Personalized tibia osteotomy three-dimensional model generation method based on CT scanning data

Abstract

The invention relates to the technical field of tibia osteotomy three-dimensional model construction, in particular to a personalized tibia osteotomy three-dimensional model generation method based on CT scanning data. The method comprises the steps of obtaining tibia CT slices of a patient; obtaining the structural feature indexes of the angular points according to the occurrence and distribution of the angular points in the tibia CT slice in the different scale transformation images; according to the matching condition of the angular points in the tibia CT slices of the current patient and the historical patient, the stable distribution degree of the angular points is obtained; according to the structural characteristic indexes and the stable distribution degree, the type of each angular point in the tibia CT slice of the current patient is obtained, and a tibia osteotomy three-dimensional model of the current patient is constructed. According to the method, the tibia osteotomy three-dimensional model is constructed on the basis of obtaining the type of each angular point in the tibia CT slice of the current patient, each part of the tibia of the current patient can be accurately identified, damage to blood vessels in tissues in the tibia treatment process is avoided, and the tibia treatment effect is effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of constructing a three-dimensional tibial osteotomy model, and in particular to a method for generating a personalized three-dimensional tibial osteotomy model based on CT scanning data. Background Art

[0002] Medial Open-Wedge High Tibial Osteotomy (MOWHTO) is a surgical method used to treat medial compartment osteoarthritis of the knee. During the operation, the osteotomy angle and distraction distance need to be precisely determined to achieve accurate correction of tibial deformity.

[0003] In the existing method, the CT slices of the tibia are analyzed, and a three-dimensional model of the tibial osteotomy is constructed using 3D printing technology, so as to obtain the angle and distraction distance of the osteotomy, improve the accuracy of the operation and effectively shorten the operation time. However, in the process of treating the tibia, it is also necessary to ensure that important blood vessels in the tissues around the tibia are avoided to avoid heavy bleeding during the operation and affect the progress of the operation. However, in the existing method, only a three-dimensional model of the tibial osteotomy is constructed, and the blood vessels in the tissues around the tibia are not taken into account, which can easily cause the set angle and distraction distance of the tibial osteotomy to damage the blood vessels in the tissue, affecting the treatment of the tibia. Summary of the invention

[0004] In order to solve the technical problem that the angle and distraction distance of tibial osteotomy set without considering the blood vessels in the surrounding tissues of the tibia cause damage to the blood vessels in the tissues, thereby affecting the treatment of the tibia, the purpose of the present invention is to provide a method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data, and the technical scheme adopted is as follows: An embodiment of the present invention provides a method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data, the method comprising the following steps: Obtain a preset number of tibial CT slices of historical patients and the current patient; The scale of each tibial CT slice is transformed by Gaussian pyramid, and the structural characteristic index of each corner point in each tibial CT slice is obtained according to the appearance and distribution of each corner point in each tibial CT slice in different scale-transformed images; According to the differences in structural characteristic indicators of the corner points matched between the current patient and each historical patient's tibial CT slices in different scale transformation images and the matching of the corner points between the current patient and each historical patient's tibial CT slices, the stable distribution degree of each corner point in each tibial CT slice of the current patient is obtained; According to the structural characteristic index and stable distribution degree of each corner point in each tibial CT slice of the current patient, the type of each corner point in each tibial CT slice of the current patient is obtained, and the tibial osteotomy three-dimensional model of the current patient is constructed; The method for obtaining the structural characteristic index is: For any tibia CT slice and any corner point in the tibia CT slice, obtaining the conspicuity of the corner point according to the appearance of the corner point in different scale transformed images corresponding to the tibia CT slice; Obtaining a distribution characteristic value of the corner point according to the distribution of the corner point in different scale transformation images corresponding to the tibia CT slice; The product of the conspicuousness of the corner point and the distribution characteristic value is used as the structural characteristic index of the corner point; The method for obtaining the stable distribution degree is: According to the difference in structural characteristic indexes of the matching corner points between the tibial CT slices of the current patient and each historical patient in different scale transformation images, the matching degree of each tibial CT slice of the current patient and each historical patient is obtained; The tibial CT slices of each patient are labeled with the same number in a specified order; wherein each tibial CT slice of a patient corresponds to a unique number; For any corner point in any numbered tibial CT slice of the current patient, obtain the corner points matched by the corner point in any numbered tibial CT slice of all historical patients, and use them as reference corner points; The accumulated result of the matching degree between the current patient and any numbered tibial CT slice of the historical patient corresponding to each reference corner point is used as the stable analysis value of the corner point; The result of normalizing the ratio of the stable analysis value to the total number of all historical patients is taken as the stable distribution degree of the corner point.

[0005] Furthermore, the method for obtaining the degree of obviousness is: Obtaining the number of images in which the corner point exists in different scale transformed images corresponding to the tibia CT slice as a first number; The ratio of the first number to the total number of all images transformed at different scales corresponding to the tibia CT slice is taken as the conspicuity of the corner point.

[0006] Furthermore, the method for obtaining the distribution characteristic value is: For any scale image in the different scale transformation images corresponding to the tibia CT slice, the corner point corresponding to the corner point in the scale image is used as the target corner point, and a local area of ​​the target corner point is constructed with the target corner point as the center and a preset length as the radius; The ratio of the number of corner points in the local area to the area of ​​the local area is used as the density distribution degree of the corner points in the scale image; For any edge line passing through the target corner point, the ratio of the number of corner points on the edge line to the number of all pixel points on the edge line is used as the first eigenvalue of the edge line; The sum of the first eigenvalues ​​of all edge lines passing through the target corner point is used as the position analysis value of the corner point in the scale image; The product of the density distribution degree of the corner point in the scale image and the position analysis value is used as the overall reference value of the corner point in the scale image; The overall reference values ​​of the corner point in all the different scale transformation images corresponding to the tibia CT slice are added, and the negative correlation and normalization results are taken as the distribution characteristic value of the corner point.

[0007] Furthermore, the method for obtaining the matching degree is: For any historical patient and any label, use any labeled tibial CT slice of the current patient as the first image, and any labeled tibial CT slice of the historical patient as the second image; For any scale, the corner points in the first image that exist in the image corresponding to the first image after the scale transformation are all taken as first corner points, and the corner points in the second image that exist in the image corresponding to the second image after the scale transformation are all taken as second corner points; Matching pairs obtained by matching the first corner point with the second corner point are all used as reference matching pairs; For any reference matching pair, the difference in the structural feature indexes of the two corner points in the reference matching pair is negatively correlated and normalized, and the result is used as the matching analysis value of the reference matching pair; The sum of the matching analysis values ​​of all reference matching pairs is used as the reference matching value of any numbered tibial CT slice of the current patient and the historical patient under the scale transformation; Obtain reference matching values ​​of the current patient and any of the labeled tibial CT slices of the historical patient under each different scale transformation, and use the maximum reference matching value as the matching degree between the current patient and any of the labeled tibial CT slices of the historical patient.

[0008] Furthermore, the method for obtaining the type of each corner point in each tibial CT slice of the current patient is: For any corner point in any tibial CT slice of the current patient, when the structural characteristic index of the corner point is greater than the preset structural characteristic index threshold and the stable distribution degree is greater than the preset stable distribution degree threshold, the type of the corner point is a normal part of the tibial contour; When the structural characteristic index of the corner point is greater than the preset structural characteristic index threshold, and the stable distribution degree is less than or equal to the preset stable distribution degree threshold, the type of the corner point is a diseased abnormal part of the tibial contour; When the structural characteristic index of the corner point is less than or equal to the preset structural characteristic index threshold, and the stable distribution degree is greater than the preset stable distribution degree threshold, the type of the corner point is a blood vessel in the tissue; When the structural feature index of the corner point is less than or equal to the preset structural feature index threshold and the stable distribution degree is less than or equal to the preset stable distribution degree threshold, the type of the corner point is an interference point.

[0009] Furthermore, the method for constructing the tibial osteotomy three-dimensional model of the current patient is: The corner points in different tibial CT slices of the current patient are matched according to the types of corner points, and the matched corner points are used as the center points of the quadtree to divide the voxel blocks to construct the tibial osteotomy three-dimensional model of the current patient.

[0010] Furthermore, the method for acquiring the corner points is: acquiring the corner points in the tibial CT slices by using a SIFT corner point detection algorithm.

[0011] The present invention has the following beneficial effects: The present invention firstly performs scale transformation on each tibial CT slice by using a Gaussian pyramid, which is beneficial to accurately analyze the characteristics of each corner point in the tibial CT slice; then, according to the appearance and distribution of each corner point in each tibial CT slice in different scale transformation images, the structural characteristic index of each corner point in each tibial CT slice is obtained, and the performance characteristics of each corner point are accurately reflected, which is beneficial to the subsequent accurate acquisition of the type of each corner point in the tibial CT slice of the current patient; in order to more accurately obtain the type of each corner point in the tibial CT slice of the current patient, so that each part of the constructed tibial osteotomy three-dimensional model of the current patient is more complete and accurate, further according to the difference in the structural characteristic index of the matching corner points of the tibial CT slices of the current patient and each historical patient in the different scale transformation images and the corner points in the tibial CT slices of the current patient and each historical patient The matching situation of each corner point in each tibial CT slice of the current patient is obtained, and the stable distribution degree of each corner point in each tibial CT slice of the current patient is obtained, which accurately reflects the matching situation of each corner point in each tibial CT slice of the current patient with the corner points in the tibial CT slices of historical patients, and further shows the characteristics of each corner point in each tibial CT slice of the current patient; then according to the structural characteristic index and stable distribution degree of each corner point in each tibial CT slice of the current patient, the type of each corner point in each tibial CT slice of the current patient is accurately obtained, and the various parts of the tibia of the current patient are accurately determined, and then the tibial osteotomy three-dimensional model of the current patient is accurately constructed, and the blood vessels in the surrounding tissues of the tibia are accurately displayed, so as to avoid damage to the blood vessels in the tissues during the tibial treatment of the current patient, effectively improve the tibial treatment effect of the current patient, and ensure the stability of the tibial treatment surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] 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.

[0013] Figure 1 A schematic flow chart of a method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data provided by one embodiment of the present invention; Figure 2 A flow chart of a method for obtaining a structural feature index provided by an embodiment of the present invention; Figure 3 A flow chart of a method for obtaining a stable distribution degree provided by an embodiment of the present invention; Figure 4A structural diagram of a system for generating a personalized tibial osteotomy three-dimensional model based on CT scan data provided by one embodiment of the present invention; Figure 5 A schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0014] 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 method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data proposed by the present invention, its specific implementation method, structure, features and effects, 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.

[0015] 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.

[0016] The specific scheme of the method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data provided by the present invention is described in detail below with reference to the accompanying drawings.

[0017] Embodiment 1: The present invention proposes a method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data. Figure 1 , which shows a schematic flow chart of a method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data provided by an embodiment of the present invention, the method comprising the following steps: Step S1: Obtain a preset number of tibial CT slices of historical patients and the current patient.

[0018] Specifically, in order to accurately construct the tibial osteotomy three-dimensional model of the current patient, the blood vessels in the tissues surrounding the tibia are taken into consideration to avoid the subsequent acquisition of the osteotomy angle and the opening distance causing serious damage to the blood vessels in the tissues, causing heavy bleeding, and affecting the treatment of the tibia. Therefore, the tibial osteotomy three-dimensional model constructed in this embodiment should also accurately display the blood vessels of the tissues surrounding the tibia. It is known that the structural distribution of the human tibia is similar, and then this embodiment compares and analyzes the tibial structure of the current patient with that of historical patients, so as to accurately identify the blood vessels in the tissues surrounding the tibia of the current patient, so as to avoid damage to the blood vessels during the surgical treatment of the tibia of the current patient.

[0019] In order to accurately construct the tibial osteotomy three-dimensional model of the current patient, this embodiment obtains a preset number of tibial CT slices of historical patients and the current patient from the hospital database. Among them, this embodiment sets the preset number to 1000, and the implementer can set the size of the preset number according to the actual situation, which is not limited here. It should be noted that the tibial CT slice is a slice of the cross section of the tibia, so the outer contour of the tibia in the tibial CT slice is roughly circular.

[0020] Step S2: scale-transform each tibial CT slice using a Gaussian pyramid, and obtain the structural feature index of each corner point in each tibial CT slice according to the appearance and distribution of each corner point in each tibial CT slice in different scale-transformed images.

[0021] It is known that when constructing the three-dimensional model of the tibial osteotomy of the current patient, the tibial CT slices of the current patient need to be aligned. After alignment, the corner points in each tibial CT slice can be obtained by the SIFT (Scale-Invariant Feature Transform) corner detection algorithm for matching, and then the voxel blocks are divided according to the matched corner points, and finally the three-dimensional model of the tibial osteotomy of the current patient is constructed. Among them, the SIFT (Scale-Invariant Feature Transform) corner detection algorithm is a well-known technology and will not be described in detail. However, the three-dimensional model of the tibial osteotomy of the current patient constructed by the above method cannot determine the abnormal part of the tibia and the blood vessels in the surrounding tissues of the tibia. Therefore, this embodiment needs to analyze each corner point in the tibial CT image of the current patient and determine the type of each corner point, so that the three-dimensional model of the tibial osteotomy of the current patient can be accurately and completely constructed subsequently.

[0022] It is known that in tibial CT slices, the tibial contour is the most obvious and the corner points on the edge line corresponding to the tibial contour are sparsely distributed, and the edge line corresponding to the tibial contour is relatively long; in tibial CT slices, the interior of the tibia is a complex honeycomb shape, the corner points are densely distributed, but the edge line where the corner points are located is relatively short; in tibial CT slices, the corner points corresponding to the blood vessels in the tissue are distributed in a disordered manner, and the edge line where the corner points are located is also relatively short. In order to accurately identify the type of each corner point in the tibial CT slice, the present embodiment first scales each tibial CT slice through the Gaussian pyramid, so that the characteristics of each corner point can be analyzed more accurately later. When a corner point in a tibial CT slice exists more times in the different scale transformation images of the tibial CT slice, it means that the corner point is more obvious in the tibial CT slice, and the corner point is more likely to be the corresponding point of the tibial contour; at the same time, when the local corner point density distribution of the corresponding corner point in the different scale transformation images of the tibial CT slice is smaller, and the corner points on the edge line where the corresponding corner point is located are fewer and the edge line is shorter, it also means that the corner point is more likely to be the corresponding point of the tibial contour. Among them, the Gaussian pyramid is a well-known technology and will not be repeated. It should be noted that in the present embodiment, the proportional coefficient k in the Gaussian pyramid is set to 1.5 and the parameter sigma is set to 1.6. The implementer can set the size of the proportional coefficient k and the parameter sigma according to the actual situation, which is not limited here. Therefore, this embodiment obtains the structural feature index of each corner point in each tibial CT slice according to the appearance and distribution of each corner point in each tibial CT slice in different scale transformation images. The larger the structural feature index, the more likely the corresponding corner point is the corresponding point of the tibial contour.

[0023] Preferably, in one possible implementation of this embodiment, the method for obtaining the structural feature index is as follows: Figure 2 , which shows a flow chart of a method for obtaining a structural feature index provided in this embodiment, the method comprising the following steps: Step S201: for any tibia CT slice and any corner point in the tibia CT slice, obtain the prominence of the corner point according to the appearance of the corner point in different scale transformed images corresponding to the tibia CT slice.

[0024] It is known that when the gray value of a corner point in a tibial CT slice is larger, the corner point exists more often in the different scale transformation images of the tibial CT slice, wherein the corner point with a larger gray value is more obvious and more likely to be a corresponding point of the tibial contour, and then this embodiment obtains the degree of obviousness of the corner point according to the appearance of the corner point in the different scale transformation images corresponding to the tibial CT slice. The greater the degree of obviousness, the more likely the corner point is to be a corresponding point of the tibial contour.

[0025] Preferably, in a method that can be implemented in this embodiment, the method for obtaining the degree of conspicuity is: obtaining the number of images in which the corner point exists in different scale transformed images corresponding to the tibia CT slice, as the first number; and taking the ratio of the first number to the total number of all different scale transformed images corresponding to the tibia CT slice as the conspicuity of the corner point.

[0026] Step S202: obtaining a distribution characteristic value of the corner point according to the distribution of the corner point in the different scale transformed images corresponding to the tibia CT slice.

[0027] During the process of different scale transformation of the tibia CT slice through the Gaussian pyramid, some corner points disappear. Therefore, this embodiment only analyzes the scale image where the corner point exists in the different scale transformation images corresponding to the tibia CT slice, and obtains the distribution characteristic value of the corner point by analyzing the distribution of the corner point in the existing corresponding scale image, wherein the larger the distribution characteristic value, the more likely the corner point is to be the corresponding point of the tibia contour.

[0028] Preferably, in a method that can be implemented in this embodiment, the method for obtaining the distribution characteristic value is: for any scale image in the different scale transformation images corresponding to the tibial CT slice, the corner point corresponding to the corner point in the scale image is used as the target corner point (the target corner point is the corner point that the corner point exists in the scale image), and the local area of ​​the target corner point is constructed with the target corner point as the center and the preset length as the radius; this embodiment sets the preset length to 10 pixels, and the implementer can set the size of the preset length according to actual conditions, which is not limited here. It should be noted that the local area of ​​the target corner point only analyzes the area located in the scale image. The ratio of the number of corner points existing in the local area to the area of ​​the local area is used as the density distribution degree of the corner point in the scale image; the smaller the density distribution degree, the more likely the corner point is to be the corresponding point of the tibial contour, because the corner points on the tibial contour are sparsely distributed; In order to more accurately analyze the characteristics of the corner point, and further analyze the edge line where the target corner point is located, for any edge line passing through the target corner point, the ratio of the number of corner points on the edge line to the number of all pixel points on the edge line is used as the first eigenvalue of the edge line; the smaller the first eigenvalue, the more likely the edge line is to be the edge line corresponding to the tibia contour. In order to perform an overall analysis, the sum of the first eigenvalues ​​of all edge lines passing through the target corner point is used as the position analysis value of the corner point in the scale image; the smaller the position analysis value, the more likely the corner point is to be the point corresponding to the tibia contour. Then, the product of the density distribution degree and the position analysis value of the corner point in the scale image is taken as the overall reference value of the corner point in the scale image; the smaller the overall reference value, the more likely the corner point is to be the corresponding point of the tibia contour; in order to more accurately analyze the possibility that the corner point is the corresponding point of the tibia contour, the overall reference values ​​of all different scale transformation images corresponding to the corner point in the tibia CT slice are further added, and the result of negative correlation and normalization is taken as the distribution characteristic value of the corner point.

[0029] The calculation formula of the distribution characteristic value is: ; In the formula, is the distribution characteristic value of the i-th corner point in the a-th tibia CT slice; N is the total number of different scale conversion images corresponding to the a-th tibia CT slice; is the number of corner points in the local area corresponding to the target corner point in the nth scale image of the i-th corner point in the a-th tibia CT slice; is the local area of ​​the target corner point corresponding to the i-th corner point in the a-th tibial CT slice in the n-th scale image; is the density distribution degree of the i-th corner point in the a-th tibia CT slice in the n-th scale image; is the number of edge lines that the i-th corner point in the a-th tibia CT slice passes through in the n-th scale image; is the number of corner points on the mth edge line that the corresponding target corner point of the i-th corner point in the a-th tibial CT slice passes through in the n-th scale image; is the number of all pixels on the mth edge line that the corresponding target corner point of the i-th corner point in the a-th tibial CT slice passes through in the n-th scale image; is the first eigenvalue of the mth edge line that the i-th corner point in the a-th tibia CT slice passes through in the n-th scale image; is the position analysis value of the i-th corner point in the a-th tibia CT slice in the n-th scale image; is the overall reference value of the i-th corner point in the a-th tibia CT slice in the n-th scale image; exp is an exponential function with a natural constant as the base.

[0030] It should be noted that if the corner point does not exist in a certain scale-transformed image corresponding to the tibia CT slice, the overall reference value of the corner point in the scale image is assumed to be 0.

[0031] Step S203: taking the product of the conspicuity of the corner point and the distribution characteristic value as the structural characteristic index of the corner point.

[0032] It is known that the greater the degree of prominence and the greater the distribution characteristic value, both indicate that the corresponding corner point is more likely to be the corresponding point of the tibia contour. Therefore, in this embodiment, the product of the degree of prominence of the corner point and the distribution characteristic value is used as the structural characteristic index of the corner point.

[0033] At this point, the structural feature index of each corner point is obtained.

[0034] Step S3: According to the differences in structural feature indicators of the matching corner points between the tibial CT slices of the current patient and each historical patient in different scale transformation images and the matching of the corner points in the tibial CT slices of the current patient and each historical patient, the stable distribution degree of each corner point in each tibial CT slice of the current patient is obtained.

[0035] Specifically, by analyzing the structural characteristic index of each corner point in each tibial CT slice of the current patient, it can only be evaluated that the corner point corresponding to the larger structural characteristic index is more likely to be the corresponding point of the tibial contour, and the corner point corresponding to the smaller structural characteristic index is more likely to be the corresponding point of the blood vessel in the external tissue of the tibia, the corresponding point of the internal part of the tibia, or the corresponding point of the noise. It is known that the abnormal part of the tibia is reflected in the tibial contour. At this time, the structural characteristic indexes corresponding to the corner points of the normal part and the abnormal part of the tibial contour are both larger. Therefore, the abnormal part of the tibia of the current patient cannot be accurately identified by the structural characteristic index of the corner point; at the same time, in order to accurately identify the corner points corresponding to the blood vessels in the external tissue of the tibia, it is also necessary to avoid the interference of the corner points corresponding to the noise and the corner points inside the tibia.

[0036] Considering that the characteristics of the corresponding corner points of the blood vessels in the tissue around the tibia of the current patient are similar to those of the corresponding corner points of the blood vessels in the tissue around the tibia of a large number of historical patients, because the distribution of human body structure is similar; at the same time, the characteristics of the corner points of the normal part of the tibia contour of the current patient are also similar to those of the corner points of the normal part of the tibia contour of a large number of historical patients; because there must be obvious differences between the abnormal part of the tibia contour of the current patient and the tibia contour of a large number of historical patients, and because the internal honeycomb structure of the tibia is diverse, there are also obvious differences in the characteristics of the internal corner points of the tibia of the current patient and those of the internal corner points of the tibia of historical patients; it is known that noise is random, and thus there are obvious differences between the corner points corresponding to the noise in the tibia CT slice of the current patient and the corner points in the tibia CT slice of the historical patients.

[0037] Therefore, this embodiment first analyzes the overall matching of each tibial CT slice of the current patient and each historical patient according to the difference in structural feature indicators of the matching corner points of the tibial CT slices of the current patient and each historical patient in different scale transformation images, and then determines the stable distribution of each corner point in each tibial CT slice of the current patient according to the matching of the corner points in the tibial CT slices of the current patient and each historical patient, which indirectly explains the matching of each corner point in the tibial CT slice of the current patient with the corner point in the tibial CT slice of the historical patient, which is conducive to accurately distinguishing the type of each corner point in the tibial CT slice of the current patient in the subsequent. Therefore, this embodiment obtains the stable distribution degree of each corner point in each tibial CT slice of the current patient according to the difference in structural feature indicators of the matching corner points of the tibial CT slices of the current patient and each historical patient in different scale transformation images and the matching of the corner points in the tibial CT slices of the current patient and each historical patient. Among them, the greater the stable distribution degree, the more the corresponding corner point in the tibial CT slice of the current patient matches the corner point in the tibial CT slice of the historical patient, and the more likely the corresponding corner point in the tibial CT slice of the current patient is the corresponding point of the normal part in the tibial contour of the current patient or the corresponding point of the blood vessel in the tissue.

[0038] Preferably, in one possible implementation of this embodiment, the method for obtaining the stable distribution degree can be found in Figure 3 , which shows a flow chart of a method for obtaining a stable distribution degree provided in this embodiment, the method comprising the following steps: Step S301: Obtain the matching degree of each tibia CT slice of the current patient and each historical patient according to the difference in structural feature indexes of matching corner points between the tibia CT slices of the current patient and each historical patient in different scale transformation images.

[0039] The greater the matching degree, the more consistent the corner point distribution characteristics in the corresponding tibial CT slices of the current patient and the corresponding historical patient are. Corner point matching is a well-known technology and will not be described in detail.

[0040] Preferably, in a method that can be implemented in this embodiment, the method for obtaining the degree of matching is: labeling each patient's tibial CT slices with the same number in a specified order; wherein each tibial CT slice of a patient corresponds to a unique number; this embodiment sets the specified order from top to bottom, and the numbering sequence is 1, 2, 3..., and the implementer can set the specified order, the number and the numbering sequence according to actual conditions, which is not limited here. For any historical patient and any label, the tibial CT slice of the current patient with the label is used as the first image, and the tibial CT slice of the historical patient with the label is used as the second image; for any scale, the corner points in the first image that exist in the image corresponding to the first image after the scale transformation are used as the first corner points, and the corner points in the second image that exist in the image corresponding to the scale transformation are used as the second corner points; the matching pairs obtained by matching the first corner point with the second corner point are used as reference matching pairs; wherein a reference matching pair contains two corner points, namely a first corner point and a second corner point; for any reference matching pair, the absolute values ​​of the difference in the structural feature indicators of the two corner points in the reference matching pair are negatively correlated and normalized as the matching analysis value of the reference matching pair; the larger the matching analysis value, the greater the matching degree of the two corner points in the reference matching pair. It should be noted that, in this embodiment, The absolute value of the difference between the structural feature indicators of the two corner points in the reference matching pair is negatively correlated and normalized, where exp is an exponential function with a natural constant as the base, and X represents the absolute value of the difference between the structural feature indicators of the two corner points in the reference matching pair; In order to analyze the matching situation of the labeled tibial CT slice of the current patient and the historical patient under the scale transformation, the addition result of the matching analysis values ​​of all reference matching pairs is used as the reference matching value of the labeled tibial CT slice of the current patient and the historical patient under the scale transformation; the larger the reference matching value, the better the matching effect of the labeled tibial CT slice of the current patient and the historical patient under the scale transformation; in order to obtain the matching situation of the labeled tibial CT slice of the current patient and the historical patient, the reference matching value of the labeled tibial CT slice of the current patient and the historical patient under each different scale transformation is obtained, and the maximum reference matching value is used as the matching degree of the labeled tibial CT slice of the current patient and the historical patient.

[0041] Step S302: According to the matching degree and the matching of the corner points in the tibial CT slices of the current patient and each historical patient, the stable distribution degree of each corner point in each tibial CT slice of the current patient is obtained.

[0042] In order to accurately analyze whether each corner point in each tibial CT slice of the current patient is a corner point corresponding to a stable distribution structure in the human body, this embodiment obtains the stable distribution degree of each corner point in each tibial CT slice of the current patient according to the matching degree and the matching of the corner points in the tibial CT slices of the current patient and each historical patient. The greater the stable distribution degree, the more likely the corresponding corner point is to be a corner point corresponding to a normal part of the tibial contour or a corner point corresponding to a blood vessel in the tissue.

[0043] Preferably, in a method that can be implemented in this embodiment, the method for obtaining the degree of stable distribution is: for any corner point in the labeled tibial CT slice of the current patient, obtain the corner points that match the corner point in the labeled tibial CT slices of all historical patients, and use them as reference corner points; it should be noted that the reference corner points may not exist in all historical patients' labeled tibial CT slices. In order to accurately analyze the stable distribution of the corner point, the cumulative result of the matching degree of the current patient with the labeled tibial CT slice of the historical patient corresponding to each reference corner point is used as the stable analysis value of the corner point; then the ratio of the stable analysis value to the total number of all historical patients is normalized as the stable distribution degree of the corner point. It should be noted that in this embodiment, the ratio of the stable analysis value to the total number of all historical patients is normalized by the norm normalization function.

[0044] At this point, the stable distribution degree of each corner point in each tibial CT slice of the current patient is accurately obtained.

[0045] Step S4: According to the structural characteristic index and stable distribution degree of each corner point in each tibial CT slice of the current patient, the type of each corner point in each tibial CT slice of the current patient is obtained, and a tibial osteotomy three-dimensional model of the current patient is constructed.

[0046] It is known that the larger the structural characteristic index is, the more likely the corresponding corner point is to be a corresponding point of the tibia contour; the smaller the structural characteristic index is, the more likely the corresponding corner point is to be a corresponding point of a blood vessel in the external tissue of the tibia, a corresponding point inside the tibia, or a corresponding point of noise; the larger the degree of stable distribution is, the more likely the corresponding corner point is to be a corresponding point of a normal part of the tibia contour or a corresponding point of a blood vessel in the tissue; the smaller the degree of stable distribution is, the more likely the corresponding corner point is to be a corresponding point of an abnormal part of the tibia contour, a corresponding point inside the tibia, or a corresponding point of noise. Therefore, this embodiment obtains the type of each corner point in each tibia CT slice of the current patient according to the structural characteristic index and stable distribution degree of each corner point in each tibia CT slice of the current patient.

[0047] Preferably, in a method that can be implemented in this embodiment, the method for obtaining the type of each corner point in each tibial CT slice of the current patient is: for any corner point in any tibial CT slice of the current patient, when the structural characteristic index of the corner point is greater than the preset structural characteristic index threshold and the stable distribution degree is greater than the preset stable distribution degree threshold, the type of the corner point is a normal part of the tibial contour; when the structural characteristic index of the corner point is greater than the preset structural characteristic index threshold and the stable distribution degree is less than or equal to the preset stable distribution degree threshold, the type of the corner point is a diseased abnormal part of the tibial contour; when the structural characteristic index of the corner point is less than or equal to the preset structural characteristic index threshold and the stable distribution degree is greater than the preset stable distribution degree threshold, the type of the corner point is a blood vessel in the tissue; when the structural characteristic index of the corner point is less than or equal to the preset structural characteristic index threshold and the stable distribution degree is less than or equal to the preset stable distribution degree threshold, the type of the corner point is an interference point, wherein the interference points include corner points corresponding to noise and corner points inside the tibia, and the interference points are not considered when constructing the tibial osteotomy three-dimensional model of the current patient. In this embodiment, the preset structural feature index threshold and the preset stable distribution degree threshold are both set to 0.6. The implementer can set the preset structural feature index threshold and the preset stable distribution degree threshold according to actual conditions, which are not limited here.

[0048] After determining the type of each corner point in each tibial CT slice of the current patient, the corner points in different tibial CT slices of the current patient are matched according to the type of the corner points, and the diseased abnormal part information and blood vessel information in the tissue of the current patient's tibia are obtained, and then the matched corner points are used as the center points of the quadtree to divide the voxel blocks, and the tibial osteotomy three-dimensional model of the current patient is accurately constructed, wherein the constructed tibial osteotomy three-dimensional model includes the blood vessels in the surrounding tissue of the tibia, so that the blood vessels in the tissue are avoided in the subsequent treatment process of the tibia of the current patient, ensuring the stable progress of the tibial treatment surgery of the current patient, and improving the treatment effect of the tibia. Among them, the quadtree is a well-known technology and will not be described in detail.

[0049] In summary, the present embodiment obtains the patient's tibial CT slices; obtains the structural characteristic index of the corner points according to the appearance and distribution of the corner points in the tibial CT slices in different scale transformation images; obtains the stable distribution degree of the corner points according to the matching of the corner points in the tibial CT slices of the current patient and the historical patients; obtains the type of each corner point in the tibial CT slice of the current patient according to the structural characteristic index and the stable distribution degree, and constructs the tibial osteotomy three-dimensional model of the current patient. The present invention constructs a tibial osteotomy three-dimensional model based on obtaining the type of each corner point in the tibial CT slice of the current patient, which is conducive to accurately identifying various parts of the tibia of the current patient, avoiding damage to blood vessels in the tissue during tibial treatment, and effectively improving the effect of tibial treatment.

[0050] Embodiment 2: The present invention also proposes a personalized tibial osteotomy three-dimensional model generation system based on CT scan data, please refer to Figure 4 , which shows a structural diagram of a personalized tibial osteotomy three-dimensional model generation system based on CT scan data provided by an embodiment of the present invention, the system includes: a tibial CT slice acquisition module 10, a structural feature index acquisition module 20, a stable distribution degree acquisition module 30 and a tibial osteotomy three-dimensional model construction module 40.

[0051] The tibia CT slice acquisition module 10 is used to acquire tibia CT slices of a preset number of historical patients and the current patient.

[0052] The structural feature index acquisition module 20 is used to scale each tibial CT slice through a Gaussian pyramid, and obtain the structural feature index of each corner point in each tibial CT slice according to the appearance and distribution of each corner point in each tibial CT slice in different scale-transformed images.

[0053] The stable distribution degree acquisition module 30 is used to obtain the stable distribution degree of each corner point in each tibial CT slice of the current patient based on the differences in structural feature indicators of the matching corner points in the tibial CT slices of the current patient and each historical patient in different scale transformation images and the matching of the corner points in the tibial CT slices of the current patient and each historical patient.

[0054] The tibial osteotomy three-dimensional model construction module 40 is used to obtain the type of each corner point in each tibial CT slice of the current patient according to the structural characteristic index and stable distribution degree of each corner point in each tibial CT slice of the current patient, and construct the tibial osteotomy three-dimensional model of the current patient.

[0055] It should be noted that: the system 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 personalized tibial osteotomy three-dimensional model generation system based on CT scan data and the personalized tibial osteotomy three-dimensional model generation method based on CT scan data 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.

[0056] Embodiment 3: The present invention also proposes a device for generating a personalized tibial osteotomy three-dimensional model based on CT scan data, the device comprising a memory and a processor, wherein an executable program code is stored in the memory, and the processor is used to call and execute the executable program code to execute a personalized tibial osteotomy three-dimensional model generation method based on CT scan data provided in an embodiment of the present application. The device can specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a personalized tibial osteotomy three-dimensional model generation method based on CT scan data provided in the above embodiment.

[0057] In addition, the present application embodiment also protects a computer device, see Figure 5 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein when the processor 402 executes the computer program 403, the computer device can execute any one of the personalized tibial osteotomy three-dimensional model generation methods based on CT scan data introduced above.

[0058] Embodiment 4: This embodiment also provides a computer-readable storage medium, which stores a computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned related method steps to implement a personalized tibial osteotomy three-dimensional model generation method based on CT scan data provided in the above embodiment.

[0059] Embodiment 5: This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data provided in the above embodiment.

[0060] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0061] 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.

[0062] 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.

Claims

1. A method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data, characterized in that: The method comprises the following steps: Obtain a preset number of tibial CT slices of historical patients and current patients; The scale of each tibial CT slice is transformed by Gaussian pyramid, and the structural characteristic index of each corner point in each tibial CT slice is obtained according to the appearance and distribution of each corner point in each tibial CT slice in different scale-transformed images; According to the differences in structural characteristic indicators of the corner points matched between the current patient and each historical patient's tibial CT slices in different scale transformation images and the matching of the corner points between the current patient and each historical patient's tibial CT slices, the stable distribution degree of each corner point in each tibial CT slice of the current patient is obtained; According to the structural characteristic index and stable distribution degree of each corner point in each tibial CT slice of the current patient, the type of each corner point in each tibial CT slice of the current patient is obtained, and the tibial osteotomy three-dimensional model of the current patient is constructed; The method for obtaining the structural characteristic index is: For any tibia CT slice and any corner point in the tibia CT slice, obtaining the conspicuity of the corner point according to the appearance of the corner point in different scale transformed images corresponding to the tibia CT slice; Obtaining a distribution characteristic value of the corner point according to the distribution of the corner point in different scale transformation images corresponding to the tibia CT slice; The product of the conspicuousness of the corner point and the distribution characteristic value is used as the structural characteristic index of the corner point; The method for obtaining the stable distribution degree is: According to the difference in structural characteristic indexes of the matching corner points between the tibial CT slices of the current patient and each historical patient in different scale transformation images, the matching degree of each tibial CT slice of the current patient and each historical patient is obtained; The tibial CT slices of each patient are labeled with the same number in a specified order; wherein each tibial CT slice of a patient corresponds to a unique number; For any corner point in any numbered tibial CT slice of the current patient, obtain the corner points matched by the corner point in any numbered tibial CT slice of all historical patients, and use them as reference corner points; The accumulated result of the matching degree between the current patient and any numbered tibial CT slice of the historical patient corresponding to each reference corner point is used as the stable analysis value of the corner point; The result of normalizing the ratio of the stable analysis value to the total number of all historical patients is taken as the stable distribution degree of the corner point.

2. The method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data according to claim 1, characterized in that: The method for obtaining the degree of obviousness is: Obtaining the number of images in which the corner point exists in different scale transformed images corresponding to the tibia CT slice as a first number; The ratio of the first number to the total number of all images transformed at different scales corresponding to the tibia CT slice is taken as the conspicuity of the corner point.

3. The method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data according to claim 1, characterized in that: The method for obtaining the distribution characteristic value is: For any scale image in the different scale transformation images corresponding to the tibia CT slice, the corner point corresponding to the corner point in the scale image is used as the target corner point, and a local area of ​​the target corner point is constructed with the target corner point as the center and a preset length as the radius; The ratio of the number of corner points in the local area to the area of ​​the local area is used as the density distribution degree of the corner points in the scale image; For any edge line passing through the target corner point, the ratio of the number of corner points on the edge line to the number of all pixel points on the edge line is used as the first eigenvalue of the edge line; The sum of the first eigenvalues ​​of all edge lines passing through the target corner point is used as the position analysis value of the corner point in the scale image; The product of the density distribution degree of the corner point in the scale image and the position analysis value is used as the overall reference value of the corner point in the scale image; The overall reference values ​​of the corner point in all the different scale transformation images corresponding to the tibia CT slice are added, and the negative correlation and normalization results are taken as the distribution characteristic value of the corner point.

4. The method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data according to claim 1, characterized in that: The method for obtaining the matching degree is: For any historical patient and any label, use any labeled tibial CT slice of the current patient as the first image, and any labeled tibial CT slice of the historical patient as the second image; For any scale, the corner points in the first image that exist in the image corresponding to the first image after the scale transformation are all taken as first corner points, and the corner points in the second image that exist in the image corresponding to the second image after the scale transformation are all taken as second corner points; Matching pairs obtained by matching the first corner point with the second corner point are all used as reference matching pairs; For any reference matching pair, the difference in the structural feature indexes of the two corner points in the reference matching pair is negatively correlated and normalized, and the result is used as the matching analysis value of the reference matching pair; The sum of the matching analysis values ​​of all reference matching pairs is used as the reference matching value of any numbered tibial CT slice of the current patient and the historical patient under the scale transformation; Obtain reference matching values ​​of the current patient and any of the labeled tibial CT slices of the historical patient under each different scale transformation, and use the maximum reference matching value as the matching degree between the current patient and any of the labeled tibial CT slices of the historical patient.

5. The method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data according to claim 1, characterized in that: The method for obtaining the type of each corner point in each tibial CT slice of the current patient is: For any corner point in any tibial CT slice of the current patient, when the structural characteristic index of the corner point is greater than the preset structural characteristic index threshold and the stable distribution degree is greater than the preset stable distribution degree threshold, the type of the corner point is a normal part of the tibial contour; When the structural characteristic index of the corner point is greater than the preset structural characteristic index threshold, and the stable distribution degree is less than or equal to the preset stable distribution degree threshold, the type of the corner point is a diseased abnormal part of the tibial contour; When the structural characteristic index of the corner point is less than or equal to the preset structural characteristic index threshold, and the stable distribution degree is greater than the preset stable distribution degree threshold, the type of the corner point is a blood vessel in the tissue; When the structural feature index of the corner point is less than or equal to a preset structural feature index threshold and the stable distribution degree is less than or equal to a preset stable distribution degree threshold, the type of the corner point is an interference point.

6. The method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data according to claim 1, characterized in that: The method for constructing the current patient's tibial osteotomy three-dimensional model is: The corner points in different tibial CT slices of the current patient are matched according to the types of corner points, and the matched corner points are used as the center points of the quadtree to divide the voxel blocks to construct the tibial osteotomy three-dimensional model of the current patient.

7. The method for generating a personalized tibial osteotomy three-dimensional model based on CT scan data according to claim 1, characterized in that: The method for acquiring the corner points is: acquiring the corner points in the tibial CT slices by using the SIFT corner point detection algorithm.

Images