System and method for segmenting acetabular femur and identifying femur head

By using regional growth algorithm and gradient image processing in minimally invasive hip arthroscopy, the problems of difficulty in segmentation between acetabular and femur and inaccurate spherical fit in traditional techniques are solved, and the rapid segmentation of acetabular and femur and femur head are achieved. The accurate identification of preoperative planning improves the efficiency and accuracy of preoperative planning.

CN118918071AActive Publication Date: 2024-11-08FIRST HOSPITAL AFFILIATED TO GENERAL HOSPITAL OF PLA

Patent Information

Application Number
CN202410953651.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-08
Estimated Expiration
2044-07-16

AI Technical Summary

Technical Problem

Prior Art In minimally invasive hip arthroscopy, traditional image processing algorithms are difficult to segment the acetabulum and femur. Especially in the case of uneven bone density distribution and narrow region, deep learning algorithms train samples in low efficiency, and spherical surfaces. The fitting results differ greatly from the actual position and take a long time.

Method used

The regional growth algorithm is used in combination with gradient image processing, and the gradient image is calculated by a Gaussian function to superimpose the gradient image on the original image. The breadth-first search and edge detection algorithm are used to perform segmentation of the acetabulum and femur and identify the femoral head, and the position and maximum radius of the sphere center are calculated.

Benefits of technology

It realizes rapid segmentation and accurate identification of the acetabular and femur, which is suitable for different types of lesion images, saves development costs, improves development efficiency, and ensures rapid verification of preoperative planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118918071A_ABST
    Figure CN118918071A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of medical image processing, and provides a system for segmenting an acetabular femur and identifying the femur head. An image acquisition device; a processor; the processor comprises an image reading module used for reading an acetabular thighbone image; the image segmentation module is used for segmenting the acetabular thighbone image according to the range of the pixel values of the pixel points by adopting a region growing algorithm, and a region defined by the pixel points in the range of the pixel values is an acetabular position segmentation image or a thighbone position segmentation image; and the femoral head recognition module is used for recognizing the femoral head by adopting a femoral recognition algorithm based on the femoral position segmentation map, and calculating the sphere center position and the maximum radius of the femoral head. The system execution process is clear and simple, input parameters of an algorithm can be automatically adjusted by a user according to data conditions, the method is suitable for different types of lesion images, under the condition that the same effect is achieved, the development cost is saved, the development efficiency is improved, and a guarantee is provided for rapid verification of preoperative planning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

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

[0003] In the prior art, the mainstream approach to hip joint femoral head identification 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 practice in the prior art generally encounters two problems. One problem is that when encountering an actual lesion image, the bone density distribution is uneven, and the area of ​​the acetabulum and femoral head is relatively narrow, the traditional image processing algorithm cannot successfully segment the acetabulum and femur, and the segmentation algorithm using deep learning requires more 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 is a large difference between the fitting result and the actual location 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 femoral head and identifying the femoral head. The system execution process is clear and simple, and 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 lesion images. While achieving the same effect, it saves development costs, improves development efficiency, and provides a guarantee for the rapid verification of subsequent operations such as preoperative planning.

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

[0007] A system for segmenting an acetabulum and femoral bone and identifying a femoral head, comprising:

[0008] A memory, which 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, the femoral position segmentation map, and the calculated spherical center position and maximum radius of the femoral head;

[0009] An image acquisition device, which is used to acquire the acetabulum-femur image including the acetabulum and femur tissues before image-guided minimally invasive hip arthroscopy surgery;

[0010] A processor is used to segment the acetabulum and femur of the acetabulum and femur image showing the diseased bone tissue obtained before the operation, and to identify the femoral head in the image-guided minimally invasive hip arthroscopy surgery, so as to be used for navigation in the subsequent image-guided minimally invasive hip arthroscopy surgery, and the acetabulum and femur are segmented and the femoral head is identified through the following modules:

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

[0012] An image segmentation module is used for segmenting the acetabulum femur image according to the range of pixel values ​​of the pixel points by using a region growing algorithm, wherein the region surrounded by the pixel points within the range of the pixel values ​​is the acetabulum position segmentation map or the femur position segmentation map;

[0013] The femoral head recognition module is used to identify the femoral head based on the femoral position segmentation map using a femoral recognition algorithm, and calculate the center position and maximum radius of the femoral head.

[0014] Furthermore, the processor also includes a gradient image calculation module;

[0015] The gradient image calculation module is used to calculate the gradient of the acetabulum-femur image before the image segmentation module is used to segment the acetabulum-femur, when the gap between the femur and the acetabulum in the read acetabulum-femur image is narrow, or the difference in pixel values ​​between the non-target area and the target area is not obvious, to obtain the gradient image of the acetabulum-femur image, and superimpose the gradient image on the original acetabulum-femur image, wherein 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.

[0016] Further, in the gradient image calculation module, the gradient of the acetabulum femur image is calculated, the gradient image of the acetabulum femur image is obtained, and the gradient image is superimposed on the original acetabulum femur image, specifically:

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

[0018] Selecting a Gaussian function parameter σ, wherein the Gaussian function parameter σ is selected based on data conditions of the acetabulum femoral image including image noise level, image resolution, image contrast and brightness, and the size of the target area, wherein 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] Substituting 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 acetabulum femur image;

[0020] The first-order gradient function is discretized to obtain a first-order gradient operator, and the first-order gradient operator is used to perform convolution with the acetabulum femur image, and the gradient size of each pixel point is calculated respectively to obtain the gradient image representing the image gradient size.

[0021] Further, in the image segmentation module, the region growing algorithm is used to segment the acetabulum femur image according to the range of pixel values ​​of the pixel points, and the area surrounded by the pixel points within the range of the pixel value is the acetabulum position segmentation map or the femur position segmentation map, specifically:

[0022] Click n+1 pixel points on the acetabulum femur image as seed points, wherein the first n seed points clicked are on the target area, and the n+1th seed point is on the non-target area;

[0023] The upper threshold and the lower threshold for segmenting the acetabulum femur image are calculated by the pixel values ​​of the clicked n+1 seed points;

[0024] Starting from the seed point, with the upper threshold and the lower threshold as boundaries, a breadth-first search is performed on the acetabulum femur image to obtain a target segmentation result, wherein the breadth-first search is an algorithm that traverses the image storage structure, traversing each vertex in the acetabulum femur image one by one from six directions: top, bottom, left, right, front, and back, to obtain all the pixel points that meet the upper threshold and the lower threshold as the target segmentation result, and the image corresponding to the target segmentation result is the acetabulum position segmentation map or the femur position segmentation map.

[0025] Further, in the image segmentation module, the upper threshold and the lower threshold for segmenting the acetabulum femur image are calculated by the pixel values ​​of the clicked n+1 seed points, specifically:

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

[0027] Adding a first preset value to the mean of the pixel values ​​of the first n seed points is used as the upper threshold;

[0028] The mean of the pixel values ​​of the first n seed points minus the second preset value is used as the lower bound preset value, the lower bound preset value is compared with the pixel value of the n+1th seed point, and the larger value between the lower bound preset value and the pixel value of the n+1th seed point is taken as the lower bound threshold.

[0029] Furthermore, the image segmentation module further includes: performing edge smoothing on the target segmentation result, specifically:

[0030] Obtaining the edge area of ​​the target segmentation result by edge detection algorithms including Sobel and Canny;

[0031] Performing a dilation operation on the acquired edge region so that the edge region is expanded by a preset number of pixels, thereby ensuring that a subsequent smoothing operation does not lose edge information of the target segmentation result;

[0032] Applying smoothing filters including Gaussian filtering and bilateral filtering to the expanded edge region to reduce noise and discontinuity of the edge and make the edge smooth;

[0033] Performing an erosion operation on the smoothed edge region to restore the edge region to its original size, retaining the main information of the edge, and removing unnecessary pixels introduced in the smoothing process;

[0034] The smoothed edge region is image-merged with the original target segmentation result to obtain a final smoothed target segmentation result.

[0035] Furthermore, in the femoral head recognition module, the spherical center position is calculated as follows:

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

[0037] Take slice data from the positive direction of the z-axis toward the origin, sum the pixel values ​​in the slice data, and when encountering the first slice data whose pixel value sum is not 0, the average value of the x-axis coordinate values ​​of the pixel points in the slice data that are not 0 is the x-coordinate of the center of the sphere, recorded as x, and the average value of the y-axis coordinate values ​​of the pixel points in the slice data that are not 0 is the y-coordinate of the center of the sphere, recorded as y, and the z-axis coordinate of the slice data at this time is marked as z1;

[0038] Take slice data from the positive direction of the x-axis toward the origin, sum the pixel values ​​in the slice data, and when the first slice data whose sum of the pixel values ​​is not 0 is encountered, the average z-axis coordinate values ​​of the pixel points in the slice data that are not 0 is the z coordinate of the center position of the sphere, denoted as z, and the x-axis coordinate of the slice data at this time is marked as x1.

[0039] Furthermore, in the image segmentation module, the maximum radius is calculated as follows:

[0040] Get the maximum value of z1-z and x1-x, where the 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 comprises:

[0042] S1: reading an acetabulum-femur image that needs to be segmented and the femoral head identified, wherein the acetabulum-femur image is an image including acetabulum and femoral tissues acquired by a medical imaging device before the image-guided hip arthroscopy minimally invasive surgery;

[0043] S2: using a region growing algorithm to segment the acetabulum and femur image according to a range of pixel values ​​of the pixel points, and the region enclosed by the pixel points within the range of the pixel values ​​is used to obtain an acetabulum position segmentation map or a femur position segmentation map;

[0044] S3: Based on the femoral position segmentation map, a femoral recognition algorithm is used to identify the femoral head, and the center position and maximum radius of the femoral head are calculated.

[0045] A computer-readable storage medium stores computer codes. When the computer codes are executed, the above method is executed.

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

[0047] (1) A system for segmenting the acetabulum and femur and identifying the femoral head is provided, comprising a memory for storing an acetabulum and femur image that needs to be segmented and the femoral head identified, as well as a segmented acetabulum position segmentation map, a femoral position segmentation map, and a calculated spherical center position and maximum radius of the femoral head; an image acquisition device for acquiring the acetabulum and femur image including the acetabulum and femoral tissues before image-guided arthroscopic minimally invasive hip surgery; a processor for segmenting the acetabulum and femur of the acetabulum and identifying the femoral head during the image-guided arthroscopic minimally invasive hip surgery, so as to use the image for navigation in the subsequent image-guided arthroscopic minimally invasive hip surgery, and to identify the femoral head during the image-guided arthroscopic minimally invasive hip surgery. The following modules are used to segment the acetabulum and femur and identify the femoral head: an image reading module is used to read the acetabulum and femur image that needs to be segmented and the femoral head is identified, wherein the acetabulum and femur image is an image including acetabulum and femoral tissues acquired by an image acquisition device before the image-guided hip arthroscopy minimally invasive surgery; an image segmentation module is used to segment the acetabulum and femur image according to the range of pixel values ​​of the pixel points using a region growing algorithm, and the area surrounded by the pixel points within the range of the pixel value is the acetabulum position segmentation map or the femoral position segmentation map; a femoral head identification module is used to identify the femoral head based on the femoral position segmentation map using a femoral identification algorithm, and calculate the center position and maximum radius of the femoral head. The above technical solution is a simple process for segmenting the acetabulum and femur and identifying the femoral head, which can realize the rapid segmentation of the acetabulum and femur and the rapid positioning of the femoral 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 difference in pixel values ​​between the non-target area and the target area is not obvious, the gradient of the acetabulum-femur image is calculated, a gradient image of the acetabulum-femur image is obtained, and the gradient image is superimposed on the original acetabulum-femur image, wherein 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 the target area and the non-target area, for actual lesion images with uneven bone density distribution and images with 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 An overall algorithm diagram executed by a processor in the system for segmenting the acetabulum and femoral bone and identifying the femoral head of the present invention;

[0050] Figure 2 This is a flow chart of the gradient calculation algorithm of the present invention;

[0051] Figure 3 It is a schematic diagram of the gradient image of the present invention;

[0052] Figure 4 It is a flow chart of the region growth algorithm of the present invention;

[0053] Figure 5 It is the femur position segmentation diagram of the present invention;

[0054] Figure 6 It is the acetabulum position segmentation diagram of the present invention;

[0055] Figure 7 7a and 7b are flowcharts and schematic diagrams for calculating the x and y coordinates of the sphere center, and 7c and 7d are flowcharts and schematic diagrams for calculating the z coordinates of the sphere center;

[0056] Figure 8 The result diagram of the center and radius of the femoral head of the present invention;

[0057] Fig. 9 The figure is an overall flow chart of the method for segmenting the acetabulum and femur and identifying the femoral head according to the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the 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 groups thereof.

[0060] First embodiment

[0061] This embodiment provides a system for segmenting the acetabulum and femur and identifying the femoral head. After reading the acetabulum and femur image, you can customize whether to calculate the image gradient and whether to superimpose the gradient image on the original image; apply the region growing algorithm to the read acetabulum and femur image, and let the user manually input the seed point to segment the acetabulum and femur. 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, which 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, the femoral position segmentation map, and the calculated spherical center position and maximum radius of the femoral head;

[0063] An image acquisition device, which is used to acquire the acetabulum-femur image including the acetabulum and femur tissues before image-guided minimally invasive hip arthroscopy surgery;

[0064] The processor is used to segment the acetabulum and femur of the acetabulum and femur images showing the diseased bone tissue obtained before the operation, and to identify the femoral head, so as to use it for navigation in the subsequent image-guided hip arthroscopy minimally invasive surgery, and adopts the following modules as follows: Figure 1 The workflow shown is to segment the acetabulum and identify the femoral head:

[0065] An image reading module is used to read the acetabulum-femur image that requires acetabulum-femur segmentation and femoral head identification, wherein the acetabulum-femur image is an image including acetabulum and femoral tissues acquired by an image acquisition device before the image-guided hip arthroscopy minimally invasive surgery.

[0066] Specifically, it is first necessary to read the acetabulum-femur image of the lesion tissue used for image-guided hip arthroscopy minimally invasive surgery. The acetabulum-femur image can be a three-dimensional CT image, or it can be any image commonly used in medicine, such as a two-dimensional X-ray image. The workflow of the present invention is applicable to any image commonly used in medicine.

[0067] The image segmentation module is used to segment the acetabulum femur image according to the range of pixel values ​​of the pixel points by using a region growing algorithm, and the area surrounded by the pixel points within the range of the pixel value is the acetabulum position segmentation map or the femur position segmentation map.

[0068] Specifically, Figure 2 As shown, the processor also includes a gradient image calculation module, which is used to distinguish the edge of the femur, the edge of the acetabulum and the non-target area, taking into account that when the gap between the femur and the acetabulum in some of the acetabulum femoral images read is narrow, or the difference in pixel values ​​between the non-target area and the target area is not obvious, before using the image segmentation module to segment the acetabulum and femur, a gradient algorithm is defined, and the user can choose whether to enable the gradient algorithm according to the actual situation of the acetabulum femoral image. The gradient algorithm is to calculate the gradient of the acetabulum femoral image, obtain the gradient image of the acetabulum femoral image, and superimpose the gradient image on the original acetabulum femoral image. The gradient algorithm specifically includes:

[0069] The gradient image is acquired by using a Gaussian function for image filtering and edge detection. A Gaussian function parameter σ is selected according to the data of the acetabulum femoral image, wherein the Gaussian function parameter σ is selected according to the data of the acetabulum femoral image including the image noise level, image resolution, image contrast and brightness, and the size of the target area. 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 acetabulum femur image. Discretize the first-order gradient function to obtain a first-order gradient operator, use the first-order gradient operator to perform convolution with the acetabulum femur image, calculate the gradient size of each pixel point respectively, and obtain the gradient image representing the image gradient size. The Gaussian function parameter σ is selected by the user according to the actual situation of the acetabulum femur image, such as Figure 3 As shown, it is the gradient map of the acetabulum femur image when σ=5.

[0071] The principle of using Gaussian function to obtain gradient image is: the Gaussian function used in the present invention is a commonly used technology in image filtering and edge detection. Gaussian filtering is a typical low-pass filtering, which 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 definitions of the one-dimensional and two-dimensional Gaussian function and the formulas of the first-order and second-order derivatives are sorted out one by one below.

[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 a two-dimensional Gaussian function is:

[0079]

[0080] In image processing, the first-order and second-order gradients of a two-dimensional Gaussian function are defined as:

[0081]

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

[0083]

[0084] By discretizing the gradient function, we can get the first-order and second-order gradient operators. By using these operators to convolve with the image, we can obtain the first-order, second-order gradients and gradients in various directions of the image.

[0085] like Figure 4 As shown, after determining whether to use the gradient algorithm to process the image, the region growing algorithm is formally used to segment the acetabulum and femur images 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 clicked seed points are on the target area, and the n+1th clicked seed point is on the non-target area.

[0087] The upper threshold and lower threshold for segmenting the acetabulum femur image are calculated by the pixel values ​​of the clicked n+1 seed points, specifically:

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

[0089]

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

[0091] The second preset value is subtracted from the average pixel value of the first n seed points as the lower preset value. In this embodiment, the second preset value is 350 as an example, that is, the lower preset value is mid_val-350, and the lower preset value is subtracted from the pixel value of the n+1th seed point (black_val=input n ) is compared, and the larger value between the lower limit preset value and the pixel value of the n+1th seed point is taken as the lower limit threshold, that is, the lower limit threshold is lower_thresh=max(mid_val-350,black_val).

[0092] Starting from the seed point, with the upper threshold and the lower threshold as boundaries, a breadth-first search is performed on the acetabulum femur image. Breadth-first search is an algorithm that traverses a graph storage structure, accessing vertices in the graph to ensure that each vertex is only accessed once. For the current pixel point, each vertex in the acetabulum femur image is traversed one by one from six directions: top, bottom, left, right, front, and back. All pixels that meet the conditions are set to 1, and those that do not meet the conditions are set to 0. When the iteration stops, all the pixel points that meet the upper threshold and the lower threshold are obtained as the target segmentation result. The image corresponding to the target segmentation result is the acetabulum position segmentation map or the femur position segmentation map. Figure 5 The figure shows the segmentation diagram of the femur position. Figure 6 The above is a segmentation diagram of the acetabulum position. Since the femur and the acetabulum have an obvious gap in the figure or after gradient processing, the femur and the acetabulum can be easily segmented.

[0093] Furthermore, the image segmentation module further includes: performing edge smoothing on the target segmentation result, specifically:

[0094] Obtaining the edge area of ​​the target segmentation result by edge detection algorithms including Sobel and Canny;

[0095] Performing a dilation operation on the acquired edge region so that the edge region is expanded by a preset number of pixels, thereby ensuring that a subsequent smoothing operation does not lose edge information of the target segmentation result;

[0096] Applying smoothing filters including Gaussian filtering and bilateral filtering to the expanded edge region to reduce noise and discontinuity of the edge and make the edge smooth;

[0097] Performing an erosion operation on the smoothed edge region to restore the edge region to its original size, retaining the main information of the edge, and removing unnecessary pixels introduced in the smoothing process;

[0098] The smoothed edge region is image-merged with the original target segmentation result to obtain a final smoothed target segmentation result.

[0099] Femoral head recognition module, used for Figure 7 The femoral head is identified by using a femoral recognition algorithm based on the femoral position segmentation map, and the spherical center position and maximum radius of the femoral head are calculated, specifically:

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

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

[0102] like Figure 7 As shown in a and 7b, slice data is taken from the positive direction of the z-axis toward the origin, and the pixel values ​​in the slice data are summed. When the first slice data whose sum of the pixel values ​​is not 0 is encountered, the average value of the x-axis coordinate values ​​of the pixel points in the slice data that are not 0 is the x-coordinate of the center position of the sphere, recorded as x, and the average value of the y-axis coordinate values ​​of the pixel points in the slice data that are not 0 is the y-coordinate of the center position of the sphere, recorded as y. At the same time, the z-axis coordinate of the slice data at this time is marked as z1.

[0103] like Figure 7 As shown in c and 7d, slice data is taken from the positive direction of the x-axis toward the origin, and the pixel values ​​in the slice data are summed. When the first slice data whose sum of the pixel values ​​is not 0 is encountered, the average z-axis coordinate values ​​of the pixel points in the slice data that are not 0 are the z coordinates of the center position of the sphere, denoted as z, and the x-axis coordinate of the slice data at this time is marked as x1.

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

[0105] The maximum value of z1-z and x1-x is obtained, and the maximum value is the maximum radius, that is, r=max(z1-z, x1-x). Figure 8 This is a cross-sectional diagram drawn based on the calculated center and radius of the femoral head.

[0106] Second embodiment

[0107] like Fig. 9 As shown, this embodiment provides a method for segmenting the acetabulum and femur and identifying the femoral head, which is performed by the system for segmenting the acetabulum and femur and identifying the femoral head as in the first embodiment, comprising:

[0108] S1: reading an acetabulum-femur image that needs to be segmented and the femoral head identified, wherein the acetabulum-femur image is an image including acetabulum and femoral tissues acquired by a medical imaging device before the image-guided hip arthroscopy minimally invasive surgery;

[0109] S2: using a region growing algorithm to segment the acetabulum and femur image according to a range of pixel values ​​of the pixel points, and the region enclosed by the pixel points within the range of the pixel values ​​is used to obtain an acetabulum position segmentation map or a femur position segmentation map;

[0110] S3: Based on the femoral position segmentation map, a femoral recognition algorithm is used to identify the femoral head, and the center position and maximum radius of the femoral head are calculated.

[0111] A computer-readable storage medium stores a computer code. When the computer code is executed, the above method is executed. A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium. The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0112] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

[0113] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] It should be noted that the above embodiments can be freely combined as needed. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention.

Claims

1. A system for segmenting the acetabulum and femoral bone and identifying the femoral head, characterized in that: include: A memory, which 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, the femoral position segmentation map, and the calculated spherical center position and maximum radius of the femoral head; An image acquisition device, which is used to acquire the acetabulum-femur image including the acetabulum and femur tissues before image-guided minimally invasive hip arthroscopy surgery; A processor is used to segment the acetabulum and femur of the acetabulum and femur image showing the diseased bone tissue obtained before the operation, and to identify the femoral head in the image-guided minimally invasive hip arthroscopy surgery, so as to be used for navigation in the subsequent image-guided minimally invasive hip arthroscopy surgery, and the acetabulum and femur are segmented and the femoral head is identified through the following modules: An image reading module, used for reading the acetabulum-femur image that needs to be segmented and the femoral head identified, wherein the acetabulum-femur image is an image including acetabulum and femoral tissues acquired by an image acquisition device before the image-guided hip arthroscopy minimally invasive surgery; An image segmentation module is used for segmenting the acetabulum femur image according to the range of pixel values ​​of the pixel points by using a region growing algorithm, wherein the region surrounded by the pixel points within the range of the pixel values ​​is the acetabulum position segmentation map or the femur position segmentation map; The femoral head recognition module is used to identify the femoral head based on the femoral position segmentation map using a femoral recognition algorithm, and calculate the center position and maximum radius of the femoral head.

2. The system for segmenting the acetabulum and femoral head and identifying the femoral head according to claim 1, characterized in that: The processor also includes a gradient image calculation module; The gradient image calculation module is used to calculate the gradient of the acetabulum-femur image before the image segmentation module is used to segment the acetabulum-femur, when the gap between the femur and the acetabulum in the read acetabulum-femur image is narrow, or the difference in pixel values ​​between the non-target area and the target area is not obvious, to obtain the gradient image of the acetabulum-femur image, and superimpose the gradient image on the original acetabulum-femur image, wherein 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.

3. The system for segmenting the acetabulum and femoral head and identifying the femoral head according to claim 2, characterized in that: In the gradient image calculation module, the gradient of the acetabulum-femur image is calculated, the gradient image of the acetabulum-femur image is obtained, and the gradient image is superimposed on the original acetabulum-femur image, specifically: Acquiring the gradient image using a Gaussian function for image filtering and edge detection; Selecting a Gaussian function parameter σ, wherein the Gaussian function parameter σ is selected based on data conditions of the acetabulum femoral image including image noise level, image resolution, image contrast and brightness, and the size of the target area, wherein 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; Substituting 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 acetabulum femur image; The first-order gradient function is discretized to obtain a first-order gradient operator, and the first-order gradient operator is used to perform convolution with the acetabulum femur image, and the gradient size of each pixel point is calculated respectively to obtain the gradient image representing the image gradient size.

4. The system for segmenting the acetabulum and femoral head and identifying the femoral head according to claim 2, characterized in that: In the image segmentation module, the region growing algorithm is used to segment the acetabulum femur image according to the range of pixel values ​​of the pixel points, and the area surrounded by the pixel points within the range of the pixel value is the acetabulum position segmentation map or the femur position segmentation map, specifically: Click n+1 pixel points on the acetabulum femur image as seed points, wherein the first n seed points clicked are on the target area, and the n+1th seed point is on the non-target area; The upper threshold and the lower threshold for segmenting the acetabulum femur image are calculated by the pixel values ​​of the clicked n+1 seed points; Starting from the seed point, with the upper threshold and the lower threshold as boundaries, a breadth-first search is performed on the acetabulum femur image to obtain a target segmentation result, wherein the breadth-first search is an algorithm that traverses the image storage structure, traversing each vertex in the acetabulum femur image one by one from six directions: top, bottom, left, right, front, and back, to obtain all the pixel points that meet the upper threshold and the lower threshold as the target segmentation result, and the image corresponding to the target segmentation result is the acetabulum position segmentation map or the femur position segmentation map.

5. The system for segmenting the acetabulum and femoral bone and identifying the femoral head according to claim 4, characterized in that: In the image segmentation module, the upper threshold and the lower threshold for segmenting the acetabulum femur image are calculated by the pixel values ​​of the clicked n+1 seed points, specifically: Calculate the mean pixel value of the first n seed points; Adding a first preset value to the mean of the pixel values ​​of the first n seed points is used as the upper threshold; The mean of the pixel values ​​of the first n seed points minus the second preset value is used as the lower bound preset value, the lower bound preset value is compared with the pixel value of the n+1th seed point, and the larger value between the lower bound preset value and the pixel value of the n+1th seed point is taken as the lower bound threshold.

6. The system for segmenting the acetabulum and femoral bone and identifying the femoral head according to claim 4, characterized in that: The image segmentation module further includes: smoothing the edges of the target segmentation result, specifically: Obtaining the edge area of ​​the target segmentation result by using edge detection algorithms including Sobel and Canny; Performing a dilation operation on the acquired edge region so that the edge region is expanded by a preset number of pixels, thereby ensuring that a subsequent smoothing operation does not lose edge information of the target segmentation result; Applying smoothing filters including Gaussian filtering and bilateral filtering to the expanded edge region to reduce noise and discontinuity of the edge and make the edge smooth; Performing an erosion operation on the smoothed edge region to restore the edge region to its original size, retaining the main information of the edge, and removing unnecessary pixels introduced in the smoothing process; The smoothed edge region is image-merged with the original target segmentation result to obtain a final smoothed target segmentation result.

7. The system for segmenting the acetabulum and femoral head and identifying the femoral head according to claim 4, characterized in that: In the femoral head recognition module, the center position of the ball is calculated as follows: In the image segmentation module, the pixel values ​​of the pixel points in the segmented femur position segmentation map are marked with 1 and 0, where 1 represents the femur and 0 represents the non-target area; Take slice data from the positive direction of the z-axis toward the origin, sum the pixel values ​​in the slice data, and when encountering the first slice data whose pixel value sum is not 0, the average value of the x-axis coordinate values ​​of the pixel points in the slice data that are not 0 is the x-coordinate of the center of the sphere, recorded as x, and the average value of the y-axis coordinate values ​​of the pixel points in the slice data that are not 0 is the y-coordinate of the center of the sphere, recorded as y, and the z-axis coordinate of the slice data at this time is marked as z1; Take slice data from the positive direction of the x-axis toward the origin, sum the pixel values ​​in the slice data, and when the first slice data whose sum of the pixel values ​​is not 0 is encountered, the average z-axis coordinate values ​​of the pixel points in the slice data that are not 0 is the z coordinate of the center position of the sphere, denoted as z, and the x-axis coordinate of the slice data at this time is marked as x1.

8. The system for segmenting the acetabulum and femoral bone and identifying the femoral head according to claim 7, characterized in that: In the image segmentation module, the maximum radius is calculated as follows: Get the maximum value of z1-z and x1-x, where the maximum value is the maximum radius.

9. A method for segmenting the acetabulum and femoral head and identifying the femoral head using the system for segmenting the acetabulum and femoral head and identifying the femoral head as claimed in any one of claims 1 to 8, characterized in that: include: S1: reading an acetabulum-femur image that needs to be segmented and the femoral head identified, wherein the acetabulum-femur image is an image including acetabulum and femoral tissues acquired by a medical imaging device before the image-guided hip arthroscopy minimally invasive surgery; S2: using a region growing algorithm to segment the acetabulum and femur image according to a range of pixel values ​​of the pixel points, and the region enclosed by the pixel points within the range of the pixel values ​​is used to obtain an acetabulum position segmentation map or a femur position segmentation map; S3: Based on the femoral position segmentation map, a femoral recognition algorithm is used to identify the femoral head, and the center position and maximum radius of the femoral head are calculated.

10. A computer-readable storage medium storing a computer code, wherein when the computer code is executed, the method as claimed in claim 9 is executed.

Citation Information

Patent Citations

  • Acquisition method for anatomical parameters of femur and acetabulum based on CT three-dimensional sequence image

    CN107274389A

  • Femoral head CT image segmentation method

    CN110349168A

  • Femur outer side wall morphological parameter three-dimensional measurement method based on CT three-dimensional reconstruction image

    CN113069135A

  • Lower limb skeleton model construction method and device, electronic equipment and storage medium

    CN114066885A

  • Acetabulum radius automatic measurement method and system based on artificial intelligence

    CN114494183A

Cited By

  • System and method for acetabulum and femur segmentation and femoral head identification

    WO2026016554A1