High-precision Segmentation Method and System for Lower Limb Fracture Images Based on Artificial Intelligence

Abstract

The present invention relates to the field of image processing technology, and particularly to a high-precision segmentation method and system for lower limb fracture images based on artificial intelligence, including: obtaining a number of initial extended bone lines within the leg connected domain; obtaining the texture degree of each initial extended bone line according to the distance between each initial extended bone line and the comparison edge, screening out a number of initial extended bone lines, and obtaining the bone connected domain in the leg connected domain; obtaining the growth coefficient between the central pixel point and each to-be-grown pixel point in the corresponding eight-neighborhood according to the difference between the gradient difference of the central pixel point and the gradient difference of the to-be-grown pixel point; and performing growth to obtain a number of growth lines; obtaining all the bone fracture lines according to the unevenness, included angle of each growth line, and the minimum distance from the edge line of the bone connected domain, and assisting doctors in observation and treatment through all the bone fracture lines. The present invention improves the accuracy of high-precision segmentation of lower limb fractures.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a high-precision segmentation method and system for lower limb fracture images based on artificial intelligence. Background Art

[0002] High-precision segmentation of lower limb fracture images is a crucial task in medical image analysis, particularly for fracture diagnosis and treatment planning. The goal is to accurately segment the fracture area from image data to help doctors determine fracture type, severity, and treatment options.

[0003] In order to perform high-precision segmentation of the patient's lower limb fracture, the patient's lower limb X-ray image is collected for fracture identification. However, due to the incomplete uniformity of tissues in different parts of the lower limb during the lower limb X-ray image acquisition process, the contrast of different parts in the image is different, which makes it impossible to clearly display the bones of some patients, thereby affecting the identification of the fracture site and reducing the accuracy of high-precision segmentation of lower limb fractures. Summary of the Invention

[0004] The present invention provides a high-precision segmentation method and system for lower limb fracture images based on artificial intelligence to solve existing problems.

[0005] The present invention's artificial intelligence-based high-precision segmentation method and system for lower limb fracture images adopts the following technical solutions:

[0006] One embodiment of the present invention provides a high-precision segmentation method for lower limb fracture images based on artificial intelligence, the method comprising the following steps:

[0007] Obtain images of the patient's lower limb fractures;

[0008] The lower limb fracture image is segmented to obtain the leg connected domain; adjacent pixels with similar gradient differences in the leg connected domain are connected to obtain several initial bone lines; all initial bone lines are extended to obtain several initial extended bone lines, and several initial extended bone lines are initially screened based on the number of intersections after extension;

[0009] The texture of each initial extended bone line is obtained based on the distance between each initial extended bone line and the comparison edge corresponding to the leg connected domain after the initial screening; and several initial extended bone lines are screened again based on the average of the textures of each initial extended bone line and the similar initial extended bone lines;

[0010] The endpoints of each initially extended bone line after rescreening are used as initial seed points, and growth is performed based on the gradient difference between adjacent pixels to obtain the bone connected domain in the leg connected domain;

[0011] Obtain the in-bone pixels and out-of-bone pixels in the eight-neighborhood of the edge pixels of the bone connected region. Through the in-bone pixels and out-of-bone pixels in the eight-neighborhood of the edge pixels of the bone connected region, obtain the in-bone edge points and out-of-bone edge points; determine the break points based on the number of in-bone edge points and out-of-bone edge points in the eight-neighborhood of the edge pixels of the bone connected region, and use the break points as seed points; denote the in-bone pixels in the eight-neighborhood of each central pixel as the to-be-grown pixels of each central pixel, and obtain the growth coefficient between the central pixel and each to-be-grown pixel in the corresponding eight-neighborhood according to the difference between the gradient difference of the central pixel and the gradient difference of the to-be-grown pixel; grow through the seed points and the growth coefficient to obtain several growth lines;

[0012] Obtain the bone fracture coefficient of each growth line according to the unevenness, included angle and the minimum distance from the edge line of the bone connected region of each growth line, obtain all the bone fracture lines through the bone fracture coefficient, and assist doctors in observation and treatment through all the bone fracture lines.

[0013] Further, the segmentation of the lower limb fracture image to obtain the leg connected region includes the following specific steps:

[0014] Segment the lower limb fracture image through the semantic segmentation algorithm in the neural network to obtain the leg connected region.

[0015] Further, the connection of adjacent pixel points with similar gradient differences in the leg connected region to obtain several initial bone lines includes the following specific steps:

[0016] Obtain the gradient values of all pixel points inside the leg connected region of the patient through the canny edge detection algorithm, obtain the eight-neighborhood pixel points of each pixel point in the leg connected region, denote the pixel point with the largest gradient value among the eight-neighborhood pixel points as the first pixel point of each pixel point, and denote the pixel point in the eight-neighborhood with the closest gradient value to the central pixel point as the second pixel point of each pixel point; when the first pixel point and the second pixel point are the same pixel point, then denote the pixel point in the eight-neighborhood as the third pixel point;

[0017] Connect all adjacent third pixel points to obtain several initial bone lines.

[0018] Further, the extension of all the initial bone lines to obtain several initial extended bone lines and the initial screening of several initial extended bone lines according to the number of intersections after extension include the following specific steps:

[0019] Obtain the tangent directions of the endpoints at both ends of each initial bone line. Along the tangent directions of the two endpoints, extend each initial bone line by half on each side to obtain the extended initial bone line, and denote the extended initial bone line as the initial extended bone line; obtain the number of initial extended bone lines that each initial extended bone line intersects with all other initial extended bone lines, and denote it as the intersection number of each initial extended bone line; perform linear normalization on the intersection numbers of all initial extended bone lines, and screen out the initial extended bone lines whose normalized intersection numbers are greater than or equal to the first preset threshold and screen out the initial extended bone lines whose normalized intersection numbers are less than the first preset threshold to retain the initial extended bone lines, and obtain several initial extended bone lines after the first screening.

[0020] Furthermore, obtain the texture degree of each initial extended bone line according to the distance between each initial extended bone line after the first screening and the comparison edge corresponding to the connected region of the leg; screen out several initial extended bone lines again through the mean value of the texture degrees of each initial extended bone line and the similar initial extended bone lines, and the specific steps are as follows:

[0021] Obtain the points closest to the edge line of the leg connected region at both ends of each initial extended bone line, and denote them as reference points. Connect the two reference points with a line, and denote the line as the comparison edge of each initial extended bone line;

[0022] The calculation formula for the texture degree of each initial extended bone line is:

[0023] ;

[0024] In the formula, represents the information entropy of the minimum distance between all initial extended bone lines and the corresponding comparison edges, represents the th initial extended bone line and the corresponding comparison edge between the distance, represents the exponential function with the natural constant as the base, represents the th initial extended bone line's texture degree;

[0025] Obtain the tangent directions of the two endpoints of each initial extended bone line. Along the tangent directions, obtain the two initial extended bone lines closest to the two endpoints, and denote them as the collinear bone lines of each initial extended bone line; calculate the mean value of the texture degrees of each initial extended bone line and the collinear bone lines, and denote it as the texture mean value of each initial extended bone line. Screen out the initial extended bone lines whose texture mean values are greater than or equal to the second preset threshold and screen out the initial extended bone lines whose texture mean values are less than the second preset threshold The initial extended bone lines are retained, and several initial extended bone lines are obtained after re-screening.

[0026] Furthermore, taking the endpoints of each initial extended bone line after re-screening as initial seed points, growth is carried out according to the gradient difference between adjacent pixel points to obtain the bone connected domain in the leg connected domain. The specific steps are as follows:

[0027] Obtain the eight-neighborhood of each endpoint on each initial extended bone line. Denote any pixel point in the eight-neighborhood of each endpoint as a reference pixel point. Connect each endpoint to the reference pixel point to obtain a straight line between each endpoint and the reference point. Denote the direction perpendicular to the direction of the straight line as the perpendicular direction of the reference point. Obtain the pixel points adjacent to the reference point on both sides in the corresponding perpendicular direction, denoted as the two gradient points of the reference point. Calculate the absolute value of the difference between the two gradient points, denoted as the gradient difference of the reference point. Obtain the pixel points adjacent to the endpoint on both sides in the corresponding perpendicular direction, denoted as the two gradient points of the endpoint. Calculate the absolute value of the difference between the gray values of the two gradient points, denoted as the gradient difference of the endpoint. Denote the difference between the gradient difference of the reference point and the gradient difference of the endpoint as the gradient difference between each endpoint and the reference point.

[0028] Taking all endpoints on the initial extended bone line as initial seed points, growth is carried out according to the principle of minimizing the gradient difference between each endpoint and all pixel points in the eight-neighborhood. Denote the grown area as the bone connected domain in the leg connected domain.

[0029] Furthermore, obtaining the in-bone pixel points and out-of-bone pixel points in the eight-neighborhood of the edge pixel points of the bone connected domain, and obtaining the in-bone edge points and out-of-bone edge points through the in-bone pixel points and out-of-bone pixel points in the eight-neighborhood of the edge pixel points of the bone connected domain. Determining the break points through the number of in-bone edge points and out-of-bone edge points in the eight-neighborhood of the edge pixel points of the bone connected domain. The specific steps are as follows:

[0030] Denote the pixel points in the eight-neighborhood of the edge pixel points within the bone connected domain as in-bone pixel points, and denote the pixel points in the eight-neighborhood of the edge pixel points outside the bone connected domain as out-of-bone pixel points.

[0031] Calculate the mean value of the gray values of all in-bone pixel points in the eight-neighborhood of each edge pixel point of the bone connected domain, denoted as the in-bone gray mean of each edge pixel point of the bone connected domain. Calculate the mean value of the gray values of all out-of-bone pixel points in the eight-neighborhood of each edge pixel point of the bone connected domain, denoted as the out-of-bone gray mean of each edge pixel point of the bone connected domain.

[0032] Compare the difference in grayscale values between each edge pixel of the bone connected component and the average grayscale value inside the bone and the average grayscale value outside the bone. When the difference between the grayscale value of each edge pixel of the bone connected component and the average grayscale value inside the bone is less than or equal to the difference between the grayscale value of the edge pixel and the average grayscale value outside the bone, mark the edge pixel of the bone connected component as an inner bone edge point; otherwise, mark the edge pixel of the bone connected component as an outer bone edge point;

[0033] Mark any edge pixel of the bone connected component that contains an inner bone edge point and an outer bone edge point in the eight-neighborhood of any pixel point as a break point.

[0034] Further, obtain the growth coefficient between the central pixel point and each growing pixel point in the corresponding eight-neighborhood according to the difference between the gradient difference of the central pixel point and the gradient difference of the growing pixel point; grow through the seed point and the growth coefficient to obtain several growth lines, including the following specific steps:

[0035] The growth coefficient between the central pixel point and the th growing pixel point in the corresponding eight-neighborhood is represented by the formula:

[0036] ;

[0037] In the formula, represents the gradient difference of the central pixel point during the growth process, represents the gradient difference of the th growing pixel point in the eight-neighborhood of the central point, is the absolute value symbol, represents the exponential function with the natural constant as the base, represents the growth coefficient between the central pixel point and the th growing pixel point in the corresponding eight-neighborhood;

[0038] Grow according to the seed point and the growth coefficient between two pixel points, and grow the pixel points whose growth coefficient is greater than or equal to the third preset threshold until the growth ends to obtain several growth lines.

[0039] Further, obtain the bone fracture coefficient of each growth line according to the unevenness, included angle of each growth line, and the minimum distance from the growth line to the edge line of the bone connected component. Obtain all the bone fracture lines through the bone fracture coefficient, and assist the doctor in observation and treatment through all the bone fracture lines, including the following specific steps:

[0040] Obtain the edge chain code of the growth line, and record the average value of the differences between adjacent code numbers in the edge chain code of each growth line as the unevenness of each growth line;

[0041] Obtain the midpoint of each growth line, obtain the included angle between the two endpoints and the midpoint line, and record it as the included angle of each growth line; obtain the minimum distance between the farthest point from the bone connected domain edge line on each growth line and the bone connected domain edge line, and record it as the minimum distance between each growth line and the bone connected domain edge line;

[0042] The bone fracture coefficient of each growth line is expressed by the formula:

[0043] ;

[0044] In the formula, represents the unevenness of the th growth line, represents the included angle of the th growth line, represents the minimum distance between the th growth line and the bone connected domain edge line; represents the linear normalization function, represents the th growth line of the bone fracture coefficient;

[0045] Record the growth lines with the bone fracture coefficient greater than the fourth preset threshold as bone fracture lines, mark the bone fracture lines in the lower limb fracture image, and assist the doctor to observe and treat the patient's lower limb fracture situation through the marked bone fracture line results.

[0046] The present invention also provides a high-precision segmentation system for lower limb fracture images based on artificial intelligence, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned high-precision segmentation methods for lower limb fracture images based on artificial intelligence are implemented.

[0047] The beneficial effects of the technical solution of the present invention are: obtain several initial extended bone lines in the leg connected domain; obtain the texture degree of each initial extended bone line according to the distance between each initial extended bone line and the comparison edge, screen out several initial extended bone lines through the texture degree, and obtain the bone connected domain in the leg connected domain; obtain the growth coefficient between the central pixel point and each growth pixel point in the corresponding eight-neighborhood according to the difference between the gradient difference of the central pixel point and the gradient difference of the to-be-grown pixel point; and perform growth to obtain several growth lines, reducing the influence of the incomplete uniformity of tissues in different parts of the lower limb on the contrast of different parts in the image; obtain all bone fracture lines according to the unevenness, included angle of each growth line and the minimum distance between the growth line and the bone connected domain edge line, and assist the doctor to observe and treat through all the bone fracture lines. The present invention improves the accuracy of high-precision segmentation of lower limb fractures. Brief Description of the Drawings

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0049] Figure 1 It is a flowchart of the steps of the high-precision segmentation method for lower limb fracture images based on artificial intelligence of the present invention. Detailed implementation manners

[0050] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, will describe in detail the specific implementation manners, structures, features and effects of the high-precision segmentation method and system for lower limb fracture images based on artificial intelligence proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0052] The following will specifically describe the specific solutions of the high-precision segmentation method and system for lower limb fracture images based on artificial intelligence provided by the present invention with reference to the accompanying drawings.

[0053] Please refer to Figure 1 , which shows a flowchart of the steps of the high-precision segmentation method for lower limb fracture images based on artificial intelligence provided by an embodiment of the present invention. The method includes the following steps:

[0054] Step S001: Collect lower limb fracture images of the patient.

[0055] It should be noted that since high-precision segmentation is performed on the lower limb fracture images of the patient, it is necessary to collect lower limb fracture images under X-ray for analysis.

[0056] Specifically, use X-ray to collect lower limb fracture images of the patient's leg, where the lower limb fracture image is a grayscale image.

[0057] Thus, the lower limb fracture image is obtained.

[0058] Step S002: Segment the lower limb fracture image to obtain the leg connected region; obtain several initial extended bone lines in the leg connected region; obtain the texture degree of each initial extended bone line according to the distance between each initial extended bone line and the corresponding comparison edge; screen out several initial extended bone lines again through the average value of the texture degrees of each initial extended bone line and its adjacent initial extended bone lines; use the endpoints of each initial extended bone line after the re-screening as the initial seed points, and perform growth according to the gradient difference between adjacent pixel points to obtain the bone connected region in the leg connected region.

[0059] It should be noted that since there is a large gray level difference between the patient's leg region and the background region outside the leg, the patient's leg region can be preliminarily screened out, and the specific information in the leg region is analyzed.

[0060] Specifically, the lower limb fracture image is segmented by the semantic segmentation algorithm in the neural network to obtain the leg connected region of the patient; among them, the loss function in the semantic segmentation algorithm is the cross-entropy loss function. Among them, the semantic segmentation algorithm is a well-known technology and will not be specifically described here.

[0061] So far, the leg connected region of the patient is obtained.

[0062] It should be noted that since the patient's leg connected region contains the patient's body tissues and bone parts, due to the penetrability of different parts of the body tissues, some bones are more obvious in the connected region, while the contrast between some bone parts and the body tissues is relatively low, resulting in the bones not being well distinguished; this may cause tissue pixel points to be regarded as bone pixel points when obtaining bone pixel points through the edge detection algorithm, so the lines detected by the edge are preliminarily screened.

[0063] Furthermore, it should be noted that when segmenting bone pixel points, the gradient of their pixel points is relatively large. Therefore, when analyzing that the pixel point with the closest and largest gradient value to the corresponding pixel points in the eight-neighborhood of each pixel point is the same pixel point, the greater the possibility that the pixel point is a bone pixel point.

[0064] Specifically, the gradient values of all pixel points inside the leg connected region of the patient are obtained through the canny edge detection algorithm, the eight-neighborhood pixel points of each pixel point in the leg connected region are obtained, the pixel point with the largest gradient value among the eight-neighborhood pixel points is recorded as the first pixel point of each pixel point, and the pixel point in the eight-neighborhood with the closest gradient value to the central pixel point is recorded as the second pixel point of each pixel point; when the first pixel point and the second pixel point are the same pixel point, the pixel points in the eight-neighborhood are recorded as the third pixel points. Among them, the canny edge detection algorithm is a well-known technology and will not be specifically described here.

[0065] Connect all adjacent third pixel points to obtain several initial bone lines.

[0066] It should be noted that since the lines of bones generally have regular texture changes, while other lines are relatively messy, it is possible to extend the initial bone lines and observe their intersection situations. When each bone line intersects with other bone lines more frequently, it indicates that the bone line is relatively messy and may be a line caused by tissue interference, so it needs to be excluded.

[0067] Specifically, obtain the tangent directions of the two end points of each initial bone line. Along the tangent directions of the two end points, extend each initial bone line by half on each side to obtain the extended initial bone line, and denote the extended initial bone line as the initial extended bone line. Obtain the number of initial extended bone lines that each initial extended bone line intersects with all other initial extended bone lines, and denote it as the intersection number of each initial extended bone line. Perform linear normalization on the intersection numbers of all initial extended bone lines, and screen out the initial extended bone lines whose normalized intersection numbers are greater than or equal to the first preset threshold Screen out and retain the initial extended bone lines whose normalized intersection numbers are less than the first preset threshold to obtain several initial extended bone lines after the first screening. Among them, in this embodiment, the first preset threshold is described by way of example, and in this embodiment is not specifically limited, and the implementer can determine it according to specific situations.

[0068] It should be noted that when the minimum distances between all initial extended bone lines and the edge line of the leg connection area are more consistent, and the distance between each initial extended bone line and the edge line of the leg connection area is smaller, it indicates that the texture degree of the initial extended bone line is higher.

[0069] Specifically, obtain the points on the leg connection area edge line that are closest to the two end points of each initial extended bone line, and denote them as reference points. Connect the lines of the two reference points, and denote them as the comparison edges of each initial extended bone line.

[0070] According to the distance between each initial extended bone line and the corresponding comparison edge, obtain the texture degree of each initial extended bone line, which is specifically expressed by the formula:

[0071] ;

[0072] In the formula, represents the information entropy of the minimum distances between all initial extended bone lines and the corresponding comparison edges, represents the th initial extended bone line and the corresponding comparison edge between the distance, represents the exponential function with the base of the natural constant, represents the texture degree of the th initial extended bone line. Among them, information entropy and

[0073] distance are both well-known technologies and will not be specifically elaborated here. Among them, when the minimum distances between all the initial extended bone lines and the edge line of the leg connection area are more consistent, that is, the information entropy of the minimum distances between all the initial extended bone lines and the corresponding comparison edges is smaller, it indicates that the texture degree of the initial extended bone lines is larger; when the

[0074] distance between each initial extended bone line and the edge line of the leg connection area is smaller, it indicates that the texture degree of this initial extended bone line is larger.

[0075] It should be noted that due to the stratification of the patient's tissue in the lower limb fracture image of the patient, the leg of the patient will show gray-scale stratification, resulting in an original initial extended bone line being divided into several initial extended bone lines. Therefore, the mean value of the texture degrees of adjacent initial extended bone lines of each initial extended bone line is obtained to determine whether this initial extended bone line needs to be screened out.

[0076] Furthermore, it should be noted that because the initial extended bone lines not affected by interference have relatively high texture degrees, it is necessary to exclude the initial extended bone lines with lower texture degrees caused by interference. Specifically, the tangent directions of the two endpoints of each initial extended bone line are obtained, and along the tangent directions, the two initial extended bone lines closest to the two endpoints are obtained and recorded as the collinear bone lines of each initial extended bone line; the mean value of the texture degrees of each initial extended bone line and its collinear bone lines is calculated and recorded as the texture mean value of each initial extended bone line. The initial extended bone lines with texture mean values greater than or equal to the second preset threshold are screened out, and the initial extended bone lines with texture mean values less than the second preset threshold are retained to obtain several initial extended bone lines after re-screening. Among them, in this embodiment, the second preset threshold is taken as an example for description and is not specifically limited in this embodiment. The implementer can determine according to the specific situation.

[0077] It should be noted that due to the different penetration degrees of different parts of the leg, the contrast of the image is uneven, resulting in incomplete initial extended bone lines. Therefore, it is necessary to grow complete bone edge lines and obtain the bone connection area.

[0078] Specifically, obtain the eight-neighborhood of each endpoint on each initial extended bone line. Denote any pixel point in the eight-neighborhood of each endpoint as a reference pixel point. Connect each endpoint to the reference pixel point to obtain a straight line between each endpoint and the reference point. Denote the direction perpendicular to the direction of the straight line as the perpendicular direction of the reference point. Obtain the pixel points adjacent to the reference point on both sides in the corresponding perpendicular direction, which are denoted as the two gradient points of the reference point. Calculate the absolute value of the difference between the two gradient points, which is denoted as the gradient difference of the reference point. Obtain the pixel points adjacent to the endpoint on both sides in the corresponding perpendicular direction, which are denoted as the two gradient points of the endpoint. Calculate the absolute value of the difference between the two gradient points, which is denoted as the gradient difference of the endpoint. Denote the difference between the gradient difference of the reference point and the gradient difference of the endpoint as the gradient difference between each endpoint and the reference point.

[0079] Through the above operations, obtain the gradient differences between each endpoint and all pixel points in all eight-neighborhoods. Use all endpoints on the initial extended bone line as initial seed points and grow according to the principle of minimizing the gradient differences between each endpoint and all pixel points in all eight-neighborhoods. Denote the grown region as the bone connected region in the leg connected region.

[0080] Thus far, the bone connected region in the leg connected region is obtained.

[0081] Step S003: Obtain the growth coefficient between the central pixel point and each to-be-grown pixel point in the corresponding eight-neighborhood according to the difference between the gradient difference of the central pixel point and the gradient difference of the to-be-grown pixel point; and perform growth to obtain several growth lines. Obtain the bone fracture coefficient of each growth line according to the unevenness, included angle of each growth line, and the minimum distance from the edge line of the bone connected region.

[0082] It should be noted that since the fracture part will have a lower bone density due to the appearance of cracks, resulting in less x-ray absorption in the fracture part and thus a decrease in the gray value in the fracture part, it is necessary to analyze the decrease in the gray value in the fracture edge.

[0083] Specifically, obtain the edge pixel points of the bone connected region. Denote the pixel points in the eight-neighborhood of the edge pixel points that are inside the bone connected region as the inner-bone pixel points, and denote the pixel points in the eight-neighborhood of the edge pixel points that are outside the bone connected region as the outer-bone pixel points.

[0084] Calculate the mean value of the gray values of all the in-bone pixels in the eight-neighborhood of each edge pixel of the bone connected component, and denote it as the in-bone gray mean of each edge pixel of the bone connected component; calculate the mean value of the gray values of all the out-of-bone pixels in the eight-neighborhood of each edge pixel of the bone connected component, and denote it as the out-of-bone gray mean of each edge pixel of the bone connected component. Compare the difference between the gray value of each edge pixel of the bone connected component and the in-bone gray mean and the out-of-bone gray mean. When the difference between the gray value of each edge pixel of the bone connected component and the in-bone gray mean is less than or equal to the difference between the gray value of the edge pixel and the out-of-bone gray mean, then mark the edge pixel of the bone connected component as an in-bone edge point; otherwise, mark the edge pixel of the bone connected component as an out-of-bone edge point.

[0085] Mark any edge pixel of the bone connected component that contains an in-bone edge point and an out-of-bone edge point in the eight-neighborhood of any pixel point as a break point.

[0086] Mark the in-bone pixels in the eight-neighborhood of each center pixel as the to-be-grown pixels of each center pixel.

[0087] Use the break point as the seed point for growth, and perform growth through the gradient difference between adjacent pixels; among them, the growth coefficient between the center pixel and each to-be-grown pixel in the corresponding eight-neighborhood is expressed by the formula:

[0088] ;

[0089] In the formula, represents the gradient difference of the center pixel during the growth process, represents the gradient difference of the th to-be-grown pixel in the eight-neighborhood of the center point, is the absolute value symbol, represents the exponential function with the natural constant as the base, represents the growth coefficient between the center pixel and the th to-be-grown pixel in the corresponding eight-neighborhood. Among them, the process of obtaining the gradient difference of the pixel is in step S002.

[0090] Among them, the smaller the difference between the gradient difference of the center point and the gradient difference of the to-be-grown pixel in the eight-neighborhood, the greater the possibility of growth between the two points; that is, the greater the growth coefficient between the corresponding two pixels.

[0091] Perform growth according to the seed point and the growth coefficient between two pixels, and grow the pixels whose growth coefficient is greater than or equal to the third preset threshold until the growth ends. Among them, the third preset threshold For example, in this embodiment No specific limitation is made, and the implementer can determine according to the specific situation.

[0092] Thus, several growth lines are obtained.

[0093] It should be noted that since there are cracks generated by fractures and cartilage edges on the bone in the growth lines, and the fracture is a brittle fracture, the pixels on the cracks generated by the fracture are smooth and relatively straight, while the cartilage is rough and runs through the entire bone plane due to reasons such as life, and the fracture edge when the fracture runs through the entire bone is sharper.

[0094] Specifically, the edge chain code of the growth line is obtained, and the mean value of the differences between adjacent code numbers in the edge chain code of each growth line is recorded as the unevenness of each growth line; among them, the edge chain code is a well-known technology and will not be specifically described here.

[0095] The midpoint on each growth line is obtained, and the angle between the two endpoints and the midpoint straight line is obtained and recorded as the angle of each growth line; the minimum distance between the farthest point from the bone connectivity domain edge line on each growth line and the bone connectivity domain edge line is obtained and recorded as the minimum distance between each growth line and the bone connectivity domain edge line.

[0096] According to the unevenness, angle and minimum distance of each growth line, the bone fracture coefficient of each growth line is obtained, and specifically expressed by the formula:

[0097] ;

[0098] In the formula, represents the unevenness of the th growth line, represents the )] [[ID=))] [[ID=))] [[ID=))] [[ID=))] [[ID=))] [[ID=))]

[0099] [[ID=))] [[ID=))]

[0100] ​​​​​​Thus, the bone fracture coefficient of each growth line is obtained.

[0101] Step S004: Obtain all the bone fracture lines based on the bone fracture coefficients of the growth lines to assist doctors in observation and treatment.

[0102] Growth lines with bone fracture coefficients greater than the fourth preset threshold are recorded as bone fracture lines. Among them, the fourth preset threshold is described by taking... as an example. In this embodiment is not specifically limited, and the implementer can determine it according to the specific situation.

[0103] Mark the bone fracture lines in the lower limb fracture image, and assist doctors in observing and treating the patient's lower limb fracture condition through the marked bone fracture line results.

[0104] It should be noted that the model used in this embodiment is only used to represent the negative correlation relationship and restrict the results of the model output to be within the interval. In specific implementation, it can be replaced with other models with the same purpose. This embodiment only takes the model as an example for description and does not specifically limit it. Among them refers to the input of the model.

[0105] This embodiment provides a high-precision segmentation system for lower limb fracture images based on artificial intelligence, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for high-precision segmentation of lower limb fracture images based on artificial intelligence in steps S001 to S004.

[0106] Thus, the present invention is completed.

[0107] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A high-precision segmentation method for lower limb fracture images based on artificial intelligence, characterized in that, The method includes the following steps: Obtain the lower limb fracture image of the patient; Segment the lower limb fracture image to obtain the leg connected region; Connect adjacent pixel points with similar gradient differences within the leg connected region to obtain several initial bone lines; Extend all the initial bone lines to obtain several initial extended bone lines, and initially screen out several initial extended bone lines according to the number of intersections after extension; Obtain the texture degree of each initial extended bone line according to the distance between each initial extended bone line after the initial screening and the comparison edge corresponding to the leg connected region; Screen out several initial extended bone lines again through the average value of the texture degrees of each initial extended bone line and the similar initial extended bone lines, including obtaining the points closest to the edge line of the leg connected region at both ends of each initial extended bone line, denoted as reference points, and connecting the two reference points to obtain the comparison edge of each initial extended bone line; The calculation formula for the texture degree of each initial extended bone line is: ； In the formula, the information entropy representing the minimum distance between all initial extended bone lines and corresponding comparison edges, represents the th initial extended bone line and the corresponding comparison edge distance, represents the exponential function with the natural constant as the base, represents the texture degree of the th initial extended bone line; Obtain the tangent directions of the two endpoints of each initial extended bone line, and along the tangent directions, obtain the two initial extended bone lines closest to the two endpoints, which are denoted as the collinear bone lines of each initial extended bone line; calculate the mean value of the texture degrees of each initial extended bone line and its collinear bone line, which is denoted as the texture mean value of each initial extended bone line, and only retain the initial extended bone lines whose texture mean value is less than the second preset threshold to obtain several initial extended bone lines after re-screening; Taking the endpoints of each initial extended bone line after the second screening as the initial seed points, grow according to the gradient difference between adjacent pixel points to obtain the bone connected region in the leg connected region; Obtain the inner bone pixel points and outer bone pixel points in the eight-neighborhood of the edge pixel points of the bone connected region, and obtain the inner bone edge points and outer bone edge points through the inner bone pixel points and outer bone pixel points in the eight-neighborhood of the edge pixel points of the bone connected region; Determine the fracture points through the number of the inner bone edge points and outer bone edge points, and use the fracture points as the seed points; Denote the inner bone pixel points in the eight-neighborhood of each central pixel point as the to-be-grown pixel points of each central pixel point, and obtain the growth coefficient between the central pixel point and each to-be-grown pixel point in the corresponding eight-neighborhood according to the difference between the gradient difference of the central pixel point and the gradient difference of the to-be-grown pixel point; Grow through the seed points and the growth coefficient to obtain several growth lines; Obtain the midpoint of each growth line, obtain the included angle between the two endpoints and the midpoint straight line, denoted as the included angle of each growth line; Obtain the minimum distance between the farthest point from the edge line of the bone connected region on each growth line and the edge line of the bone connected region, denoted as the minimum distance between each growth line and the edge line of the bone connected region; ​ ； In the formula, represents the unevenness of the th growth line, represents the included angle of the th growth line, represents the minimum distance between the th growth line and the edge line of the bone connection region; represents the linear normalization function, represents the bone fracture coefficient of the th growth line; The growth lines with a bone fracture coefficient greater than a fourth preset threshold are recorded as bone fracture lines, and the bone fracture lines in the lower limb fracture image are marked to obtain all bone fracture lines.

2. The high-precision segmentation method for lower limb fracture images based on artificial intelligence according to claim 1, wherein, ​ ​ 3. The high-precision segmentation method for lower limb fracture images based on artificial intelligence according to claim 1, wherein ​ The gradient values of all pixel points inside the leg connected region of the patient are obtained through the Canny edge detection algorithm. The eight-neighborhood pixel points of each pixel point within the leg connected region are obtained. The pixel point with the largest gradient value among the eight-neighborhood pixel points is denoted as the first pixel point of each pixel point, and the pixel point in the eight-neighborhood with the gradient value closest to the gradient value between the eight-neighborhood pixel points and the central pixel point is denoted as the second pixel point of each pixel point; when the first pixel point and the second pixel point are the same pixel point, then the pixel points in the eight-neighborhood are denoted as the third pixel points. All adjacent third pixel points are connected to obtain several initial bone lines.

4. The high-precision segmentation method for lower limb fracture images based on artificial intelligence according to claim 1, wherein, The above-mentioned initial bone lines are extended to obtain several initial extended bone lines. According to the number of intersections after extension, several initial extended bone lines are initially screened out. The specific steps are as follows: Obtain the tangent directions of the endpoints at both ends of each initial bone line. Along the tangent directions of the two endpoints, extend each initial bone line by half on each side to obtain the extended initial bone line, and denote the extended initial bone line as the initial extended bone line; obtain the number of initial extended bone lines that each initial extended bone line intersects with all other initial extended bone lines, and denote it as the intersection number of each initial extended bone line; perform linear normalization on the intersection numbers of all initial extended bone lines, and filter out the initial extended bone lines with the normalized intersection number greater than or equal to the first preset threshold and filter out the initial extended bone lines with the normalized intersection number less than the first preset threshold and retain the initial extended bone lines, so as to obtain several initial extended bone lines after the first screening.

5. The high-precision segmentation method for lower limb fracture images based on artificial intelligence according to claim 1, characterized in that, Taking the endpoints of each initial extended bone line after re-screening as initial seed points, growth is carried out according to the gradient difference between adjacent pixel points to obtain the bone connected region in the leg connected region. The specific steps are as follows: Obtain the eight-neighborhood of each endpoint on each initial extended bone line. Denote any pixel point in the eight-neighborhood of each endpoint as a reference pixel point. Connect each endpoint and the reference pixel point to obtain a straight line between each endpoint and the reference point. Denote the direction perpendicular to the direction of the straight line as the perpendicular direction of the reference point. Obtain the pixel points adjacent to the reference point on both sides in the corresponding perpendicular direction, and denote them as the two gradient points of the reference point. Calculate the absolute value of the difference between the two gradient points, and denote it as the gradient difference of the reference point; obtain the pixel points adjacent to the endpoint on both sides in the corresponding perpendicular direction, and denote them as the two gradient points of the endpoint. Calculate the absolute value of the difference between the gray values of the two gradient points, and denote it as the gradient difference of the endpoint; denote the difference between the gradient difference of the reference point and the gradient difference of the endpoint as the gradient difference between each endpoint and the reference point. Taking all the endpoints on the initial extended bone line as initial seed points, growth is carried out according to the principle of minimizing the gradient difference between each endpoint and all pixel points in all eight-neighborhoods. Denote the grown region as the bone connected region in the leg connected region.

6. The high-precision segmentation method for lower limb fracture images based on artificial intelligence according to claim 5, wherein Obtain the bone inner pixel points and bone outer pixel points in the eight-neighborhood of the edge pixel points of the bone connected region. Through the bone inner pixel points and bone outer pixel points in the eight-neighborhood of the edge pixel points of the bone connected region, obtain the bone inner edge points and bone outer edge points; determine the break points through the number of bone inner edge points and bone outer edge points in the eight-neighborhood of the edge pixel points of the bone connected region. The specific steps are as follows: Denote the pixel points in the eight-neighborhood of the edge pixel points within the bone connected region as bone inner pixel points, and denote the pixel points in the eight-neighborhood of the edge pixel points outside the bone connected region as bone outer pixel points. Calculate the average gray value of all bone inner pixel points in the eight-neighborhood of each edge pixel point of the bone connected region, and denote it as the average bone inner gray value of each edge pixel point of the bone connected region. Calculate the average gray value of all bone outer pixel points in the eight-neighborhood of each edge pixel point of the bone connected region, and denote it as the average bone outer gray value of each edge pixel point of the bone connected region. Compare the difference in gray value between each edge pixel of the bone connected region and the average gray value inside the bone and the average gray value outside the bone. When the difference between the gray value of each edge pixel of the bone connected region and the average gray value inside the bone is less than or equal to the difference between the gray value of the edge pixel and the average gray value outside the bone, the edge pixel of the bone connected region is marked as an inner bone edge point; otherwise, the edge pixel of the bone connected region is marked as an outer bone edge point; Any edge pixel of the bone connected region that contains an inner bone edge point and an outer bone edge point in the eight-neighborhood of any pixel point is marked as a break point.

7. The method for high-precision segmentation of lower limb fracture images based on artificial intelligence according to claim 6, wherein Obtain the growth coefficient between the central pixel point and each to-be-grown pixel point in the corresponding eight-neighborhood according to the difference between the gradient difference of the central pixel point and the gradient difference of the to-be-grown pixel point; grow through the seed point and the growth coefficient to obtain a number of growth lines, and the specific steps are as follows: The formula for the growth coefficient between the central pixel and the th pixel to be grown in the corresponding eight-neighborhood is expressed as: ； In the formula, represents the gradient difference of the central pixel point during the growth process, represents the th gradient difference of the to-be-grown pixel points in the eight-neighborhood of the central point, is the absolute value symbol, represents the exponential function with the natural constant as the base, represents the growth coefficient between the central pixel point and the th to-be-grown pixel point in the corresponding eight-neighborhood; Grow according to the growth coefficient between the seed point and two pixel points, and grow the pixel points whose growth coefficient is greater than or equal to the third preset threshold until the growth ends, and obtain several growth lines.

8. An artificial intelligence-based high-precision segmentation system for lower limb fracture images, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the high-precision segmentation method for lower limb fracture images based on artificial intelligence according to any one of claims 1-7.

Images