Implant implantation correction method

Abstract

The invention discloses an implant implantation correction method, which comprises the following steps of: (1) framing a target implant on an original two-dimensional image to obtain a mask of the target implant; (2) obtaining a candidate connected domain passing through a mask area in the original two-dimensional image, extracting a candidate binary outer contour of the candidate connected domain, and obtaining a candidate line segment in the candidate connected domain; (3) combining the candidate line segments to obtain a line segment combination corresponding to the target implant; (4) drawing a target line segment combination on the binary image, obtaining a target connected domain, and taking a middle point of a short side of a minimum enclosing rectangle of the target connected domain as an extension line end point to be drawn; and (5) connecting the end points of the extension line, calculating the deviation between the implantation angle of the implant and the planned angle according to the extension line end points, and correcting the implant when the deviation exceeds a limited range. When the implant is implanted, the axial direction of the implant is identified, the deviation between the implantation angle and the planned angle can be calculated, and when the deviation exceeds a limited range, angle adjustment of the implant is prompted.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an implant correction method. Background Art

[0002] Kirschner wire is a medical device widely used in surgical operations, and it has powerful functions. It can be used not only as an implant, such as for fixing fractures to help fracture healing, but also as a tool, such as a guide tool to provide guidance for subsequent drilling and screw insertion, thereby improving the success rate.

[0003] As a guide tool for metal implants, the Kirschner wire needs to be implanted in the body in advance according to the planned angle to reach the specified position. If it is found that it is inconsistent with the plan after implantation, it needs to be removed and implanted again until the requirements are met. Multiple implantations not only prolong the operation time, but may also cause greater harm to the human body. Summary of the invention

[0004] Purpose of the invention: In view of the above-mentioned deficiencies, the present invention proposes an implant correction method, which identifies the implant when it is implanted and extends it at both ends to calculate the deviation between the implantation angle and the planned angle. When the deviation exceeds the specified range, the angle adjustment is prompted to achieve a successful implantation in one go.

[0005] Technical solution:

[0006] The present invention provides an implant correction method, comprising the steps of:

[0007] (1) Selecting the target implant on the original two-dimensional image containing the implant to obtain its mask;

[0008] (2) obtaining and screening the candidate connected domains passing through the mask area in the original two-dimensional image, extracting the corresponding candidate binary outer contours, performing straight line search on the candidate binary outer contours to obtain a number of single line segments, and screening to obtain candidate line segments;

[0009] (3) combining the candidate line segments obtained in step (2), calculating the intersection of each line segment combination with the mask area, and retaining the line segment combination with the longest total line segment length as the line segment combination corresponding to the target implant;

[0010] (4) drawing all the line segments in the line segment combination obtained in step (3) on the binary image, obtaining a minimum circumscribed rectangle containing all the line segments, extending the minimum circumscribed rectangle along the length direction until it intersects with the edge of the binary image, subtracting the minimum circumscribed rectangle from the candidate connected domain to obtain a target connected domain, obtaining a minimum circumscribed rectangle of the target connected domain, and using the midpoint of the short side of the minimum circumscribed rectangle as the endpoint of the extended line to be drawn;

[0011] (5) Connect the endpoints of the extension line obtained in step (4), and calculate the deviation between the implantation angle and the planned angle of the implant based on the connection, and correct it when the deviation exceeds the specified range.

[0012] Specifically, in the step (2), the candidate connected domains in the mask are obtained and screened, specifically:

[0013] (21) obtaining a gradient binary image corresponding to the original two-dimensional image, and searching for connected domains on the image to obtain a plurality of connected domains;

[0014] (22) performing intersection calculation on each connected domain obtained in step (21) and the mask area, and retaining the connected domains in which the pixel points of the intersection are greater than the first threshold;

[0015] (23) Perform straight line detection on the binary gradient image to obtain a number of candidate line segments, perform intersection calculations on the candidate line segments with the connected domains retained in step (22), and retain the connected domains in which the pixel points of the intersection are greater than the second threshold as candidate connected domains.

[0016] More specifically, the step (21) comprises:

[0017] Acquire a gradient binary image corresponding to the original two-dimensional image, perform connected domain search and screening on the gradient binary image, and obtain a first screened image;

[0018] The original two-dimensional image is binarized, and connected domains are searched and screened, and then the intersection is taken with the first screened image to obtain a second screened image, that is, to obtain several connected domains therein.

[0019] Furthermore, the step of obtaining the gradient binary image corresponding to the original two-dimensional image is specifically as follows:

[0020] The original two-dimensional image is subjected to gradient detection to obtain a gradient image, and the gradient image is subjected to binarization processing using an adaptive binarization method to obtain a corresponding gradient binary image.

[0021] Furthermore, the condition for screening the connected domain is: removing the connected domains whose width and height are less than 5 pixels, within 10 pixels from the image edge or whose area is less than 100 in the binary image obtained by the binarization process.

[0022] More specifically, in the step (23), before performing line detection on the gradient binary image, it also includes a step of performing edge detection on the gradient binary image.

[0023] More specifically, in the step (2), the extraction of the candidate binary outer contour corresponding to the candidate connected domain is as follows:

[0024] The intersection of each candidate connected domain and each candidate line segment is calculated respectively, and the ratio between the area corresponding to the intersection and the area of ​​the corresponding candidate connected domain is calculated. The candidate connected domains whose ratio is greater than the set ratio are retained, and their outer contours are used as candidate binary outer contours.

[0025] Specifically, in step (2), the screening to obtain the candidate line segments is as follows:

[0026] The slope ranges of all single line segments are distributed and counted to obtain the slope distribution ranges corresponding to the single line segments with a set proportion, and the single line segments outside the slope distribution range are removed to obtain candidate line segments.

[0027] Specifically, in the step (3), when combining the candidate line segments, it is determined whether the two candidate line segments belong to the same implant based on whether the distance between the extension lines of the two candidate line segments in the mask area is within the set distance. If so, the two candidate line segments belong to the same implant, otherwise they do not.

[0028] Specifically, in the step (1), after selecting the target implant, the step also includes removing an area within a set range outside the selected area.

[0029] Beneficial effects: The present invention selects the target implant by a frame, and uses a set of line segments to replace the implant to extend the implant after identification. It is suitable for complex application scenarios in clinical images with large differences in brightness or contrast, various metal adhesions and intersections, and implant bending. It can simultaneously meet the requirements of high accuracy, low missed detection rate, and low false detection rate. The present invention identifies the implant when it is implanted in the human body, and then extends it at both ends to calculate the deviation between the implantation angle and the planned angle. When the deviation exceeds the specified range, an angle adjustment prompt is given to achieve the purpose of successful implantation in one go. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are merely embodiments of the present invention, and ordinary technicians in this field can obtain other drawings based on these drawings without creative work.

[0031] Figure 1 An exemplary flow chart of the implant correction method of the present invention;

[0032] Figure 2 The original two-dimensional image containing the Kirschner wire is obtained;

[0033] Figure 3 For Figure 2 Example of Kirschner wire selection on the top;

[0034] Figure 4 for Figure 3 The mask binary image of the K-wire selection area;

[0035] Figure 5 For Figure 2 Example graph obtained by performing gradient search;

[0036] Figure 6 For Figure 5 An example of the result of binarization.

[0037] Figure 7 For Figure 6 An example diagram of a first screening image obtained by performing contour screening;

[0038] Figure 8 For Figure 2 An example of the result of binarization.

[0039] Fig. 9 For Figure 8 Perform contour screening and compare with Figure 7 An example diagram of a second screened image obtained by performing intersection calculation;

[0040] Fig.10 For Figure 2 An example of the results obtained by edge detection;

[0041] Fig.11 For Fig.10 An example of the results obtained by performing straight line detection;

[0042] Fig.12 is a sample graph of candidate connected domains;

[0043] Fig.13 is a sample image of candidate contours;

[0044] Fig.14 Based on Fig.13 An example of the results of straight line detection and single line segment screening and extraction;

[0045] Fig.15 For Fig.14 Example of target Kirschner wires obtained through screening;

[0046] Fig.16 Based on Fig.15 An example diagram of finding the endpoint of the extension line of the target Kirschner wire is obtained;

[0047] Fig.17 This is an example of a drawn K-wire extension line. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0049] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present invention should have the common meanings understood by persons having ordinary skills in the field to which the present invention belongs.

[0050] The implant correction method of the present invention is as follows Figure 1 As shown, the steps include:

[0051] S1, selecting the target implant on the original two-dimensional image containing the implant, and filling the selected area to obtain a mask;

[0052] Acquire an original two-dimensional image containing at least one implant. In a specific embodiment of the present invention, the implant is a Kirschner wire, such as Figure 2 As shown, a closed frame is used to frame the target implant on the original two-dimensional image. Further, a rectangular frame can be used to frame a partial area of ​​the target implant, such as Figure 3 As shown, the selected area is filled to obtain a mask;

[0053] Specifically, the mask obtained by filling the framed area is to take the pixel value of the pixel point in the framed area as 255, and take the pixel value of the pixel point outside the framed area as 0, so as to obtain the corresponding mask, such as Figure 4 shown.

[0054] Furthermore, in order to remove edge interference, in the present invention, an area within a set range outside the framed area is removed. Specifically, the area within the set range is an area with a width of 10 pixels outside the framed area.

[0055] Generally, in the present invention, there is usually only one implant in the framed area, and other interferences may be included in the framed area. However, when selecting, it is necessary to ensure that the foreground of the target implant accounts for the largest proportion as much as possible to improve the overall recognition accuracy of the implant.

[0056] In addition, if the target implant is curved, the frame selection should be as close as possible to the end of the target implant to be extended. Through such a design, the slope of the line segment actually retained in the subsequent process can be close to the slope of the extension line of the target implant to be extended, thereby solving the problem of inaccurate extension of the implant when it is curved.

[0057] If the target implant is not selected, all metal implants in the image must be automatically identified and extended, which increases the complexity of the algorithm and cannot simultaneously meet the requirements of low missed detection rate and high recognition accuracy. In addition, too many detected targets will interfere with the user's vision. In the future, it is likely that the user will still be required to specify and only display the extension line of a certain implant.

[0058] S2, performing gradient detection on the original two-dimensional image obtained in S1, and performing binarization processing on the original two-dimensional image to obtain a corresponding gradient binary image, and performing connected domain search and screening on the gradient binary image to obtain a first screened image;

[0059] In the present invention, the Sobel operator is used to perform gradient detection on the original two-dimensional image obtained by S1, such as Figure 5 As shown, a better edge detection effect can be produced, and the edge of the Kirschner wire can be found when the edge is relatively unclear, so as to reduce the missed detection rate.

[0060] In the present invention, in actual clinical surgery, the exposure imaging conditions and the location of the implant are unknown. In this scenario, the intensity value of each pixel in the gradient image obtained by gradient detection is quite different. If a fixed threshold binarization method such as OTSU is used, the target edge image obtained may be broken, which increases the difficulty of subsequent algorithms. Therefore, the present invention adopts an adaptive binarization method, in which the weighted average of the gradient intensity in the neighborhood of each pixel is used to determine the segmentation threshold of each pixel, such as Figure 6 As shown, a more complete target edge can be obtained, which is convenient for searching candidate lines. In the present invention, the kernel function size of the adaptive binarization method can be 3, 5 or 7, and 5 is preferred in this embodiment.

[0061] In the present invention, the connected domain search and screening are performed on the gradient binary image to remove interference from the regions with smaller width and height, located at the edge of the image or with smaller contour area, and the first screening image is obtained by drawing with a rough edge, such as Figure 7 As shown, the present invention adopts the form of rough edge to ensure that the actual edge is preserved.

[0062] In the present invention, the screening conditions for searching and screening the connected domain of the binary gradient image obtained by S2 are: the width and height are less than 5 pixels, within 10 pixels from the edge of the image, or the contour area is less than 100, that is, the connected domains that meet these conditions need to be removed. Through this setting, missed detection can be reduced. Furthermore, the present invention can be further narrowed on the basis of these conditions, such as the width and height are less than 3 pixels, within 0 pixels from the edge, or the contour area is less than 10, but the subsequent screening time will be increased accordingly.

[0063] S3, binarizing the original two-dimensional image obtained in S1, searching and screening the connected domain of the original two-dimensional image, and then taking the intersection with the first screening image to obtain a second screening image;

[0064] In the present invention, the binarization processing of the original two-dimensional image obtained by S1 can also be performed by adaptive binarization processing, such as Figure 8 As shown, specifically, the kernel function of the adaptive binarization processing in this step can be an odd number between 9 and 17, and 15 is preferred in this embodiment.

[0065] In the present invention, the connected domain search and screening are performed on the original two-dimensional image after binarization to remove interference with small width and height dimensions, located at the edge of the image or with a small connected domain area. The conditions for contour search and screening settings can be consistent with S2.

[0066] In the present invention, after the original two-dimensional image after binarization is subjected to contour search and screening, the original two-dimensional image is intersected with the first screening image to obtain a second screening image such as Fig. 9 As shown, the obtained second screening image needs to meet the following conditions: the number of pixels in the intersection is greater than the set value; in the present invention, the set value can be 50-100, and 100 is preferably taken in this embodiment.

[0067] S4, performing intersection calculation on each connected domain in the second screening image obtained in S3 and the mask area obtained in S1, and retaining the connected domains in which the pixel points of the intersection are greater than the first threshold;

[0068] In the present invention, the first threshold value may be 20-100, and in this embodiment, 100 is preferably selected.

[0069] S5, edge detection is performed on the gradient binary image obtained in S2, and straight line detection is performed on it to obtain a number of candidate line segments, and intersection calculations are performed on the connected domain obtained in S4 and the aforementioned several candidate line segments, and the connected domains in which the pixel points of the intersection are greater than the second threshold are retained as candidate connected domains, such as Fig.12 As shown;

[0070] In the present invention, the canny algorithm can be used to perform edge detection on the gradient binary image obtained by S2, such as Fig.10 As shown; further, the setting of the low threshold and the high threshold in the canny algorithm can ensure that there is a larger threshold range, thereby reducing the missed detection rate.

[0071] In the present invention, straight line detection can use Hough transform based on cumulative probability, so that a series of line segments can be obtained, such as Fig.11 shown.

[0072] In the present invention, the second threshold value may be 20-100, and in this embodiment, 100 is preferably selected.

[0073] S6, respectively calculating the intersection of each candidate connected domain and each candidate line segment obtained in S5, calculating the ratio between the area corresponding to the intersection and the area of ​​the corresponding candidate connected domain, retaining the candidate connected domains whose ratio is greater than the set ratio, and taking their outer contours as candidate binary outer contours; if there is no candidate binary outer contour, returning to S1;

[0074] In the present invention, after obtaining a candidate connected domain that meets the requirements, the outer contour of the aforementioned candidate connected domain can be redrawn on a new image, and then the candidate binary outer contour can be obtained, such as Fig.13 shown.

[0075] In the present invention, the area of ​​a line segment is the number of pixels in the area corresponding to the line segment.

[0076] In this embodiment, the ratio may be set to 0.2-0.4, preferably 0.4.

[0077] In the present invention, there is generally only one candidate binary outer contour, otherwise a pop-up window prompt is displayed to prompt the user to re-select the target implant on the original two-dimensional image obtained in S1. At this time, there are the following possibilities: the target implant is not included in the selected area, the selection is too large or too small, or the selected area contains too much interference. In this case, a relatively clean area can be selected for re-selection, that is, return to S1.

[0078] S7, performing straight line search on the candidate binary outer contour obtained in S6 to obtain a number of single line segments, screening to obtain candidate line segments, and if there are not at least two single line segments in the candidate line segments, returning to S1;

[0079] Taking the Kirschner wire as an example, a Kirschner wire has at least two line segments located on both sides of the Kirschner wire. These line segments belong to the same connected domain corresponding to the binary outer contour in the binary image, and the slopes of the line segments are similar. If there are not at least two single line segments, a pop-up window prompts the user to re-select the target implant on the original two-dimensional image obtained by S1, that is, return to S1.

[0080] In the present invention, after obtaining a number of single line segments, the slope ranges of all the single line segments are distributed and counted. Based on the principle of minority obeys majority, a retention ratio can be set according to actual needs. According to the slope ranges of all the single line segments counted above and the retention ratio, the single line segments whose slopes are outside the retention ratio and are greatly different from the slopes of most of the single line segments are removed. Such single line segments may be interference caused by the setting of the threshold during straight line detection, and candidate line segments are obtained, wherein different line segments are represented by different colors, such as Fig.14 The blue and purple segments in the figure.

[0081] S8, combining the candidate line segments obtained in S7, calculating the intersection of each line segment combination and the mask obtained in S1, and retaining the line segment combination with the longest total line segment length as the line segment combination corresponding to the target implant;

[0082] In the present invention, when combining candidate line segments, the thickness of an implant such as a Kirschner wire can be obtained based on experience. When the extension lines of the two sides of the Kirschner wire are in the mask, the distance between the corresponding line segments on the extension lines should be within a set range. That is, whether the two candidate line segments belong to the same implant can be determined based on whether the distance between the extension lines of the two candidate line segments in the mask area is within the set distance. If so, the two candidate line segments belong to the same implant, otherwise they do not. The set distance here depends on the content of the detection. If only thinner implants are detected, the set range can be set smaller (such as 1-20mm) based on prior information. If other relatively thick implants are to be identified, the set range can be set larger (such as 1-40mm).

[0083] In this embodiment, although only one candidate contour is retained, the adhesion between metals makes the single line segment in the found contour likely to belong to multiple objects. Therefore, different line segments belonging to the same object can be combined according to the slope information, and the intersection of each line segment combination and the mask obtained by S1 is calculated, and the combination with the longest total length of the line segment is retained as the line segment combination corresponding to the target implant, such as Fig.15 shown.

[0084] In the present invention, generally there is at least one set of line segments, otherwise a pop-up window prompt is displayed to prompt the user to re-select the target implant on the original two-dimensional image acquired in S1, that is, return to S1.

[0085] S9, draw all the line segments in the line segment combination retained in S8 on the binary image, obtain the minimum bounding rectangle containing all the line segments, extend the minimum bounding rectangle along the length direction until it intersects with the edge of the binary image, and obtain an image area, subtract the image area from the connected domain corresponding to the candidate contour obtained in S6, perform contour search after morphological operation, and obtain the target connected domain connected to the edge of the image, and obtain the minimum bounding rectangle of the target connected domain respectively. The midpoint of the short side of the minimum bounding rectangle is the end point of the extended line to be drawn, as shown in the example Fig.16 shown.

[0086] In the present invention, there is generally at least one set of endpoints, otherwise a pop-up window prompt is displayed to prompt the user to re-select the target implant on the original two-dimensional image acquired in S1, that is, return to S1.

[0087] S10, connect S9 to get the extension line endpoint, for example Fig.17 As shown, the deviation between the implantation angle of the implant and the planned angle is calculated accordingly, and when the deviation exceeds the specified range, the angle of the implant is prompted to be adjusted, thereby achieving the goal of a successful implantation in one go.

[0088] In the present invention, there may be a situation where the mask obtained by S1 is very close to the edge of the image. In this case, the aforementioned image area is subtracted from the connected domain corresponding to the candidate contour obtained by S6. In the obtained connected domain, the length dimension may be very short, that is, there is only a small area at the edge of the image. This part of the area does not meet the aforementioned set length range and can be eliminated, that is, the distance between the two short side midpoints of the minimum circumscribed rectangle of the target connected domain obtained by S9, that is, the two extension line endpoints, does not exceed the set value, and the connected domain close to the edge of the image is eliminated to obtain the final target connected domain, and the deviation between the implantation angle of the implant and the planned angle is calculated with its corresponding extension line endpoints.

[0089] The present invention selects the target implant by a frame, and replaces the implant with a set of line segments to extend the implant after identification. It is suitable for complex application scenarios in clinical images with large differences in brightness or contrast, various metal adhesions and intersections, and implant bending, and can simultaneously meet the requirements of high accuracy, low missed detection rate, and low false detection rate. The present invention identifies the implant when it is implanted in the human body, and then extends it at both ends to calculate the deviation between the implantation angle and the planned angle. When the deviation exceeds the specified range, the implant angle adjustment is prompted to achieve the purpose of successful implantation in one go.

[0090] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention (including the claims) is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0091] The embodiments of the present invention are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for implant correction, characterized in that: Includes steps: (1) Selecting the target implant on the original two-dimensional image containing the implant to obtain its mask; (2) obtaining and screening the candidate connected domains passing through the mask area in the original two-dimensional image, extracting the corresponding candidate binary outer contours, performing straight line search on the candidate binary outer contours to obtain a number of single line segments, and screening to obtain candidate line segments; (3) combining the candidate line segments obtained in step (2), calculating the intersection of each line segment combination with the mask area, and retaining the line segment combination with the longest total line segment length as the line segment combination corresponding to the target implant; (4) drawing all the line segments in the line segment combination obtained in step (3) on the binary image, obtaining a minimum circumscribed rectangle containing all the line segments, extending the minimum circumscribed rectangle along the length direction until it intersects with the edge of the binary image, subtracting the minimum circumscribed rectangle from the candidate connected domain to obtain a target connected domain, obtaining a minimum circumscribed rectangle of the target connected domain, and using the midpoint of the short side of the minimum circumscribed rectangle as the endpoint of the extended line to be drawn; (5) Connect the endpoints of the extension line obtained in step (4), and calculate the deviation between the implantation angle and the planned angle of the implant based on the connection, and correct it when the deviation exceeds the specified range.

2. The implant correction method according to claim 1, characterized in that: In the step (2), the step of obtaining and screening the candidate connected domains in the mask is specifically as follows: (21) obtaining a gradient binary image corresponding to the original two-dimensional image, and searching for connected domains on the image to obtain a plurality of connected domains; (22) performing intersection calculation on each connected domain obtained in step (21) and the mask area, and retaining the connected domains in which the pixel points of the intersection are greater than the first threshold; (23) Perform straight line detection on the binary gradient image to obtain a number of candidate line segments, perform intersection calculations on the candidate line segments with the connected domains retained in step (22), and retain the connected domains in which the pixel points of the intersection are greater than the second threshold as candidate connected domains.

3. The implant correction method according to claim 2, characterized in that: The step (21) comprises: Acquire a gradient binary image corresponding to the original two-dimensional image, perform connected domain search and screening on the gradient binary image, and obtain a first screened image; The original two-dimensional image is binarized, and connected domains are searched and screened, and then the intersection is taken with the first screened image to obtain a second screened image, that is, to obtain several connected domains therein.

4. The implant correction method according to claim 3, characterized in that: The step of obtaining the gradient binary image corresponding to the original two-dimensional image is specifically as follows: The original two-dimensional image is subjected to gradient detection to obtain a gradient image, and the gradient image is subjected to binarization processing using an adaptive binarization method to obtain a corresponding gradient binary image.

5. The implant correction method according to claim 3, characterized in that: The condition for screening the connected domain is: removing the connected domains whose width and height are less than 5 pixels, within 10 pixels from the edge of the image, or whose area is less than 100 in the binary image obtained by the binarization process.

6. The implant correction method according to claim 2, characterized in that: In the step (23), before performing straight line detection on the gradient binary image, it also includes a step of performing edge detection on the gradient binary image.

7. The implant correction method according to claim 2, characterized in that: In the step (2), the extraction of the candidate binary outer contour corresponding to the candidate connected domain is specifically as follows: The intersection of each candidate connected domain and each candidate line segment is calculated respectively, and the ratio between the area corresponding to the intersection and the area of ​​the corresponding candidate connected domain is calculated. The candidate connected domains whose ratio is greater than the set ratio are retained, and their outer contours are used as candidate binary outer contours.

8. The implant correction method according to claim 1, characterized in that: In step (2), the screening to obtain candidate line segments is as follows: The slope ranges of all single line segments are distributed and counted to obtain the slope distribution ranges corresponding to the single line segments with a set proportion, and the single line segments outside the slope distribution range are removed to obtain candidate line segments.

9. The implant correction method according to claim 1, characterized in that: In the step (3), when combining the candidate line segments, it is determined whether the two candidate line segments belong to the same implant based on whether the distance between the extension lines of the two candidate line segments in the mask area is within the set distance. If so, the two candidate line segments belong to the same implant, otherwise they do not.

10. The implant correction method according to claim 1, characterized in that: In the step (1), after selecting the target implant, the step also includes removing an area within a set range outside the selected area.

Images