Auxiliary marking method for mandibular angle osteotomy range

Abstract

The invention relates to the technical field of medical image analysis, in particular to a mandibular angle osteotomy range auxiliary marking method. The method comprises the following steps of: selecting an actual neural edge according to a gray level similarity condition and position distribution of two suspected neural edges in an edge pair in a local region; obtaining a distance adjustment coefficient according to the correlation between the component of a line segment between a safe osteotomy line of a historical patient and an actual nerve edge in the horizontal direction and the mandible width and the similar situation of the change trend of the safe osteotomy lines of the patient to be detected and the historical patient in the local area on the same side in the horizontal direction; and adjusting the position of the safe osteotomy line in the local area of the patient to be detected by using the position adjusting device to obtain an optimized osteotomy line. According to the method, the correlation between the mandible width of the patient to be detected and image distortion is analyzed based on the position of the inferior alveolar nerve blood vessel, the distortion condition of the safe osteotomy line in the panorama acquisition process is eliminated by using the distance adjustment coefficient, and the rationality of the mandible angle osteotomy range determined based on the optimized osteotomy line is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image analysis, and in particular to a method for auxiliary marking of a mandibular angle osteotomy range. Background Art

[0002] Mandibular angle osteotomy is a common facial plastic surgery that adjusts the chin line by cutting off part of the bone in the mandibular angle area to make it smoother and more natural. The mandibular angle area is densely distributed with important nerve structures such as the facial nerve and the inferior alveolar nerve. If the operation is not performed properly, the nerves may be damaged, causing facial numbness, facial paralysis or loss of sensation. Therefore, assisting in the division of the osteotomy range in mandibular angle osteotomy surgery is of great significance to protecting the key nerves of the mandible.

[0003] X-rays are usually used to collect a panoramic oral view of the patient, in which a safe osteotomy line is determined, and the osteotomy line is projected onto the three-dimensional oral structure to determine the osteotomy range. The oral panoramic view unfolds the jaw arch structure into a flat image, and projecting the three-dimensional oral structure onto the oral panoramic view will cause partial distortion of the oral condition, resulting in errors in the process of projecting the safe osteotomy line determined in the oral panoramic view onto the three-dimensional oral structure, which in turn leads to an inappropriate range of mandibular angle osteotomy. Summary of the invention

[0004] In order to solve the technical problem that the range of mandibular angle osteotomy is inappropriate due to partial distortion of the oral condition in the oral panoramic film, the purpose of the present invention is to provide a method for auxiliary marking of the range of mandibular angle osteotomy. The technical scheme adopted is as follows: The present invention proposes a method for auxiliary marking of mandibular angle osteotomy range, the method comprising: Obtaining a safe osteotomy line in which the mandibular region is divided into two local regions in a panoramic view of the patient's oral cavity; the patient includes a patient to be tested and a historical patient; Obtaining suspected nerve edges in the local area; forming an edge pair from any two suspected nerve edges in the local area, and obtaining the actual nerve edge in the local area according to the grayscale similarity and position distribution of the two suspected nerve edges in the edge pair; According to the correlation between the horizontal component of the line segment between the safety osteotomy line and the actual nerve edge of the historical patients and the mandibular width, and the similarity of the horizontal change trend of the safety osteotomy line in the ipsilateral local area between the patient to be tested and the historical patients, the distance adjustment coefficient of each local area of ​​the patient to be tested is obtained; The position of the safe osteotomy line in the local area of ​​the patient to be tested is adjusted based on the distance adjustment coefficient to obtain an optimized osteotomy line.

[0005] Furthermore, the obtaining of the actual nerve edge in the local area includes: Calculate the variance of the shortest distances from all pixels on any suspected nerve edge in the edge pair to the other suspected nerve edge; The grayscale values ​​of the pixels on the suspected nerve edge are arranged in order to obtain a grayscale sequence; the DTW values ​​of the grayscale sequences of the two suspected nerve edges in the edge pair are obtained; Obtain the canine area and the third molar area in each local area, and the mandibular symmetry line dividing the two local areas; draw parallel lines to the mandibular symmetry line through the pixel points corresponding to the maximum values ​​in the ordinates of the pixel coordinates in the canine area and the third molar area in each local area, and record them as the first reference line and the second reference line respectively; Calculate the average distances from the endpoints of the two suspected nerve edges in each edge pair of each local area to the first reference line and the second reference line, respectively, and record them as the first distance and the second distance respectively; According to the variance, the DTW value, the first distance and the second distance, a neural edge index of each edge pair is obtained; and two suspected neural edges in the edge pair corresponding to the largest neural edge index in each local area are recorded as actual neural edges.

[0006] Furthermore, the step of obtaining the distance adjustment coefficient of each local area of ​​the patient to be tested includes: Obtain the mandibular width of historical patients, perform curve fitting on the mandibular width of all historical patients, and calculate the mean slope of all points on the fitting curve, which is recorded as the first slope; The actual nerve edge closest to the safety osteotomy line in the local area is selected as the target edge, and the line segment with the shortest distance between the safety osteotomy line and its target edge is recorded as the distance line; the mean of the components of the distance lines in the two local areas of all historical patients in the horizontal direction is subjected to curve fitting, and the mean of the slopes of all points on the fitting curve is calculated and recorded as the second slope; Perform curve fitting on the horizontal components of the pixel points on the safe osteotomy line in the local area to obtain the osteotomy component line; calculate the mean of the root mean square errors of the osteotomy component lines in the local areas on the same side of the patient to be tested and different historical patients, and record them as the osteotomy level difference of each local area of ​​the patient to be tested; Performing negative correlation and normalization processing on the product of the absolute value of the difference between the first slope and the second slope and the osteotomy level difference, so as to obtain the correlation between the patient to be tested and the historical patient in each local area; The mandibular width of the patient to be tested is normalized, and a negative correlation mapping is performed on the product of the normalization result and the correlation degree to obtain a distance adjustment coefficient for each local area of ​​the patient to be tested.

[0007] Further, the step of adjusting the position of the safe osteotomy line in the local area of ​​the patient to be tested based on the distance adjustment coefficient to obtain the optimized osteotomy line includes: Using the distance adjustment coefficient, weighted processing is performed on the horizontal component of the distance line in each local area of ​​the patient to be tested, and the square root of the sum of the squares of the components of the distance line in the vertical direction is taken as the optimized distance of the corresponding distance line; The safe osteotomy line of each local area of ​​the patient to be tested is translated along the direction of the distance line to obtain an optimized osteotomy line of the corresponding local area; the distance between the optimized osteotomy line and the target edge in the direction of the distance line is equal to the optimized distance.

[0008] Further, obtaining a neural edge index of each edge pair according to the variance, the DTW value, the first distance and the second distance includes: The sum of the first distance and the second distance is calculated, and the product of the sum, the variance and the DTW value is negatively correlated to obtain a neural edge index of each edge pair.

[0009] Furthermore, obtaining the suspected nerve edge in the local area includes: A pixel point in any local area is recorded as an example point, and the preset neighborhood is divided into two parts based on the symmetry line of the preset neighborhood of the example point. After the cumulative sum of the grayscale values ​​of the pixel points in each part is calculated, the absolute value of the difference between the corresponding cumulative sums of the two parts is recorded as the regional grayscale difference of the symmetry line; the symmetry line corresponding to the maximum value of the regional grayscale difference of all symmetry lines of the preset neighborhood of the example point is selected and recorded as the analysis line of the example point; The pixel point with the smallest angle with the analysis line of the example point within the preset neighborhood of the example point is recorded as a similar point; and the pixel point in the local area and its similar point are subjected to region growth to obtain a suspected nerve edge.

[0010] Furthermore, performing region growing on pixel points and similar points in the local region includes: In the local area, a pixel point is selected as a growth point for regional growth, and similar points of the growth point that meet the preset growth conditions are used as new growth points for regional growth, until the similar points of the new growth points do not meet the preset growth conditions, the regional growth is stopped, and a suspected nerve edge is obtained; The preset growth condition includes: the angle between the analysis line and the corresponding growth point is smaller than a preset angle threshold and the absolute value of the regional grayscale difference is smaller than a preset grayscale difference threshold.

[0011] Furthermore, the two local areas into which the mandibular area is divided are symmetrical about the mandibular symmetry line.

[0012] Furthermore, the mandibular width is equal to the longest distance of the mandibular region in the horizontal direction.

[0013] Furthermore, the preset neighborhood is eight neighborhoods.

[0014] The present invention has the following beneficial effects: In the embodiment of the present invention, in order to avoid damaging the inferior alveolar nerve during mandibular angle osteotomy surgery, the position of the inferior alveolar nerve and blood vessels needs to be determined before adjusting the safe osteotomy line. The position of the nerve and blood vessels in the mandible is fixed, and the two blood vessel wall edges are parallel and the grayscale performance of the two blood vessel wall edges is similar. Combined with the position distribution and grayscale similarity of the two suspected nerve edges in the edge alignment, the actual nerve edge representing the blood vessel wall edge of the inferior alveolar nerve and blood vessels is selected; the oral panoramic image has a distorted structure in the horizontal direction, and the correlation between the horizontal component of the line segment between the safe osteotomy line and the actual nerve edge of the historical patient and the mandibular width is reversed. The correlation between the mandibular width of the historical patients and the horizontal distortion of the oral panoramic view is reflected. The similarity of the horizontal change trend of the safe osteotomy line in the local area on the same side of the patient to be tested and the historical patients reflects the correlation between the patient to be tested and the historical patients. The correlation between the mandibular width of the patient to be tested and the horizontal distortion of the oral panoramic view is analyzed by combining the two to determine the distance adjustment coefficient, which is used to present the required reduction degree of the horizontal component of the distance line. The safe osteotomy line is adjusted to eliminate the distortion of the oral framing view during the image acquisition process, and improve the rationality of the mandibular angle osteotomy range determined based on the optimized osteotomy line. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flowchart of the steps of a method for auxiliary marking of mandibular angle osteotomy range provided by one embodiment of the present invention; Figure 2 A system structure diagram of a mandibular angle osteotomy range auxiliary marking system provided by one embodiment of the present invention; Figure 3 A schematic diagram of a computer device for an auxiliary marking device for the mandibular angle osteotomy range provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a mandibular angle osteotomy range auxiliary marking method proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following is a detailed description of a method for assisting in marking the range of mandibular angle osteotomy provided by the present invention in conjunction with the accompanying drawings.

[0020] Embodiment 1: The present invention proposes a method for assisting the marking of the mandibular angle osteotomy range. Figure 1 , which shows a flowchart of the steps of a method for auxiliary marking of mandibular angle osteotomy range provided by an embodiment of the present invention, the method comprising: Step S1: Obtaining a safe osteotomy line in which the mandibular region is divided into two local regions in an oral panoramic view of the patient; the patient includes a patient to be tested and a historical patient.

[0021] Before collecting oral images, the patient needs to bite the locator correctly and keep the head upright. The locator can keep the mouth open at an appropriate angle. The doctor uses an X-ray machine to rotate around the patient's head to scan the oral cavity and obtain a panoramic view of the oral cavity. In order to facilitate the analysis of the range of mandibular angle osteotomy, it is necessary to extract the mandibular area in the oral panoramic view; based on the symmetry line of the mandibular area, that is, the mandibular symmetry line, it is divided into local areas symmetrical on the left and right sides. The doctor marks a safe osteotomy line, namely the Kamiishi line, in each local area based on experience.

[0022] In an embodiment of the present invention, image processing software such as Dubhewer software is used to perform image segmentation on the oral panoramic image to extract the mandibular area. In other embodiments, semantic segmentation can also be used to extract the mandibular area in the oral panoramic image. The oral panoramic image is input into a trained neural network to output the mandibular area in the panoramic image, and other methods are not limited here.

[0023] It should be noted that in order to ensure the quality of the oral panoramic image, the patient needs to remove dentures, jewelry, glasses and other metal objects in the mouth before the examination, and the patient must remain still during the scanning process.

[0024] Step S2: Obtain the suspected nerve edges in the local area; any two suspected nerve edges in the local area constitute an edge pair, and obtain the actual nerve edges in the local area based on the grayscale similarity and position distribution of the two suspected nerve edges in the edge pair.

[0025] The safety osteotomy line is mainly used to avoid damage to the inferior alveolar nerve in mandibular angle osteotomy surgery. The position of the inferior alveolar nerve and blood vessels needs to be determined before adjusting the safety osteotomy line. In the oral panoramic film, the inferior alveolar nerve and blood vessels usually appear as thin and long dark lines, but local bone density abnormalities in the mandible and certain jaw tumors may also appear as thin and long lines in the image, affecting the determination of the position of the inferior alveolar nerve. The dark line edge of the local area is extracted to obtain the suspected nerve edge.

[0026] Preferably, in some possible implementation modes of the embodiments of the present invention, the method for obtaining the suspected nerve edge includes: randomly selecting a pixel point in a local area as an example point, dividing the preset neighborhood into two parts based on the symmetry line of the preset neighborhood of the example point, calculating the cumulative sum of the grayscale values ​​of the pixel points in each part, and then recording the absolute value of the difference between the corresponding cumulative sums of the two parts as the regional grayscale difference of the symmetry line; selecting the symmetry line corresponding to the maximum value of the regional grayscale difference of all symmetry lines of the preset neighborhood of the example point as the analysis line of the example point; recording the pixel point with the smallest angle with the analysis line of the example point within the preset neighborhood of the example point as a similarity point; performing regional growth on the pixel points in the local area and their similar points to obtain the suspected nerve edge.

[0027] The nerves and blood vessels appear as long and thin dark stripes, with one side of each edge being darker and the other side being brighter; if a pixel is located on the edge of a nerve or blood vessel, the edge divides the preset neighborhood of the pixel into two parts with large grayscale differences, and the analysis line of the pixel represents the local edge of the nerve or blood vessel; because the nerve or blood vessel is relatively smooth, the directions of the analysis lines of adjacent pixels located on the edge of the nerve or blood vessel are relatively consistent, and the greater the possibility that the example point and its similar point are located on the edge of the nerve or blood vessel. Therefore, it is necessary to perform regional growth based on the pixels and their similar points in the local area. Since the edge of the nerve or blood vessel is relatively smooth and the grayscale difference on both sides of the pixel on the edge is relatively close, the smaller the angle between the analysis lines of the growth point and its similar point and the closer the regional grayscale difference, the more likely it is that the growth point and its similar point are located on the edge of the nerve or blood vessel. In an embodiment of the present invention, the regional growing process is as follows: any pixel point in the local area is selected as a growth point for regional growth, and similar points of the growth points that meet the preset growth conditions are used as new growth points for regional growth, and the regional growth is stopped when the similar points of the new growth points do not meet the preset growth conditions, thereby obtaining a suspected nerve edge; the preset growth conditions include: the angle with the analysis line of the corresponding growth point is less than the preset angle threshold and the difference in regional grayscale difference with the corresponding growth point is less than the preset grayscale difference threshold.

[0028] It should be noted that the preset neighborhood in this embodiment is eight neighborhoods, and the symmetry lines of the eight neighborhoods of the example point include a horizontal symmetry line, a vertical symmetry line, a 45-degree diagonal line, and a 135-degree diagonal line.

[0029] In an implementation manner of the embodiment of the present invention, the preset neighborhood is eight neighborhoods, the preset angle threshold is set to 45 degrees, and the preset grayscale difference threshold is set to 10.

[0030] The nerves and blood vessels usually appear as tube piles or linear structures in the images, and the appearance of the blood vessel walls in the images is relatively consistent, which means that the two edges of the blood vessel walls are usually parallel and have similar grayscale. At the same time, the inferior alveolar nerve and blood vessels are usually located between the mandibular third molar area and the premolar area, starting to appear about 1 cm from the mesial or distal surface of the mandibular second molar, and extending to the bottom of the canine area. The inferior alveolar nerve and blood vessels are located between the canine and the third molar. Therefore, the grayscale similarity and position distribution of the two suspected nerve edges in the edge alignment are analyzed to analyze the edge characteristics of the inferior alveolar nerve and blood vessels on the two edges, and then the actual nerve edge is selected.

[0031] Preferably, in some possible implementation modes of the embodiments of the present invention, the method for obtaining the actual nerve edge includes: calculating the variance of the shortest distances from all pixels on any suspected nerve edge in the edge pair to another suspected nerve edge; arranging the grayscale values ​​of the pixels on the suspected nerve edge in sequence to obtain a grayscale sequence; obtaining the DTW value of the grayscale sequence of the two suspected nerve edges in the edge pair; obtaining the canine area and the third molar area in each local area, and the mandibular symmetry line dividing the two local areas; drawing parallel lines to the mandibular symmetry line through the pixel points corresponding to the maximum value in the vertical coordinates of the pixel coordinates in the canine area and the third molar area in each local area, respectively, and recording them as the first reference line and the second reference line respectively; calculating the mean distances from the endpoints of the two suspected nerve edges in each edge pair of each local area to the first reference line and the second reference line respectively, and recording them as the first distance and the second distance respectively; obtaining the nerve edge index of each edge pair according to the variance, DTW value, first distance and second distance; recording the two suspected nerve edges in the edge pair corresponding to the largest nerve edge index in each local area as the actual nerve edges. The dynamic time warping (DTW) algorithm and pixel coordinates are well known to those skilled in the art and will not be described in detail herein.

[0032] The variance of the shortest distance from a pixel point on any suspected nerve edge to another suspected nerve edge in the edge pair is used to measure the parallel distribution of the two suspected nerve edges. The smaller the variance, the greater the possibility of parallel distribution of the two edges, and the greater the possibility of representing the vascular wall of the inferior alveolar nerve and blood vessels. The DTW value of the grayscale sequence of the two suspected nerve edges in the edge pair is used to measure the grayscale similarity of the two suspected nerve edges. The smaller the DTW value, the more similar the grayscale distribution of the two edges, and the greater the possibility of representing the vascular wall of the inferior alveolar nerve and blood vessels. If the endpoints of the two suspected nerve edges in the edge pair close to the mandibular symmetry line are closer to the canine teeth and the endpoints far from the mandibular symmetry line are closer to the third molar, that is, the smaller the first distance and the second distance, the more similar the grayscale distribution of the two edges is, the greater the possibility of representing the vascular wall of the inferior alveolar nerve and blood vessels, and the larger the nerve edge index. The actual nerve edge refers to the edge of the vascular wall of the inferior alveolar nerve and blood vessels.

[0033] Therefore, the variance, DTW value, the first distance, and the second distance are all negatively correlated with the neural edge index. In an embodiment of the present invention, the sum of the first distance and the second distance is calculated, and the product of the sum, the variance, and the DTW value is negatively correlated to obtain the neural edge index of each edge pair. In an embodiment of the present invention, the correlation between the variance, the DTW value, the first distance, and the second distance and the neural edge index can also be constructed through other basic mathematical operations, which will not be limited or elaborated here.

[0034] It should be noted that in the embodiment of the present invention, the inverse of the above-mentioned product is used as the exponent of an exponential function with a natural constant as the base to achieve negative correlation mapping processing of the product. Negative correlation mapping methods such as taking the inverse or the negative number can also be selected, which is not limited here.

[0035] In an embodiment of the present invention, the oral panoramic image is input into a trained neural network, and an oral panoramic image with the canine area and the third molar area marked is output. In other embodiments, the doctor directly marks the canine area and the third molar area in the local area of ​​the oral panoramic image based on experience.

[0036] Step S3: According to the correlation between the horizontal component of the line segment between the safety osteotomy line and the actual nerve edge of the historical patients and the mandibular width, and the similarity of the horizontal change trend of the safety osteotomy line in the ipsilateral local area between the patient to be tested and the historical patients, the distance adjustment coefficient of each local area of ​​the patient to be tested is obtained.

[0037] The safety osteotomy line needs to be located at a certain distance below the inferior alveolar nerve and blood vessels. If the distance is too close, the inferior alveolar nerve and blood vessels may be damaged during the operation, and if the distance is too far, the surgical effect may not be achieved. Therefore, the safety osteotomy line needs to be adjusted based on the position of the safety osteotomy line and the inferior alveolar nerve and blood vessels. The oral panorama unfolds the jaw arch structure into a plane image, resulting in distortion of the horizontal structure, i.e., stretching or compression, so that there is a difference in the horizontal distance between the oral panorama and the oral cavity of the patient to be tested. The increase in mandibular width will aggravate the distortion of the oral panorama. The correlation between the horizontal component of the line segment between the safety osteotomy line and the actual nerve edge of the historical patient and the mandibular width reflects the correlation between the mandibular width of the historical patient and the horizontal distortion of the oral panorama. The similarity of the horizontal change trend of the safety osteotomy line in the local area on the same side between the patient to be tested and the historical patient reflects the correlation between the patient to be tested and the historical patient. The correlation between the mandibular width of the patient to be tested and the horizontal distortion of the oral panorama is analyzed by combining the two, and then the distance adjustment coefficient is determined to eliminate the horizontal distortion of the panorama.

[0038] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the distance adjustment coefficient includes: obtaining the mandibular width of historical patients, performing curve fitting on the mandibular width of all historical patients, calculating the mean slope of all points on the fitting curve, and recording it as the first slope; selecting the actual nerve edge closest to the safety osteotomy line in the local area as the target edge, and recording the line segment with the shortest distance between the safety osteotomy line and its target edge as the distance line; performing curve fitting on the mean of the components of the distance lines of two local areas of all historical patients in the horizontal direction, calculating the mean slope of all points on the fitting curve and recording it as the second slope; and selecting the actual nerve edge closest to the safety osteotomy line in the local area as the target edge, and recording the line segment with the shortest distance between the safety osteotomy line and its target edge as the distance line. The horizontal components of the pixel points on the middle safety osteotomy line are curve fitted to obtain the osteotomy component line; the mean of the root mean square error of the osteotomy component line in the local area on the same side of the patient to be tested and different historical patients is calculated and recorded as the osteotomy level difference of each local area of ​​the patient to be tested; the absolute value of the difference between the first slope and the second slope and the product of the osteotomy level difference are negatively correlated and normalized to obtain the correlation between the patient to be tested and the historical patients in each local area; the mandibular width of the patient to be tested is normalized, and the normalized result and the product of the correlation are negatively correlated to obtain the distance adjustment coefficient of each local area of ​​the patient to be tested.

[0039] The increase in mandibular width will aggravate the distortion of oral panorama. Different patients may have different distortions of oral panorama due to the difference in mandibular width. It is necessary to analyze whether the patient to be tested has the same distortion as the historical patients. The horizontal component of the distance line is affected by the distortion of oral panorama. When analyzing the correlation between mandibular width and distance line, the horizontal component is considered. The first slope and the second slope reflect the change trend of mandibular width and the change trend of horizontal component of distance line of historical patients respectively. If the difference between the first slope and the second slope is smaller, the possibility of positive correlation between mandibular width and horizontal component of distance line of historical patients is greater, indicating that the larger the mandibular width of historical patients, the more obvious the horizontal stretching distortion of oral panorama. At the same time, the smaller the difference in osteotomy level, the more consistent the change trend of osteotomy component line between the patient to be tested and the historical patients, indicating that the correlation between the patient to be tested and the historical patients is stronger. When the mandibular width of the patient to be tested is larger, the oral panorama is more seriously affected by horizontal stretching distortion. Therefore, the larger the mandibular width of the patient to be tested and the greater the correlation between the patient to be tested and the historical patients, the more seriously the oral panoramic image of the patient to be tested will be affected by the horizontal stretching distortion. In order to reduce the influence of distortion during image acquisition, it is necessary to reduce the horizontal component of the distance line, and thus it is necessary to negatively correlate the product of the mandibular width of the patient to be tested and the correlation to obtain the distance adjustment coefficient.

[0040] In the embodiment of the present invention, the opposite number of the data to be processed is used as the exponent of the exponential function with the natural constant as the base, so as to realize the negative correlation and normalization or negative correlation mapping processing of the data to be processed. The historical patients include patients with various mandibular widths, and the mandibular width of the patient to be measured is within the mandibular width range of the historical patients. In this embodiment, the mandibular width of the historical patients is used to perform maximum and minimum value normalization processing on the mandibular width of the patient to be measured.

[0041] It should be noted that the line segment connecting the shortest distance corresponding to the pixel points between any two pixel points located on the safety osteotomy line and its target edge is recorded as the distance line. When performing curve fitting on the horizontal component of the pixel points on the safety osteotomy line in the local area, the horizontal coordinate in the fitting process is the position of the pixel point on the safety osteotomy line, and the vertical coordinate is the horizontal component of the pixel point. When analyzing the root mean square error of the osteotomy component line of the patient to be tested and the historical patient, it is necessary to align the pixel points at the same position on the two osteotomy component lines.

[0042] In an implementation of the embodiment of the present invention, the curve fitting method is the least squares method.

[0043] In one implementation of the embodiment of the present invention, the mandibular width is equal to the longest distance of the mandibular region in the horizontal direction.

[0044] Step S4: adjusting the position of the safe osteotomy line in the local area of ​​the patient to be tested based on the distance adjustment coefficient to obtain an optimized osteotomy line.

[0045] The distance adjustment coefficient shows the required reduction degree of the horizontal component of the distance line. The smaller the distance adjustment coefficient is, the greater the reduction degree of the horizontal component of the distance line due to the horizontal stretching distortion of the oral panoramic image of the patient to be tested is required, and then the position of the safe osteotomy line is adjusted to determine the optimized osteotomy line that eliminates the influence of horizontal distortion caused by the panoramic image acquisition process.

[0046] Preferably, in some possible implementation modes of the embodiments of the present invention, the method for obtaining the optimized osteotomy line includes: using the distance adjustment coefficient to weight the component of the distance line in the horizontal direction in each local area of ​​the patient to be tested, and taking the square root of the sum of the squares of the component of the distance line in the vertical direction as the optimized distance of the corresponding distance line; translating the safe osteotomy line of each local area of ​​the patient to be tested along the direction of the distance line to obtain the optimized osteotomy line of the corresponding local area; the distance between the optimized osteotomy line and the target edge in the direction of the distance line is equal to the optimized distance.

[0047] The optimized osteotomy line is in the two-dimensional image of the oral cavity, but the mandibular angle osteotomy plastic surgery is performed on the three-dimensional mandible of the patient to be tested, and the optimized osteotomy line needs to be projected into the three-dimensional mandible model of the patient to be tested. The specific method is as follows: first, the three-dimensional mandible model of the patient to be tested is generated by cone-beam CT; second, feature points such as tooth tips and roots are extracted from the oral panoramic image of the patient to be tested and the three-dimensional mandible model; then, the feature registration algorithm is used to match the feature points of the oral panoramic image and the three-dimensional mandible model, and the geometric transformation matrix from the oral panoramic image to the three-dimensional mandible model is calculated; finally, the two optimized osteotomy lines of the oral panoramic image are projected onto the three-dimensional mandible model through the transformation matrix, and the three-dimensional model and projection lines are loaded using 3D modeling software such as Mimics software for visualization to obtain the optimized osteotomy lines in the three-dimensional mandible model of the patient to be tested.

[0048] Cutting the jawbone portion below the optimized osteotomy line in the three-dimensional mandibular model of the patient to be tested will not damage the inferior alveolar nerve and blood vessels; the doctor optimizes the jawbone portion below the osteotomy line in the three-dimensional mandibular model to determine the appropriate cutting direction and position based on the facial needs of the patient to be tested.

[0049] So far, the present invention is completed.

[0050] Embodiment 2: The present invention proposes a mandibular angle osteotomy range auxiliary marking system, please refer to Figure 2 , which shows a system structure diagram of a mandibular angle osteotomy range auxiliary marking system provided by an embodiment of the present invention, the system comprising: The data acquisition module 510 is used to obtain a safe osteotomy line in which the mandibular region is divided into two local regions in the oral panoramic view of the patient; the patient includes a patient to be tested and a historical patient; The neural edge extraction module 520 is used to obtain the suspected neural edges in the local area; any two suspected neural edges in the local area form an edge pair, and the actual neural edges in the local area are obtained according to the grayscale similarity and position distribution of the two suspected neural edges in the edge pair; The adjustment coefficient analysis module 530 is used to obtain the distance adjustment coefficient of each local area of ​​the patient to be tested based on the correlation between the horizontal component of the line segment between the safety osteotomy line and the actual nerve edge of the historical patient and the mandibular width, and the similarity of the horizontal change trend of the safety osteotomy line in the local area on the same side between the patient to be tested and the historical patient; The osteotomy range adjustment module 540 is used to adjust the position of the safe osteotomy line in the local area of ​​the patient to be tested based on the distance adjustment coefficient to obtain an optimized osteotomy line.

[0051] It should be noted that: the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the mandibular angle osteotomy range auxiliary marking system and the mandibular angle osteotomy range auxiliary marking method embodiment provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0052] Embodiment 3: Figure 3 A computer device schematic diagram of a mandibular angle osteotomy range auxiliary marking device provided by an embodiment of the present invention. Figure 3 As shown, the computer device includes: a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and running on the processor 602, wherein when the processor 602 executes the computer program 603, the computer device can execute any one of the mandibular angle osteotomy range auxiliary marking methods introduced above.

[0053] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a mandibular angle osteotomy range auxiliary marking method provided in an embodiment of the present application.

[0054] In this embodiment, the functional modules of the device can be divided according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0055] It should be understood that the device provided in this embodiment is used to execute the above-mentioned mandibular angle osteotomy range auxiliary marking method, and thus can achieve the same effect as the above-mentioned implementation method.

[0056] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a device, the processing module may be used to control and manage the actions of the device. The storage module may be used to support the device to execute mutual program codes, etc.

[0057] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits included in the disclosure of this application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0058] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0060] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for auxiliary marking of mandibular angle osteotomy range, characterized in that: The method includes: Obtaining a safe osteotomy line in which the mandibular region is divided into two local regions in an oral panoramic view of the patient; the patient includes a patient to be tested and a historical patient; Obtaining suspected nerve edges in the local area; forming an edge pair from any two suspected nerve edges in the local area, and obtaining the actual nerve edge in the local area according to the grayscale similarity and position distribution of the two suspected nerve edges in the edge pair; According to the correlation between the horizontal component of the line segment between the safety osteotomy line and the actual nerve edge of the historical patients and the mandibular width, and the similarity of the horizontal change trend of the safety osteotomy line in the ipsilateral local area between the patient to be tested and the historical patients, the distance adjustment coefficient of each local area of ​​the patient to be tested is obtained; The position of the safe osteotomy line in the local area of ​​the patient to be tested is adjusted based on the distance adjustment coefficient to obtain an optimized osteotomy line.

2. The method for auxiliary marking of mandibular angle osteotomy range according to claim 1, characterized in that: The obtaining of the actual nerve edge in the local area comprises: Calculate the variance of the shortest distances from all pixels on any suspected nerve edge in the edge pair to the other suspected nerve edge; The grayscale values ​​of the pixels on the suspected nerve edge are arranged in order to obtain a grayscale sequence; the DTW values ​​of the grayscale sequences of the two suspected nerve edges in the edge pair are obtained; Obtain the canine area and the third molar area in each local area, and the mandibular symmetry line dividing the two local areas; draw parallel lines to the mandibular symmetry line through the pixel points corresponding to the maximum values ​​in the ordinates of the pixel coordinates in the canine area and the third molar area in each local area, and record them as the first reference line and the second reference line respectively; Calculate the average distances from the endpoints of the two suspected nerve edges in each edge pair of each local area to the first reference line and the second reference line, respectively, and record them as the first distance and the second distance respectively; According to the variance, the DTW value, the first distance and the second distance, a neural edge index of each edge pair is obtained; and two suspected neural edges in the edge pair corresponding to the largest neural edge index in each local area are recorded as actual neural edges.

3. The method for auxiliary marking of mandibular angle osteotomy range according to claim 1, characterized in that: The step of obtaining the distance adjustment coefficient of each local area of ​​the patient to be tested includes: Obtain the mandibular width of historical patients, perform curve fitting on the mandibular width of all historical patients, and calculate the mean slope of all points on the fitting curve, which is recorded as the first slope; The actual nerve edge closest to the safety osteotomy line in the local area is selected as the target edge, and the line segment with the shortest distance between the safety osteotomy line and its target edge is recorded as the distance line; the mean of the components of the distance lines in the two local areas of all historical patients in the horizontal direction is subjected to curve fitting, and the mean of the slopes of all points on the fitting curve is calculated and recorded as the second slope; Perform curve fitting on the horizontal components of the pixel points on the safe osteotomy line in the local area to obtain the osteotomy component line; calculate the mean of the root mean square errors of the osteotomy component lines in the local areas on the same side of the patient to be tested and different historical patients, and record them as the osteotomy level difference of each local area of ​​the patient to be tested; Performing negative correlation and normalization processing on the product of the absolute value of the difference between the first slope and the second slope and the osteotomy level difference, so as to obtain the correlation between the patient to be tested and the historical patient in each local area; The mandibular width of the patient to be tested is normalized, and a negative correlation mapping is performed on the product of the normalization result and the correlation degree to obtain a distance adjustment coefficient for each local area of ​​the patient to be tested.

4. The method for auxiliary marking of mandibular angle osteotomy range according to claim 3, characterized in that: The step of adjusting the position of the safe osteotomy line in the local area of ​​the patient to be tested based on the distance adjustment coefficient to obtain the optimized osteotomy line comprises: Using the distance adjustment coefficient, weighted processing is performed on the horizontal component of the distance line in each local area of ​​the patient to be tested, and the square root of the sum of the squares of the components of the distance line in the vertical direction is taken as the optimized distance of the corresponding distance line; The safe osteotomy line of each local area of ​​the patient to be tested is translated along the direction of the distance line to obtain the optimized osteotomy line of the corresponding local area; the distance between the optimized osteotomy line and the target edge in the direction of the distance line is equal to the optimized distance.

5. The method for auxiliary marking of mandibular angle osteotomy range according to claim 2, characterized in that: The obtaining of a neural edge index of each edge pair according to the variance, the DTW value, the first distance and the second distance includes: The sum of the first distance and the second distance is calculated, and the product of the sum, the variance and the DTW value is negatively correlated to obtain a neural edge index of each edge pair.

6. The method for auxiliary marking of mandibular angle osteotomy range according to claim 1, characterized in that: The obtaining of the suspected nerve edge in the local area includes: A pixel point in any local area is recorded as an example point, and the preset neighborhood is divided into two parts based on the symmetry line of the preset neighborhood of the example point. After the cumulative sum of the grayscale values ​​of the pixel points in each part is calculated, the absolute value of the difference between the corresponding cumulative sums of the two parts is recorded as the regional grayscale difference of the symmetry line; the symmetry line corresponding to the maximum value of the regional grayscale difference of all symmetry lines of the preset neighborhood of the example point is selected and recorded as the analysis line of the example point; The pixel point with the smallest angle with the analysis line of the example point within the preset neighborhood of the example point is recorded as a similar point; and the pixel point in the local area and its similar point are subjected to region growth to obtain a suspected nerve edge.

7. The method for auxiliary marking of mandibular angle osteotomy range according to claim 6, characterized in that: The performing region growing on the pixel points and similar points in the local region comprises: In the local area, a pixel point is selected as a growth point for regional growth, and similar points of the growth point that meet the preset growth conditions are used as new growth points for regional growth, until the similar points of the new growth points do not meet the preset growth conditions, the regional growth is stopped, and a suspected nerve edge is obtained; The preset growth condition includes: the angle between the analysis line and the corresponding growth point is smaller than a preset angle threshold and the absolute value of the regional grayscale difference is smaller than a preset grayscale difference threshold.

8. The method for auxiliary marking of mandibular angle osteotomy range according to claim 2, characterized in that: The two local areas into which the mandibular region is divided are symmetrical with respect to the mandibular symmetry line.

9. The method for auxiliary marking of mandibular angle osteotomy range according to claim 1, characterized in that: The mandibular width is equal to the longest distance of the mandibular region in the horizontal direction.

10. The method for auxiliary marking of mandibular angle osteotomy range according to claim 6, characterized in that: The preset neighborhood is eight neighborhoods.

Images