A cbct feature extraction method for alveolar bone bone density evaluation

Abstract

The present application relates to the technical field of medical auxiliary diagnosis, in particular to a CBCT feature extraction method for alveolar bone bone density evaluation. The present application is based on the difference of absorption degradation significance of different sub-blocks, combines sub-blocks in alveolar bone blocks, generates different connection blocks, and selects lesion blocks; according to the boundary clarity degree of all lesion blocks in the alveolar bone blocks and the lesion degree difference of different sub-blocks in them, the lesion activity degree is obtained; according to the size and fluctuation degree of absorption degradation significance of sub-blocks of alveolar bone blocks in different preset directions, the bone density spatial dispersion degree is obtained; according to the lesion activity degree, the bone density spatial dispersion degree and the correlation degree of the two of all alveolar bone blocks in the scanning time window, the bone pathological risk degree is obtained. The present application improves the reliability of alveolar bone bone density evaluation by improving the analysis level of CBCT image from morphological observation to pathological function inference.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical auxiliary diagnosis, and particularly relates to a CBCT feature extraction method for alveolar bone bone density evaluation. BACKGROUND

[0002] In dental clinical practice, accurate evaluation of alveolar bone bone density is a key basis for developing programs such as dental implantation, orthodontic treatment, and periodontal disease diagnosis and treatment. Cone beam computed tomography (CBCT) has the characteristics of flexible scanning range, low radiation dose, and high spatial resolution, and can provide three-dimensional alveolar bone structure information, and has become an important imaging means for alveolar bone evaluation.

[0003] Existing CBCT-based bone density feature evaluation methods are mostly limited to basic morphological parameters such as gray value and volume; however, single gray value or morphological parameter has weak correlation with pathology and is easily disturbed by CBCT imaging noise, and it is difficult to sensitively reflect specific pathological changes such as progressive bone resorption and trabecular microarchitecture degradation of alveolar bone, which causes these information to be submerged by imaging noise in the feature extraction process, significantly reducing the reliability of CBCT features for alveolar bone bone density evaluation. SUMMARY

[0004] In order to solve the technical problem that the correlation between morphological parameters and pathology is weak and the microstructure features are distorted, resulting in poor reliability of CBCT features for alveolar bone bone density evaluation, the purpose of the present application is to provide a CBCT feature extraction method for alveolar bone bone density evaluation, and the technical solution adopted is as follows:

[0005] The present application provides a CBCT feature extraction method for alveolar bone bone density evaluation, which comprises:

[0006] Obtaining alveolar bone blocks of a tooth site to be analyzed at each time point within a scanning time window;

[0007] Dividing the alveolar bone blocks into different sub-blocks, obtaining the absorption degradation significance of the sub-blocks, merging the sub-blocks in the alveolar bone blocks based on the differences in the absorption degradation significance of the different sub-blocks, generating different connected blocks, and selecting a lesion block;

[0008] According to the boundary clarity of all lesion blocks in the alveolar bone blocks and the difference in the lesion degree of different sub-blocks therein, obtaining a lesion activity degree;

[0009] According to the size and fluctuation degree of the absorption degradation significance of the sub-blocks of the alveolar bone blocks in different preset directions, obtaining a bone density spatial dispersion degree;

[0010] According to the lesion activity degree, the bone density spatial dispersion degree and the correlation degree of the two, the bone pathological risk degree is obtained.

[0011] Further, the lesion activity degree comprises:

[0012] The variance and the range of the absorption degradation significance of all sub-blocks in each lesion block are calculated respectively, and the product of the variance and the range is taken as the lesion internal heterogeneity;

[0013] According to the difference of the absorption degradation significance of the sub-blocks at the boundary position in each lesion block and the adjacent sub-blocks in the non-lesion connected block, the lesion boundary definition is obtained.

[0014] According to the lesion internal heterogeneity and the lesion boundary definition of all sub-blocks in the alveolar bone block, the lesion activity degree is obtained.

[0015] Further, the lesion boundary definition comprises:

[0016] The sub-blocks in the remaining connected blocks in the alveolar bone block except the lesion blocks are recorded as non-lesion sub-blocks; a first boundary block is selected from the sub-blocks of each lesion block, and at least one non-lesion sub-block exists in the adjacent sub-blocks of the first boundary block;

[0017] The absolute value of the difference of the absorption degradation significance of each first boundary block and all non-lesion blocks adjacent thereto is averaged to obtain the local definition of each first boundary block.

[0018] The average of the local definition of all first boundary blocks in each lesion block is taken as the boundary definition of each lesion block.

[0019] Further, the lesion activity degree comprises:

[0020] According to the lesion internal heterogeneity and the lesion boundary definition of each lesion block, the local activity degree of the corresponding lesion block is obtained.

[0021] The ratio of the number of sub-blocks in each lesion block in the alveolar bone block to the total number of sub-blocks in all lesion blocks is recorded as the lesion weight; the local activity degrees of all lesion blocks in the alveolar bone block are weighted and summed according to the lesion weight to obtain the lesion activity degree of the alveolar bone block.

[0022] Further, the bone density spatial dispersion degree comprises:

[0023] A second boundary block is selected from the sub-blocks of the alveolar bone block, and the edge voxel points of the alveolar bone block are located in the second boundary block.

[0024] For each second boundary block in each preset direction, calculate the mean and variance of the absorption degradation significance of all sub-blocks in each second boundary block in each preset direction, and take the product of the mean and the variance as the local dispersion of each second boundary block in each preset direction.

[0025] Calculate the mean of the local dispersion of all second boundary blocks in all preset directions, and normalize the mean to obtain the bone density spatial dispersion of the alveolar bone block.

[0026] Further, the bone pathology risk degree is obtained by:

[0027] Arrange the bone density spatial dispersion and the lesion activity of the alveolar bone block at all time points in the scanning time window in time sequence to obtain a spatial dispersion sequence and a lesion activity sequence, and obtain the correlation coefficient between the spatial dispersion sequence and the lesion activity sequence.

[0028] Calculate the overall dispersion and the overall activity by averaging the bone density spatial dispersion and the lesion activity of the alveolar bone block at all time points in the scanning time window.

[0029] Adjust the overall dispersion and the overall activity using the correlation coefficient to obtain the bone pathology risk degree.

[0030] Further, the bone pathology risk degree is a weighted result of the sum of the overall dispersion and the overall activity using the sum of the correlation coefficient and a constant 1.

[0031] Further, the generation of different connection blocks and the selection of lesion blocks comprises:

[0032] Cluster all sub-blocks in the alveolar bone block based on the absolute value of the difference between the absorption degradation significance of each two sub-blocks to obtain a plurality of clustering clusters; a plurality of three-dimensional connected regions are formed by adjacent sub-blocks in the same clustering cluster, which are referred to as connection blocks.

[0033] Calculate the mean of the absorption degradation significance of all sub-blocks in the alveolar bone block to obtain a division threshold.

[0034] Calculate the mean of the absorption degradation significance of all sub-blocks in each clustering cluster, and take the connection block corresponding to the clustering cluster whose mean is greater than the division threshold as a lesion block.

[0035] Further, the absorption degradation significance of the sub-block is obtained by:

[0036] Obtain the skewness and kurtosis of the gray value of all voxel points in the sub-block; and take the product of the absolute value of the difference between the kurtosis and a preset normal kurtosis and the skewness as the absorption degradation significance of the sub-block.

[0037] Further, the lesion internal heterogeneity and the lesion boundary definition are positively correlated with the local activity.

[0038] The present application has the following advantages:

[0039] In the embodiment of the present application, the absorption degradation significance, the lesion activity and the bone density spatial dispersion degree are independent of the microstructure of the volatile true structure, the block continuity, the boundary features, the internal heterogeneity and the spatial distribution pattern of the lesion are fused, the biological features highly correlated with the bone absorption activity and the microstructure degradation degree are extracted from the CBCT image, the microstructure feature capture distortion is reduced, and the correlation strength between the CBCT features and the real pathological state is significantly enhanced; the lesion activity and the bone density spatial dispersion degree successively present the bone structure degradation degree of the alveolar bone block and the lesion cell activity, and the correlation degree of the two is combined to analyze the synergy and the mode of the lesion damage, break through the limitation of the traditional morphological parameters, realize the multi-dimensional coupling analysis of the pathological progression and the spatial heterogeneity, and improve the reliability of the bone pathological risk analysis. The present application solves the problem of poor reliability of alveolar bone density evaluation caused by the weakening of the correlation between morphological parameters and pathology and the microstructure feature capture distortion by improving the analysis level of the CBCT image from morphological observation to pathological function inference. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art and the advantages thereof, a brief introduction will be given to the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0041] Figure 1 A step flow chart of a CBCT feature extraction method for alveolar bone density evaluation provided by an embodiment of the present application;

[0042] Figure 2 A flow chart of a method for obtaining lesion activity provided by an embodiment of the present application;

[0043] Figure 3 A computer device schematic diagram of a CBCT feature extraction device for alveolar bone density evaluation provided by an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined inventive objectives, the following describes in detail the specific implementation, structure, features and effects of a CBCT feature extraction method for alveolar bone bone density evaluation according to the present application, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0045] Unless otherwise defined, 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 application belongs.

[0046] The following specifically describes a specific scheme of a CBCT feature extraction method for alveolar bone bone density evaluation provided by the present application in combination with the accompanying drawings.

[0047] Embodiment 1:

[0048] The present application proposes a CBCT feature extraction method for alveolar bone bone density evaluation, please refer to Figure 1 , which shows a step flowchart of a CBCT feature extraction method for alveolar bone bone density evaluation provided by one embodiment of the present application, which includes:

[0049] Step S1: Obtain the alveolar bone block of the tooth site to be analyzed at each time point within the scanning time window.

[0050] Using a cone beam computed tomography (CBCT) device, the alveolar bone CBCT images at different viewing angles at each time point are collected within the scanning time window with a unified scanning protocol. These images can completely capture the anatomical information of the teeth of the tooth site to be analyzed. All alveolar bone CBCT images at the same time point are three-dimensionally reconstructed to obtain a three-dimensional jawbone model at each time point. The tooth site to be analyzed is determined in the three-dimensional jawbone model, and the three-dimensional volume contained by the alveolar crest top from 1 millimeter to 1 millimeter of the root tip crown is taken as the alveolar bone block at each time point. The scanning key parameters include: voltage 80 to 90 kilovolts peak, tube current 4 to 10 milliamperes, voxel size 0.08 to 0.25 millimeters, and scanning field of view diameter 4 to 8 centimeters. In order to reduce motion artifacts, the patient's head is fixed by a positioning device during scanning, so that the occlusal plane is parallel to the horizontal plane.

[0051] In one implementation manner of the embodiment of the present application, the length of the scanning time window is set to 20 seconds, and the time interval between the adjacent two time points is set to 2 seconds, which can be set by the implementer according to the specific situation.

[0052] Step S2: dividing the alveolar bone block into different sub-blocks, obtaining absorption degradation significance of the sub-blocks; based on the difference of absorption degradation significance of different sub-blocks, merging the sub-blocks in the alveolar bone block, generating different connection blocks, and selecting a lesion block.

[0053] The alveolar bone lesion is relatively complex in imaging performance. In order to accurately analyze the alveolar bone density abnormality, the alveolar bone block is divided into sub-blocks. Generally, alveolar bone resorption and micro-architecture disorder and other bone density pathological changes do not exist in isolation, but present a continuous distribution block feature in the form of a lesion, so it is necessary to merge the sub-blocks in the alveolar bone block. The absorption degradation significance reflects the significant degree of bone resorption and microstructure degradation of the sub-block, and presents the local pathological state of the sub-block; based on the difference of absorption degradation significance of different sub-blocks, the block is merged to generate a connection block representing a potential continuous lesion, and the accurate boundary of the lesion is determined, which is crucial for subsequent lesion evaluation. The lesion block represents the alveolar bone density loss lesion.

[0054] In one implementation manner of the embodiment of the present application, the alveolar bone block is uniformly divided into different sub-blocks, and the size of the sub-block is 3 voxels 3 voxels 3 voxels.

[0055] Step S3: obtaining lesion activity degree according to the boundary clear degree of all lesion blocks in the alveolar bone block and the lesion degree difference of different sub-blocks in the alveolar bone block.

[0056] Significant heterogeneity often exists inside the alveolar bone lesion, which is related to the progression stage of the lesion. Specifically, the alveolar bone resorption of the active lesion progression period spreads from the local to the surrounding, resulting in a larger lesion degree difference inside the lesion; the alveolar bone resorption of the stable period stops, and the pathological state of the whole lesion tends to be stable, resulting in a smaller lesion degree difference inside the lesion. At the same time, the boundary between the active lesion progression period alveolar bone lesion and healthy tissue has the "steep transition" feature, while the boundary of the stable period alveolar bone lesion presents a gentle transition. By comprehensively analyzing the lesion degree difference of different sub-blocks in the lesion block in the alveolar bone block, the boundary clear degree of the lesion block, and the possibility of the lesion corresponding to the active lesion progression period, the lesion activity degree is obtained.

[0057] Step S4: obtaining bone density spatial dispersion degree according to the size and fluctuation degree of absorption degradation significance of the sub-blocks of the alveolar bone block in different preset directions.

[0058] The pathological changes of alveolar bone resorption, microstructure degradation, etc. often start locally, forming scattered lesions interwoven with healthy bone, and the core space features of the lesions present a sudden change between healthy tissue and lesions, making the absorption degradation significance of sub-blocks in multiple preset directions higher and changing dramatically. However, the bone density distribution of healthy alveolar bone in each preset direction is relatively uniform, making the absorption degradation significance of sub-blocks in each preset direction lower and consistent. Therefore, the size and fluctuation degree of the absorption degradation significance of sub-blocks in the preset direction can be combined to obtain the bone density spatial dispersion.

[0059] Step S5: According to the lesion activity degree, the bone density spatial dispersion, and the correlation degree of the two of all alveolar bone blocks in the scanning time window, the bone quality pathological risk degree is obtained.

[0060] The lesion activity degree and the bone density spatial dispersion present the bone quality structure degradation degree and the lesion cell activity of the alveolar bone block, respectively. The combination of the two can analyze the basic risk level of the alveolar bone quality density pathology. In combination with the correlation degree of the lesion activity degree and the bone density spatial dispersion, the cooperativity and mode of lesion destruction can distinguish the different pathological states of the alveolar bone quality density, and realize more accurate bone quality pathological risk degree analysis.

[0061] Preferably, in some possible implementation manners of the embodiment of the present application, the absorption degradation significance acquisition method comprises: obtaining the skewness and kurtosis of the gray value of all voxel points in the sub-block; and taking the product of the absolute value of the difference between the kurtosis and the preset normal kurtosis and the skewness as the absorption degradation significance of the sub-block.

[0062] It should be noted that the core pathological feature of the degree of early alveolar bone resorption or bone density loss is local mineral loss. The gray value of the voxel point reflects the attenuation degree of the position to the X-ray. The higher the mineral content in the bone tissue, the stronger the X-ray attenuation, and the weaker the signal received by the detector. Therefore, the gray value of the CBCT image is positively correlated with the bone tissue mineral content, and the gray distribution change can reflect the abnormal bone density caused by early bone resorption.

[0063] The trabecular arrangement of the alveolar bone is regular, the mineral distribution is uniform, and the gray scale distribution is approximately normally distributed. However, local mineral loss caused by bone resorption causes an increase in low gray value voxels, showing right skewness, and bone structure degradation of the alveolar bone leads to more dispersed bone density distribution or abnormal sharp peaks due to microcystic areas, showing reduced or increased kurtosis. Therefore, the greater the skewness, the higher the proportion of low gray value voxels in the sub-block, and the more significant the local bone resorption of the sub-block; the greater the difference between the kurtosis and the preset normal kurtosis, the more disordered the local microstructure of the alveolar bone. In this embodiment, the preset normal kurtosis is set to 3 because the kurtosis of the normal distribution is 3. The greater the absorption degradation significance, the more obvious the right skewness and kurtosis abnormality of the gray scale distribution of the sub-block, and the more significant the bone resorption and microstructure degradation of the sub-block.

[0064] Preferably, in some possible implementation manners of the embodiment of the present application, the selection method of the lesion block comprises: clustering all the sub-blocks in the alveolar bone block based on the absolute value of the difference between the absorption degradation significances of each two sub-blocks to obtain a plurality of clustering clusters; forming a plurality of three-dimensional connected regions from adjacent sub-blocks in the same clustering cluster, denoted as connected blocks; averaging the absorption degradation significances of all the sub-blocks in the alveolar bone block to obtain a division threshold; calculating the mean value of the absorption degradation significances of all the sub-blocks in each clustering cluster, and taking the connected block corresponding to the clustering cluster with the mean value greater than the division threshold as the lesion block.

[0065] It should be noted that the clustering only considers the similarity of the features, however, the lesion is usually continuous, and the construction of the connected unit introduces the spatial continuity constraint, so that the connected block is more consistent with the real lesion morphology. The division threshold is the overall normal level of the absorption degradation significances of all the sub-blocks, and the greater the connected block corresponding to the clustering cluster with the mean value greater than the division threshold, the greater the possibility of being a lesion, and the connected block is taken as the lesion block. In the embodiment of the present application, the sub-blocks within the 6-adjacent range of each sub-block are recorded as the adjacent sub-blocks of the sub-block, that is, each sub-block shares a complete face with its adjacent sub-blocks, or the sub-blocks within the 18-adjacent range.

[0066] In one implementation manner of the embodiment of the present application, the K-means clustering algorithm is used to cluster the sub-blocks in the alveolar bone block; wherein the K value is determined by the elbow method; and the absolute value of the difference between the absorption degradation significances of two sub-blocks corresponds to the distance.

[0067] Preferably, in some possible implementation manners of the embodiment of the present application, the acquisition method of the lesion activity degree is described in Figure 2 which shows a flowchart of a method for acquiring a lesion activity degree according to an embodiment of the present application, and the method comprises:

[0068] Step S310: Calculate the variance and range of the absorption and degradation significance of all sub-blocks in each lesion block, and take the product of the variance and the range as the lesion internal heterogeneity.

[0069] It should be noted that, since the pathological severity of the active lesion progression period lesion gradually decreases from the center to the edge, the internal pathology of the stable period lesion tends to be stable, and the absorption and degradation significance presents the local pathological state of the sub-block, the difference in absorption and degradation significance of different sub-blocks in the active lesion progression period lesion is larger, and the difference in absorption and degradation significance of different sub-blocks in the stable period lesion is smaller. When the variance is larger, it indicates that the difference in pathological state of different sub-blocks in the lesion block is more significant. The range directly reflects the "gradient span" of the internal bone density loss of the lesion, which is a key quantitative index of the imbalance of lesion progression; when the range is larger, it indicates that the difference in pathological degree inside the lesion block corresponding to the lesion is more significant. Therefore, the variance and the range are positively correlated with the lesion internal heterogeneity. If the lesion internal heterogeneity is larger, it indicates that there is a significant pathological gradient inside the lesion block corresponding to the lesion, and the possibility of the lesion being in the active lesion progression period is greater; otherwise, the lesion degree inside the lesion tends to be consistent, and the possibility of the lesion being in the stable period is greater.

[0070] Step S320: Obtain the lesion boundary definition according to the difference in absorption and degradation significance of the sub-blocks at the boundary position in each lesion block and the adjacent sub-blocks in the non-lesion connection block.

[0071] Preferably, in some possible implementation manners of the embodiment of the present application, the method for obtaining the lesion boundary definition comprises: recording the sub-blocks in the alveolar bone block except the lesion block as non-lesion sub-blocks; selecting a first boundary block from the sub-blocks of each lesion block, and there is at least one non-lesion sub-block in the adjacent sub-blocks of the first boundary block; averaging the absolute value of the difference in absorption and degradation significance between each first boundary block and all non-lesion blocks adjacent thereto to obtain the local definition of each first boundary block; and taking the average of the local definition of all first boundary blocks in each lesion block as the boundary definition of each lesion block.

[0072] It should be noted that the boundary of the lesion progression period alveolar bone lesion and the healthy tissue has a "steep transition" feature, and the absorption degradation degree decreases rapidly and stably from the lesion tissue of the lesion to the healthy tissue. The boundary of the stable period alveolar bone lesion presents a gentle transition, and the absorption degradation degree of the sub-block at the edge of the lesion gradually changes. The local clarity presents the local boundary gradient of the lesion block corresponding to the lesion, the complete boundary gradient of the lesion is analyzed by comprehensively analyzing the local clarity of all boundary sub-blocks in the lesion block, and the boundary clarity is obtained. When the boundary clarity is greater, it indicates that the heterogeneity difference of the lesion inside the lesion block corresponding to the lesion boundary is greater, which means that the boundary of the lesion and the healthy tissue is clearer, and the possibility that the lesion is in the active lesion progression period is greater.

[0073] Step S330: obtaining the lesion activity degree according to the lesion inside heterogeneity and the boundary clarity of all sub-blocks in the alveolar bone block.

[0074] Preferably, in some possible implementation manners of the embodiment of the present application, the method for obtaining the lesion activity degree comprises: obtaining the local activity degree of each lesion block according to the lesion inside heterogeneity and the lesion boundary clarity of each lesion block; taking the ratio of the number of sub-blocks in each lesion block in the alveolar bone block to the total number of sub-blocks in all lesion blocks as the lesion weight; and obtaining the lesion activity degree of the alveolar bone block by weighted summation of the local activity degrees of all lesion blocks in the alveolar bone block according to the lesion weight.

[0075] It should be noted that the greater the lesion inside heterogeneity and the lesion boundary clarity, the greater the possibility that the lesion corresponding to the lesion block is in the active lesion progression period. Therefore, the lesion inside heterogeneity and the lesion boundary clarity are positively correlated with the local activity degree. In the embodiment of the present application, the product of the lesion inside heterogeneity and the lesion boundary clarity of each lesion block is normalized to obtain the local activity degree. The normalization processing can be performed by using the maximum-minimum normalization, or other normalization methods such as Sigmoid function, function transformation, maximum-minimum normalization, which are not limited herein.

[0076] In one specific implementation manner of the embodiment of the present application, the lesion activity degree is expressed by the following formula:

[0077]

[0078] In the formula, is the lesion activity degree of the alveolar bone block; K is the total number of lesion blocks in the alveolar bone block; is the number of sub-blocks in the kth lesion block in the alveolar bone block; is the total number of sub-blocks in all lesion blocks in the alveolar bone block; is the lesion weight of the kth lesion block in the alveolar bone block; Local activity degree of the kth lesion block in the alveolar bone block.

[0079] Preferably, in some possible implementation manners of the embodiment of the present application, the method for obtaining the bone density spatial dispersion degree comprises: selecting a second boundary block from a sub-block of the alveolar bone block, and the edge voxel point of the alveolar bone block is located in the second boundary block; calculating the mean value and the variance of the absorption degradation significance of all the sub-blocks for each sub-block in each preset direction of each second boundary block in the alveolar bone block, and taking the product of the mean value and the variance as the local dispersion degree of each second boundary block in each preset direction; and calculating the mean value of the local dispersion degrees of all the second boundary blocks in all the preset directions in the alveolar bone block, and performing normalization processing on the mean value to obtain the bone density spatial dispersion degree of the alveolar bone block.

[0080] It should be noted that for each sub-block in each preset direction of each second boundary block in the alveolar bone block, the center voxel point of the sub-block is located on a straight line in the preset direction passing through the center voxel point of the second boundary block. The bone density distribution of the healthy alveolar bone is relatively uniform in each preset direction, so that the absorption degradation significance of the sub-blocks in each preset direction is relatively low and consistent, while the alveolar bone with lesions has a large number of small lesions, so that the absorption degradation significance of the sub-blocks in multiple preset directions is relatively high and changes sharply. If the mean value and the variance are smaller, it indicates that the dispersion degree of the absorption degradation significance of the sub-blocks in the preset direction of the second boundary block is smaller, so that the local dispersion degree is smaller, and the possibility that the sub-blocks in the preset direction of the second boundary block belong to the healthy alveolar bone is greater. By averaging the local dispersion degrees of all the second boundary blocks in all the preset directions in the alveolar bone block, the bone density spatial dispersion degree describing the distribution of the pathological state in the entire alveolar bone block is obtained, which directly reflects the pathological degradation of the overall distribution of the alveolar bone block. The greater the bone density spatial dispersion degree of the alveolar bone block, the more dispersed the small lesions in the alveolar bone block, and the more serious the degradation of the bone structure.

[0081] In one specific implementation manner of the embodiment of the present application, the bone density spatial dispersion degree SDI of the alveolar bone block is expressed by the formula: ; in the formula, M is the number of the second boundary blocks in the alveolar bone block; G is the number of the preset directions; is the local dispersion degree of the mth second boundary block in the alveolar bone block in the gth preset direction; and Norm is a normalization function.

[0082] In one implementation manner of the embodiment of the present application, the preset directions include the vertical direction from the alveolar crest to the root tip and the mesial-distal horizontal direction.

[0083] Preferably, in some possible implementation manners of the embodiment of the present application, the method for obtaining the alveolar bone pathological risk degree comprises: arranging the spatial dispersion degree of the bone density of the alveolar bone block and the lesion activity degree at all time points in the scanning time window in time sequence to sequentially obtain a spatial dispersion sequence and a lesion activity sequence, and obtaining a correlation coefficient between the spatial dispersion sequence and the lesion activity sequence; averaging the spatial dispersion degree of the bone density of the alveolar bone block and the lesion activity degree at all time points in the scanning time window to sequentially obtain an overall dispersion degree and an overall activity degree; and adjusting the overall dispersion degree and the overall activity degree by using the correlation coefficient to obtain the alveolar bone pathological risk degree.

[0084] It should be noted that when the correlation coefficient is closer to 1, the spatial dispersion degree of the bone density and the lesion activity degree increase synchronously, that is, the lesions of the alveolar bone block are more dispersed and the lesions are more active, which corresponds to "extensive active bone absorption" in pathology, bone absorption is started from multiple sites at the same time and is in the progress stage, the bone density loss has the characteristics of "wide range and fast speed", and the risk shows a synergistic additive effect. When the correlation coefficient is close to 0, it indicates that the global and local characteristics of the alveolar bone block are not synchronized, and the risk is mainly dominated by a single dimension, without the need for synergistic amplification. When the correlation coefficient is close to -1, it indicates that the increase in the spatial dispersion degree of the bone density and the decrease in the lesion activity degree are synchronous, that is, the lesions of the alveolar bone block are more dispersed and stable, which corresponds to "multiple small stable lesions" in pathology, bone absorption has stopped, and only scattered old lesions are left, and the risk shows a decay effect. If the overall dispersion degree and the overall activity degree are greater, the bone structure of the alveolar bone block in the scanning time window is more seriously deteriorated and the lesion cell activity is stronger, the bone structure and the biological destruction are more serious, and the two represent the basic risk level of the alveolar bone pathological density. By adjusting using the correlation coefficient, more accurate alveolar bone pathological risk degree analysis can be achieved.

[0085] In the embodiment of the present application, the sum of the overall dispersion degree and the overall activity degree is weighted by using the sum of the correlation coefficient and the constant 1 to obtain the alveolar bone pathological risk degree. If the alveolar bone pathological risk degree is greater, it indicates that the overall risk of the alveolar bone density loss is higher, and the bone health status is worse.

[0086] In one implementation manner of the embodiment of the present application, the correlation coefficient refers to a Pearson correlation coefficient.

[0087] In the embodiment of the present application, the alveolar bone pathological risk degree of the tooth site to be analyzed is input into a pre-trained neural network, the neural network has been trained using a large amount of labeled clinical data, for example, bone density categories such as normal bone, mild osteoporosis, and severe osteoporosis are labeled, to learn the complex mapping relationship between the alveolar bone pathological risk degree and the bone density category, and the neural network outputs the bone density classification result of the alveolar bone of the tooth site to be analyzed.

[0088] The classification result of the scheme is an objective feature labeling result generated based on big data analysis, does not directly provide a diagnosis conclusion, but provides an objective quantitative data reference for a doctor, enables the doctor to focus on the pathological features of the alveolar bone more quickly, improves the recognition efficiency of the doctor on the alveolar bone density classification result, and finally the medical judgment still needs to be completed by a professional doctor.

[0089] Up to now, the present application is completed.

[0090] Embodiment 2:

[0091] The present application also provides a computer device schematic diagram of a CBCT feature extraction device for alveolar bone density evaluation, please refer to Figure 3 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 the processor 602 executes the computer program 603, so that the computer device can execute any one of the foregoing introduced CBCT feature extraction methods for alveolar bone density evaluation.

[0092] In addition, the present application embodiment also protects a device, which can include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute the CBCT feature extraction method for alveolar bone density evaluation provided by the present application embodiment.

[0093] The present embodiment can divide the device into functional modules according to the above-mentioned method examples, for example, each functional module can be corresponding, or two or more functions can be integrated in one processing module, and the integrated module can be realized in the form of hardware. It should be noted that the division of modules in the present embodiment is illustrative, and is only a logical function division, and another division mode can be used in actual implementation.

[0094] In the case of dividing each module corresponding to each function, the device can also include a communication module, a signal analysis module, a complexity analysis module, and a positioning module, etc. It should be noted that all related contents of each step involved in the above method embodiment can be referred to the function description of the corresponding functional module, and will not be repeated here.

[0095] It should be understood that the device provided by the present embodiment is used to execute the above-mentioned CBCT feature extraction method for alveolar bone density evaluation, so as to achieve the same effect as the above-mentioned implementation method.

[0096] In the case of employing the integrated unit, the device can include a processing module, a storage module. Wherein, when the device is applied to the equipment, the processing module can be used to control and manage the actions of the equipment. The storage module can be used to support the equipment to execute the mutual program code and the like.

[0097] Wherein, the processing module can be a processor or a controller, which can realize or execute various exemplary logical blocks, modules and circuits contained in combination with the disclosure of the present application. The processor can also be a combination of realizing computing functions, such as including one or more microprocessor combinations, a combination of digital signal processing (Digital Signal Processing, DSP) and microprocessor, and the like. The storage module can be a memory.

[0098] Embodiment 3:

[0099] The embodiment also provides a computer readable storage medium, which stores computer program codes, when the computer program codes run on the computer, the computer executes the above-mentioned related method steps to realize the CBCT feature extraction method for alveolar bone bone density evaluation provided by the above-mentioned embodiment.

[0100] Wherein, the device and the computer readable storage medium provided by the embodiment are used to execute the corresponding method provided above, and thus the beneficial effects that can be achieved are referred to the beneficial effects in the corresponding method provided above, which will not be described here.

[0101] In the embodiments provided by the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiment described above is only illustrative, and the division of the modules or units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed each other can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0102] It should be noted that: the above-mentioned sequence of the embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0103] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

Claims

1. A CBCT feature extraction method for alveolar bone mineral density assessment, characterized in that, The method includes: Obtain alveolar bone blocks of the tooth to be analyzed at various time points within the scanning time window; The alveolar bone block is divided into different sub-blocks, and the resorption and degradation significance of the sub-blocks is obtained; based on the difference in the resorption and degradation significance of the different sub-blocks, the sub-blocks in the alveolar bone block are merged to generate different connecting blocks, and disease blocks are selected. The activity of lesions is obtained by considering the clarity of the boundaries of all lesion blocks in the alveolar bone region and the differences in the severity of lesions among different sub-blocks within them. Based on the magnitude and fluctuation of the absorption and degradation significance of sub-blocks in different preset directions of alveolar bone blocks, the spatial dispersion of bone density is obtained; The bone pathological risk level is obtained based on the lesion activity, bone density spatial dispersion, and correlation between the two in all alveolar bone blocks within the scanning time window. The acquisition of bone pathological risk includes: The spatial dispersion of bone density and the lesion activity of alveolar bone blocks at all time points within the scanning time window are arranged in chronological order to obtain spatial discrete sequence and lesion activity sequence, and the correlation coefficient between the spatial discrete sequence and the lesion activity sequence is obtained. The spatial dispersion of bone density and the activity of lesions in the alveolar bone block at all time points within the scanning time window are averaged to obtain the overall dispersion and overall activity. By using the correlation coefficient, the overall dispersion and the overall activity are adjusted to obtain the bone pathology risk score; The bone pathology risk score is a weighted result of the sum of the overall dispersion and the overall activity, using the sum of the correlation coefficient and the constant 1.

2. The CBCT feature extraction method for alveolar bone mineral density assessment according to claim 1, characterized in that, The acquisition of lesion activity includes: Calculate the variance and range of the absorption and degradation significance of all sub-blocks within each lesion block, and use the product of the variance and the range as the intralesion heterogeneity. The clarity of the lesion boundary is obtained based on the difference in the significance of absorption and degradation between the sub-blocks located at the boundary position within each lesion block and the adjacent sub-blocks within the non-lesion connecting block. The lesion activity is obtained based on the internal heterogeneity of the lesion in all sub-blocks of the alveolar bone block and the clarity of the lesion boundary.

3. The CBCT feature extraction method for alveolar bone mineral density assessment according to claim 2, characterized in that, The acquisition of lesion boundary clarity includes: The sub-blocks within the connecting blocks of the alveolar bone block, excluding the diseased block, are denoted as non-disease sub-blocks; a first boundary block is selected from the sub-blocks of each diseased block, and at least one of the non-disease sub-blocks exists among the adjacent sub-blocks of the first boundary block; The local clarity of each first boundary block is obtained by averaging the absolute values ​​of the differences in the absorption and degradation significance between each first boundary block and all adjacent non-lesion blocks. The average local sharpness of all first boundary blocks within each lesion block is taken as the boundary sharpness of each lesion block.

4. The CBCT feature extraction method for alveolar bone mineral density assessment according to claim 2, characterized in that, The acquisition of lesion activity includes: The local activity of the corresponding lesion block is obtained based on the internal heterogeneity and the boundary clarity of each lesion block. The ratio of the number of sub-blocks in each lesion block in the alveolar bone block to the total number of sub-blocks in all lesion blocks is recorded as the lesion weight; the local activity of all lesion blocks in the alveolar bone block is weighted and summed according to the lesion weight to obtain the lesion activity of the alveolar bone block.

5. The CBCT feature extraction method for alveolar bone mineral density assessment according to claim 1, characterized in that, The acquisition of bone mineral density spatial dispersion includes: A second boundary block is selected from the sub-blocks of the alveolar bone block, and the edge voxel points of the alveolar bone block are located in the second boundary block; For each sub-block of the alveolar bone block located in each second boundary block in each preset direction, calculate the mean and variance of the significance of absorption and degradation of all sub-blocks respectively, and use the product of the mean and the variance as the local dispersion of each second boundary block in each preset direction. Calculate the mean of the local dispersion of all second boundary blocks in the alveolar bone block in all preset directions, and normalize the mean to obtain the spatial dispersion of bone density of the alveolar bone block.

6. The CBCT feature extraction method for alveolar bone mineral density assessment according to claim 1, characterized in that, The generation of different connectivity blocks and the selection of lesion blocks include: Based on the absolute value of the difference in the significance of absorption and degradation between every two sub-blocks, all sub-blocks in the alveolar bone block are clustered to obtain several clusters; several three-dimensional connected regions are formed by adjacent sub-blocks within the same cluster, denoted as connecting blocks. The average of the resorption and degradation significance of all sub-regions within the alveolar bone block is used to obtain the segmentation threshold; Calculate the mean of the absorption degradation significance of all sub-blocks within each cluster, and identify the connected blocks of clusters whose mean is greater than the partition threshold as lesion blocks.

7. The CBCT feature extraction method for alveolar bone mineral density assessment according to claim 1, characterized in that, The acquisition of the absorption degradation significance of the sub-block includes: Obtain the skewness and kurtosis of the gray values ​​of all voxels within the sub-block; multiply the absolute value of the difference between the kurtosis and the preset normal kurtosis and the skewness as the absorption degradation saliency of the sub-block.

8. A CBCT feature extraction method for alveolar bone mineral density assessment according to claim 4, characterized in that, The heterogeneity within the lesion and the clarity of the lesion boundary are both positively correlated with the local activity.

Images