operators to convolve with the image, the first-order and second-order gradients of the image and the gradients in each direction can be calculated.

[0085] As Figure 4 shown, after determining whether to use the gradient algorithm to process the image, the region growing algorithm is formally adopted to segment the acetabulum-femur image to obtain the acetabulum position segmentation map and the femur position segmentation map. Specifically:

[0086] Click n + 1 pixel points on the acetabulum-femur image as seed points. The first n of the clicked seed points are on the target region, and the (n + 1)-th seed point is on the non-target region.

[0087] Calculate the upper bound threshold and the lower bound threshold for segmenting the acetabulum-femur image based on the pixel values of the n + 1 clicked seed points. Specifically:

[0088] Calculate the average value of the pixel values of the first n seed points as mid_val, that is

[0089]

[0090] Then, based on the characteristics of bone density, add a first preset value to the average value of the pixel values of the first n seed points as the upper bound threshold. In this embodiment, the first preset value is taken as 350 for example, that is, the upper bound threshold is upper_thresh = mid_val + 350.

[0091] Subtract a second preset value from the average value of the pixel values of the first n seed points as the lower bound preset value. In this embodiment, the second preset value is taken as 350 for example, that is, the lower bound preset value is mid_val - 350. Compare the lower bound preset value with the pixel value of the (n + 1)-th seed point (black_val = input n )), and take the larger value of the lower bound preset value and the pixel value of the (n + 1)-th seed point as the lower bound threshold, that is, the lower bound threshold is lower_thresh = max(mid_val - 350, black_val).

[0092] Starting from the seed points, with the upper bound threshold and the lower bound threshold as boundaries, perform a breadth-first search on the acetabular femoral image. Breadth-first search is an algorithm for traversing a graph storage structure that visits the vertices in the graph, ensuring that each vertex is visited only once. For the current pixel point, set to traverse each vertex in the acetabular femoral image one by one in six directions: up, down, left, right, front, and back. Set all eligible pixel points to 1 and ineligible ones to 0. When the iteration stops, obtain all the pixel points that meet the upper bound threshold and the lower bound threshold as the target segmentation result, and the image corresponding to the target segmentation result is the acetabular position segmentation map or the femoral position segmentation map. As Figure 5 shown in the femoral position segmentation map, as Figure 6 described as the acetabular position segmentation map. Since there are obvious gaps between the femur and the acetabulum themselves or after gradient processing in the figure, the femur and the acetabulum are easily segmented.

[0093] Furthermore, in the image segmentation module, it further includes: smoothing the edge of the target segmentation result, specifically:

[0094] Obtain the edge region of the target segmentation result through edge detection algorithms including Sobel and Canny;

[0095] Perform a dilation operation on the obtained edge region to expand the edge region by a preset number of pixels to ensure that the edge information of the target segmentation result is not lost during subsequent smoothing operations;

[0096] Apply a smoothing filter including Gaussian filter and bilateral filter to the dilated edge region for smoothing to reduce edge noise and discontinuity and make the edge smooth;

[0097] Perform an erosion operation on the smoothed edge region to restore the edge region to its original size, retain the main information of the edge, and remove unnecessary pixels introduced during the smoothing process;

[0098] Merge the smoothed edge region with the original target segmentation result to obtain the finally smoothed target segmentation result.

[0099] The femoral head recognition module is used to, as Figure 7 shown, based on the femoral position segmentation map, adopt a femoral recognition algorithm to recognize the femoral head and calculate the center position and the maximum radius of the femoral head, specifically:

[0100] (1) Calculate the center position, specifically:

[0101] In the image segmentation module, the pixel values of the pixel points in the segmented femoral position segmentation map are marked with 1 and 0, where 1 represents the femur and 0 represents the non-target area.

[0102] As Figure 7 shown in FIGS. a and 7b, slice data is taken from the positive z-axis direction towards the origin, and the pixel values in the slice data are summed. When the sum of the pixel values of the first slice data that is not zero is encountered, the average value of the x-axis coordinate values of the non-zero pixel points in the slice data is the x-coordinate of the center position of the sphere, denoted as x, and the average value of the y-axis coordinate values of the non-zero pixel points in the slice data is the y-coordinate of the center position of the sphere, denoted as y. At the same time, the z-axis coordinate of the slice data at this time is denoted as z1.

[0103] As Figure 7 shown in FIGS. c and 7d, slice data is taken from the positive x-axis direction towards the origin, and the pixel values in the slice data are summed. When the sum of the pixel values of the first slice data that is not zero is encountered, the average value of the z-axis coordinate values of the non-zero pixel points in the slice data is the z-coordinate of the center position of the sphere, denoted as z. At the same time, the x-axis coordinate of the slice data at this time is denoted as x1.

[0104] (2) Calculate the maximum radius, specifically:

[0105] Obtain the maximum value of z1 - z and x1 - x, and the maximum value is the maximum radius. That is, r = max(z1 - z, x1 - x). Figure 8 It is a sectional view drawn based on the calculated center of the femoral head and the radius.

[0106] Second Embodiment

[0107] As Figure 9 shown, this embodiment provides a method for segmenting the acetabulum and femur and identifying the femoral head, which is executed by a system for segmenting the acetabulum and femur and identifying the femoral head as in the first embodiment, including:

[0108] S1: Read the acetabulum and femur image that needs to be segmented for the acetabulum and femur and identify the femoral head, where the acetabulum and femur image is an image including acetabulum and femoral tissues obtained by a medical imaging device before the image-guided hip arthroscopic minimally invasive surgery;

[0109] S2: Use the region growing algorithm to segment the acetabulum and femur image according to the range of pixel values of the pixel points. The region surrounded by the pixel points within the range of pixel values is to obtain the acetabulum position segmentation map or the femoral position segmentation map;

[0110] S3: Using a femur recognition algorithm based on the femur position segmentation map, identify the femoral head and calculate the center position and maximum radius of the femoral head.

[0111] A computer-readable storage medium stores computer code that, when executed, performs the above-described method. Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be accomplished by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium, which can include: read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs, etc.

[0112] The above are only the preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments. Any technical solutions falling within the concept of the present invention are within the protection scope of the present invention. It should be noted that for those of ordinary skill in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as within the protection scope of the present invention.

[0113] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0114] It should be noted that the above embodiments can be freely combined as needed. The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be regarded as within the protection scope of the present invention.

Claims

1. A system for dividing the acetabulum and femur and identifying the femoral head, characterized in that, Including: A memory that stores the obtained acetabular femoral image that needs to be segmented and the femoral head needs to be recognized, as well as the segmented acetabular position segmentation map, femoral position segmentation map, calculated center position of the femoral head and maximum radius; An image acquisition device that is used to acquire the acetabular femoral image including acetabular and femoral tissues before the image-guided arthroscopic hip minimally invasive surgery; A processor that is used to segment the acetabulum and femur of the acetabular femoral image presenting the diseased bone tissue obtained before the image-guided arthroscopic hip minimally invasive surgery, and recognize the femoral head for use in navigation during the subsequent image-guided arthroscopic hip minimally invasive surgery, and segment the acetabulum and femur and recognize the femoral head through the following modules: An image reading module that is used to read the acetabular femoral image that needs to be segmented and the femoral head needs to be recognized, where the acetabular femoral image is an image including acetabular and femoral tissues obtained by the image acquisition device before the image-guided arthroscopic hip minimally invasive surgery; An image segmentation module that is used to segment the acetabular femoral image according to the range of pixel values of pixel points by using a region growing algorithm, and the region surrounded by the pixel points within the range of the pixel values is the acetabular position segmentation map or femoral position segmentation map; A femoral head recognition module that is used to recognize the femoral head based on the femoral position segmentation map by using a femoral recognition algorithm, and calculate the center position and maximum radius of the femoral head; The processor further includes a gradient image calculation module; The gradient image calculation module is used to calculate the gradient of the acetabular femoral image and obtain the gradient image of the acetabular femoral image before segmenting the acetabulum and femur by using the image segmentation module when the gap between the femur and the acetabulum in the read acetabular femoral image is narrow, or the pixel value difference between the non-target area and the target area is not obvious, and superimpose the gradient image on the original acetabular femoral image, where the target area is the area where the acetabulum or the femur is located, and the non-target area is the area other than the area where the acetabulum and the femur are located; Calculating the center position specifically as: Mark the pixel values of the pixel points in the segmented femoral position segmentation map in the image segmentation module with 1 and 0, where 1 represents the femur and 0 represents the non-target area; Take slice data from the positive z-axis direction towards the origin direction, sum the pixel values in the slice data, and when encountering the first slice data whose sum of pixel values is not 0, the average value of the x-axis coordinate values of the non-zero pixel points in the slice data is the x coordinate of the center position of the femoral head, denoted as x, the average value of the y-axis coordinate values of the non-zero pixel points in the slice data is the y coordinate of the center position of the femoral head, denoted as y, and at the same time record the z-axis coordinate of the slice data at this time as z1; Take slice data from the positive x-axis direction towards the origin direction, sum the pixel values in the slice data, and when encountering the first slice data where the sum of the pixel values is not 0, the average value of the z-axis coordinate values of the non-zero pixel points in the slice data is the z-coordinate of the center position of the sphere, denoted as z. At the same time, record the x-axis coordinate of the slice data at this time as x1; Calculate the maximum radius, specifically: Obtain the maximum value among z1 - z and x1 - x, and this maximum value is the maximum radius.

2. The system for dividing the acetabulum and femur and identifying the femoral head according to claim 1, wherein In the gradient image calculation module, calculate the gradient of the acetabular femoral image, obtain the gradient image of the acetabular femoral image, and superimpose the gradient image on the original acetabular femoral image, specifically: Use the Gaussian function for image filtering and edge detection to obtain the gradient image; Select Gaussian function parameters , wherein the Gaussian function parameters are selected according to data including the image noise level, image resolution, image contrast and brightness, and the size of the target area in the acetabular femoral image. The higher the image noise level, the larger the Gaussian function parameters; the lower the image resolution, the larger the Gaussian function parameters; the lower the image contrast and brightness, the larger the Gaussian function parameters; the smaller the target area, the larger the Gaussian function parameters. Substitute the Gaussian function parameters into the Gaussian function to calculate the first-order partial derivative of the Gaussian function, thereby obtaining the first-order gradient function of the acetabular femoral image; Discretize the first-order gradient function to obtain a first-order gradient operator, use the first-order gradient operator to convolve with the acetabular femoral image, calculate the gradient magnitude of each pixel point respectively, and obtain the gradient image representing the image gradient magnitude.

3. The system for dividing the acetabulum and femur and identifying the femoral head according to claim 1, characterized in that, In the image segmentation module, use the region growing algorithm to segment the acetabular femoral image according to the range of pixel values of pixel points. The region surrounded by the pixel points within the range of pixel values is the acetabular position segmentation map or the femoral position segmentation map, specifically: Click n + 1 pixel points on the acetabular femoral image as seed points. The first n clicked seed points are on the target area, and the (n + 1)-th clicked seed point is on the non-target area; Calculate the upper bound threshold and the lower bound threshold for segmenting the acetabular femoral image through the pixel values of the n + 1 clicked seed points; Starting from the seed points, with the upper bound threshold and the lower bound threshold as boundaries, perform a breadth-first search on the acetabular femoral image to obtain the target segmentation result. Among them, the breadth-first search is an algorithm for traversing the image storage structure, traversing each vertex in the acetabular femoral image one by one from six directions: up, down, left, right, front, and back, and obtaining all pixel points that meet the upper bound threshold and the lower bound threshold as the target segmentation result. The image corresponding to the target segmentation result is the acetabular position segmentation map or the femoral position segmentation map.

4. The system for dividing the acetabulum and femur and identifying the femoral head according to claim 3, wherein In the image segmentation module, calculate the upper bound threshold and the lower bound threshold for segmenting the acetabular femoral image through the pixel values of the n + 1 clicked seed points, specifically: Calculate the average value of the pixel values of the first n seed points; Add a first preset value to the average value of the pixel values of the first n seed points as the upper bound threshold; Subtract a second preset value from the average value of the pixel values of the first n seed points as the lower bound preset value, compare the lower bound preset value with the pixel value of the (n + 1)-th seed point, and take the larger value between the lower bound preset value and the pixel value of the (n + 1)-th seed point as the lower bound threshold.

5. The system for dividing the acetabulum femur and identifying the femoral head according to claim 3, characterized in that, In the image segmentation module, it also includes: smoothing the edge of the target segmentation result, specifically: Obtain the edge region of the target segmentation result through edge detection algorithms including Sobel and Canny; Perform a dilation operation on the obtained edge region to expand the edge region by a preset number of pixels, ensuring that the edge information of the target segmentation result is not lost during subsequent smoothing operations; Apply a smoothing filter including Gaussian filtering, bilateral filtering, etc. to the dilated edge region for smoothing to reduce edge noise and discontinuity and make the edge smooth; Perform an erosion operation on the smoothed edge region to restore the edge region to its original size, retain the main information of the edge, and remove unnecessary pixels introduced during the smoothing process; Perform image merging on the smoothed edge region and the original target segmentation result to obtain the finally smoothed target segmentation result.

6. A method for segmenting the acetabulum and femur and identifying the femoral head using the system for segmenting the acetabulum and femur and identifying the femoral head according to any one of claims 1-5, characterized in that, Including: S1: Read the acetabulum-femur image that needs to be segmented for the acetabulum and femur and identify the femoral head, where the acetabulum-femur image is an image including acetabulum and femoral tissues obtained by a medical imaging device before the image-guided arthroscopic minimally invasive hip surgery; S2: Use a region growing algorithm to segment the acetabulum-femur image according to the range of pixel values of pixel points, and the region enclosed by the pixel points within the range of pixel values is the obtained acetabulum position segmentation map or femur position segmentation map; S3: Based on the femur position segmentation map, use a femur recognition algorithm to identify the femoral head and calculate the center position and maximum radius of the femoral head.

7. A computer-readable storage medium storing computer code that, when executed by hardware, implements the method described in claim 6.

Images