Alveolar bone resorption measurement method, system, electronic device and readable storage medium

Abstract

The application provides a method for measuring alveolar bone resorption, comprising: obtaining cone beam CT three-dimensional data of an oral cavity, and determining a tooth region of a target tooth; determining a tooth long axis according to the tooth region; determining a mesiodistal reference axis according to a tangent direction of a dental arch curve at a center of the target tooth; removing a component parallel to the tooth long axis in the tangent direction and unitizing to obtain an orthogonalized mesiodistal reference axis, and unifying a positive direction of the orthogonalized mesiodistal reference axis to a direction from a right side of a patient to a left side; establishing a single-tooth local coordinate system based on the tooth long axis and the orthogonalized mesiodistal reference axis; determining a measuring direction corresponding to at least two tooth surfaces of a mesial surface, a distal surface, a buccal surface and a lingual surface in the coordinate system; determining an enamel cementum junction reference point, an alveolar crest reference point and an apical reference point along each tooth surface measuring direction; and taking a first bone height to first root length ratio parallel to the tooth long axis as a radiological bone loss index of the tooth surface, and the index is a measurement value of the tooth surface alveolar bone resorption degree. The application also provides an alveolar bone resorption measurement system, an electronic device and a readable storage medium.

Description

Technical Field

[0001] This invention relates to a method and system for measuring alveolar bone resorption, and more particularly to a method, system, electronic device, and readable storage medium for measuring alveolar bone resorption. Background Technology

[0002] Alveolar bone resorption alters the height and shape of the bone support surrounding the teeth. The degree of resorption affects tooth stability, restorative design, and the choice of subsequent treatment pathways. Clinically, comparable quantitative results of bone loss need to be provided on imaging, examining both the tooth and its surface.

[0003] Current artificial periodontal probing relies on operator technique, making it difficult to provide millimeter-level or scale-level results that correspond one-to-one with the spatial position of cone-beam computed tomography (CBCT). Panoramic and periapical radiographs are two-dimensional projections, with the buccal and lingual bone walls overlapping with proximal structures. The nominal mesial and distal surfaces of rotated and crowded teeth are more likely to be misaligned with the actual proximal direction.

[0004] On cone-beam computed tomography (CBCT), some methods derive the long axis, mesiodistal axis, and buccal-lingual axis from the three-dimensional morphology of a single tooth, and then set up multiple measurement planes. Other methods utilize the boundaries of adjacent teeth to create proximal measurement planes. In these approaches, the mesiodistal axis still originates from the tooth's own morphology. When teeth are rotated, tilted, or crowded, the morphological axis deviates from the direction of proximal junctions, and the nominal mesiodistal and distal surfaces fall onto the buccal or lingual side. The buccal-lingual division also shifts accordingly. Consequently, the surface-level results for different teeth do not match.

[0005] Another method involves taking two feature points on the largest buccal-lingual cross-section of a single tooth and calculating the planar distance to determine the presence or absence of bone dehiscence. This method does not provide tooth surface grade indicators for consistency in the mesial, distal, buccal, and lingual directions.

[0006] The current methods for measuring alveolar bone resorption, including its application to the tooth surface of rotated and crowded teeth, and its comparability across the entire mouth, still require improvement. Summary of the Invention

[0007] To address one of the aforementioned technical problems, this invention provides a method and system for measuring alveolar bone resorption.

[0008] According to one aspect of the present invention, a method for measuring alveolar bone resorption includes: acquiring three-dimensional volumetric data of an oral cone-beam computed tomography (CBCT) to determine the tooth region of a target tooth; determining the long axis of the tooth based on the tooth region; determining a mesiodistal reference axis based on the tangent direction of the dental arch curve at the center of the target tooth; removing the component parallel to the long axis of the tooth from the tangent direction and normalizing it to obtain an orthogonalized mesiodistal reference axis; unifying the positive direction of the orthogonalized mesiodistal reference axis to point from the right side of the patient to the left side; establishing a single-tooth local coordinate system based on the long axis of the tooth and the orthogonalized mesiodistal reference axis; and determining the mesial and distal surfaces in the single-tooth local coordinate system. Measurement directions corresponding to at least two of the tooth surfaces (facial, buccal, and lingual); determination of a cementoenamel junction reference point, an alveolar ridge reference point, and a periapical reference point along each tooth surface measurement direction; and determination of the distance from the cementoenamel junction reference point to the alveolar ridge reference point, parallel to the tooth's long axis, as a first bone height along each tooth surface measurement direction; determination of the absolute value of the projection of the difference between the periapical reference point and the cementoenamel junction reference point along the tooth's long axis as a first root length; and determination of the ratio of the first bone height to the first root length as a radiographic bone loss index for the corresponding tooth surface, wherein the radiographic bone loss index is a measurement of the degree of alveolar bone resorption on the corresponding tooth surface.

[0009] According to at least one embodiment of the present invention, dental arch curves are extracted for the maxilla and mandible respectively, the three-dimensional center points of the existing teeth are arranged in the order of the dentition, the missing tooth position is filled by interpolation of the center of the adjacent existing teeth, and the dental arch curve is obtained by fitting the spline curve, the nearest point of the target tooth center on the dental arch curve is determined, and the tangent direction at the nearest point is used as the source of the mesiodistal reference direction.

[0010] According to at least one embodiment of the present invention, when the modulus of the tangent direction after removing the component parallel to the tooth long axis is too small to obtain a stable unit vector, the tangent direction is first projected onto a plane perpendicular to the head-to-feet direction, and then the component parallel to the tooth long axis in the projection result is removed and normalized.

[0011] According to at least one embodiment of the present invention, the origin of the single-tooth local coordinate system is taken as the geometric center of the tooth region. The single-tooth local coordinate system takes the orthogonalized mesiodistal reference axis as the first axis and the tooth long axis as the third axis. The positive direction is anatomically downward, with the anatomical downward direction of the maxillary teeth pointing in the opposite direction to the crown direction and the anatomical downward direction of the mandibular teeth pointing in the crown direction. The second axis of the single-tooth local coordinate system is determined by the first axis and the third axis according to the right-hand rule, with the positive direction pointing from the lingual side to the buccal side.

[0012] According to at least one embodiment of the present invention, in a plane perpendicular to the long axis of the tooth, with the orthogonalized mesiodistal reference axis as the angular reference, the circumference is divided into four sectors corresponding to the mesial surface, distal surface, buccal surface and lingual surface, each sector occupying 90°, and the anterior teeth correspond to the buccal surface with the labial side, and the maxillary posterior teeth correspond to the lingual surface with the palatal side.

[0013] According to at least one embodiment of the present invention, a measurement slice is generated that passes through the tooth long axis and forms an angle with the orthogonalized mesiodistal reference axis, the angle being taken at intervals of 15°, 30° or 45°, and the measurement results of the measurement slice are assigned to the corresponding tooth surface according to the sector into which the angle is entered.

[0014] According to at least one embodiment of the present invention, when the first root length is not less than 5 mm, the radiographic bone loss index is expressed as a percentage; when the first root length is less than 5 mm, the first bone height is used as the output result of the corresponding tooth surface, and the root length of the corresponding tooth surface is marked as unreliable.

[0015] According to at least one embodiment of the present invention, the torsion angle between the mesiodistal morphological axis of the tooth itself and the tangent of the dental arch curve is determined, and when the torsion angle exceeds a torsion threshold, the tangent of the dental arch curve is used as the mesiodistal reference axis, wherein the torsion threshold is 15° or 20°.

[0016] According to at least one embodiment of the present invention, the edentulous position is involved in the dental arch curve interpolation, and no radiographic bone loss index is output for the edentulous position, and the implant and residual root are not included in the tangent calculation, or only the crown center is used as the weak control point of the dental arch curve, the weight of the weak control point being one-quarter to one-half of the weight of the normal tooth center.

[0017] According to at least one embodiment of the present invention, the three-dimensional volume data is decompressed and converted into absorption coefficient data, wherein the absorption coefficient is the absorption coefficient of a substance to X-rays. The tooth detection results are mapped back to three-dimensional voxel coordinates according to the dental arch curve parameters to complete tooth numbering and missing tooth identification. A three-dimensional sub-volume containing the target tooth and its adjacent bone tissue is extracted from the three-dimensional volume data according to tooth position. The three-dimensional sub-volume is a three-dimensional region of interest. Tooth instance segmentation is performed on the three-dimensional region of interest. The tooth instance segmentation divides the voxels in the three-dimensional region of interest into background voxels and target tooth voxels. The tooth region is obtained from the target tooth voxels.

[0018] According to at least one embodiment of the present invention, multiple cross sections of the tooth region are extracted along an initial principal axis direction, wherein the initial principal axis is the principal component direction of the tooth region or the orientation direction obtained by tooth segmentation. The cross section located from the crown to the middle of the root shaft and avoiding the irregular area of ​​the crown occlusal surface and the root tip is determined as an effective cross section. The center position of the tooth region within each effective cross section is calculated, and a straight line is fitted to the center position of the tooth region within each effective cross section to obtain the tooth long axis direction.

[0019] According to at least one embodiment of the present invention, radiographic bone loss indices in multiple measurement directions within the same tooth surface are summarized to obtain a summary index for the tooth surface. The summarization is one of the following: after removing the largest and smallest indices within the tooth surface, the maximum value of the remaining indices is taken; the 95th percentile value of each indices within the tooth surface is taken; the median value of each indices within the tooth surface is taken; or the mean value of each indices within the tooth surface is taken.

[0020] According to at least one embodiment of the present invention, radiographic bone loss indicators are output for each tooth and each tooth surface, and severity auxiliary prompts are generated based on a set threshold. The auxiliary prompts are used for radiographic reference and are not used as clinical diagnostic conclusions.

[0021] According to another aspect of the present invention, an alveolar bone resorption measurement system includes: a data acquisition module for acquiring three-dimensional volumetric data of an oral cone-beam computed tomography (CBCT) and determining the tooth region of a target tooth; a tooth long axis determination module for determining the tooth long axis based on the tooth region; a reference axis determination module for determining a mesiodistal reference axis based on the tangent direction of the dental arch curve at the center of the target tooth, removing the component parallel to the tooth long axis in the tangent direction and normalizing it to obtain an orthogonalized mesiodistal reference axis, and unifying the positive direction of the orthogonalized mesiodistal reference axis to point from the patient's right side to the left side; a coordinate system establishment module for establishing a single-tooth local coordinate system based on the tooth long axis and the orthogonalized mesiodistal reference axis; and a tooth surface direction determination module for determining the tooth surface direction based on the tooth long axis and the orthogonalized mesiodistal reference axis. In the local tooth coordinate system, the measurement directions corresponding to at least two of the tooth surfaces (mesial, distal, buccal, and lingual) are determined. A reference point determination module is used to determine the cementoenamel junction reference point, alveolar ridge reference point, and periapical reference point along the measurement directions of each tooth surface. An index calculation module is used to determine the distance from the cementoenamel junction reference point to the alveolar ridge reference point, parallel to the tooth's long axis, as the first bone height; the absolute value of the projection of the difference between the periapical reference point and the cementoenamel junction reference point along the tooth's long axis, as the first root length; and the ratio of the first bone height to the first root length, as the radiographic bone loss index of the corresponding tooth surface. The radiographic bone loss index is a measurement of the degree of alveolar bone resorption on the corresponding tooth surface.

[0022] According to one aspect of the present invention, an electronic device is provided, comprising: a memory storing execution instructions, and a processor executing the execution instructions stored in the memory, such that the processor performs the method as described in any of the preceding claims.

[0023] According to one aspect of the present invention, a readable storage medium is provided, wherein executable instructions are stored therein, which, when executed by a processor, are used to implement the method as described in any of the preceding claims.

[0024] Compared with the prior art, the present invention has the following beneficial effects.

[0025] The mesial-distal reference axis is taken from the tangent of the dental arch curve at the center of the tooth and orthogonalized relative to the tooth's long axis. The positive direction is uniformly from right to left for the patient. Even with rotation, tilt, or crowding, the mesial and distal surfaces remain consistent with the direction of adjacency of the dentition. The buccal-lingual division is also determined by this axis, allowing for comparison of the tooth surface grades of different teeth. Within a single-tooth local coordinate system, the ratio of the first bone height to the first root length is calculated according to the tooth surface measurement direction. This ratio represents the measured degree of alveolar bone resorption on that tooth surface. The measurement occurs in that tooth surface direction, without projecting all three points onto the same common tooth long axis before taking the measurement. Two-segment spacing; edentulous sites participate in arch interpolation, while implants and residual roots are not included in tangent calculations. The arch curve remains continuous at the gap, and the tangent can still be defined at the target tooth position. For indicators in multiple measurement directions within the same tooth surface, the largest and smallest values ​​can be removed and the remaining maximum value can be taken, or the 95th percentile, median, or mean can be taken. Local burrs on a single slice are not easily directly used as the final result for that tooth surface. No indicators are output for edentulous sites and implant sites. When the torsion angle exceeds the threshold, the report indicates that the arch tangent has been used as a mesiodistal reference. Attached Figure Description

[0026] The accompanying drawings illustrate exemplary embodiments of the invention and, together with the description thereof, serve to explain the principles of the invention. These drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification.

[0027] Figure 1 A method for measuring alveolar bone resorption according to an embodiment of the present invention is shown.

[0028] Figure 2 A schematic diagram of the dental arch curve, missing tooth interpolation, and tangent at the center of the tooth is shown according to an embodiment of the present invention.

[0029] Figure 3 A schematic diagram of a local coordinate system for a single tooth is shown according to an embodiment of the present invention.

[0030] Figure 4This illustration shows a comparative view of the tooth surfaces of the same torsion tooth under two references: the mesiodistal morphological axis and the tangent of the dental arch curve, according to an embodiment of the present invention.

[0031] Figure 5 A schematic diagram of a tooth surface sector and a cross-tooth long axis slice is shown according to an embodiment of the present invention.

[0032] Figure 6 A schematic diagram of bone height and axial root length is shown according to one embodiment of the present invention.

[0033] Figure 7 A schematic diagram of an alveolar bone resorption measurement system according to an embodiment of the present invention is shown.

[0034] Figure 8 A schematic diagram of an electronic device according to an embodiment of the present invention is shown. Detailed Implementation

[0035] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present invention are shown in the accompanying drawings.

[0036] It should be noted that, unless otherwise specified, the embodiments and features described in this invention can be combined with each other. The technical solution of this invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0037] Unless otherwise stated, the exemplary embodiments shown are to be understood as providing exemplary features of various details that provide ways in which the technical concept of the invention can be implemented in practice. Therefore, unless otherwise stated, the features of the various embodiments may be additionally combined, separated, interchanged, and rearranged without departing from the technical concept of the invention.

[0038] The terminology used herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms “a” and “the” are intended to include the plural forms as well. Furthermore, when the terms “comprising” and “including” and variations thereof are used in this specification, they indicate the presence of the stated features, steps, operations, and components, but do not exclude the presence or addition of other features, steps, operations, and components.

[0039] According to one embodiment of the present invention, a method for measuring alveolar bone resorption is provided. For example... Figure 1 As shown, the method may include steps 102 to 118.

[0040] In step 102, three-dimensional volumetric data of the oral cavity cone-beam CT is acquired, and the tooth region of the target tooth is determined. The system reads the DICOM sequence, sorts the image sequence according to the image location information, and reads spatial information such as pixel spacing, slice thickness, and image orientation to reconstruct the three-dimensional volumetric data. There are no special restrictions on the model of the acquisition equipment, tube voltage and current parameters, and reconstruction algorithm, as long as it can form three-dimensional volumetric data covering the target dentition region. The DICOM data is decompressed and converted into absorption coefficient data. The absorption coefficient refers to the absorption coefficient of a substance to X-rays. The converted volumetric data maintains the same spatial geometric parameters as the original image.

[0041] One or more of the following can be performed on the volume data: spatial resampling, grayscale truncation, and intensity normalization. In one embodiment, the voxel resolution is 0.25 mm.

[0042] The tooth region describes the three-dimensional spatial extent occupied by a single target tooth, typically represented as a single-tooth binary mask. To determine the tooth region, tooth numbering and missing tooth identification are performed first, followed by the extraction of a three-dimensional region of interest (ROI) based on tooth position. The ROI is a three-dimensional sub-volume containing the target tooth and its adjacent bone tissue. Tooth instance segmentation is then performed on the ROI, dividing the voxels into background voxels and target tooth voxels.

[0043] Based on the parameters of the dental arch curve, a correspondence is established between the detection plane or curved surface layer and the voxel space. The detected tooth center is mapped to three-dimensional coordinates. The same set of dental arch parameters is used for numbering, missing tooth marking, and region of interest (ROI) clipping. A three-dimensional sub-volume containing the target tooth and its adjacent bone tissue is extracted tooth by tooth position. This three-dimensional sub-volume is the three-dimensional ROI. Tooth instance segmentation is performed on the ROI to obtain the tooth region. Segmentation can employ a three-dimensional encoder-decoder structure. The input is single-channel grayscale data, and the output consists of two categories: background and target teeth. Post-processing can retain the largest connected components and remove fragments with excessively small volumes.

[0044] Reference points for the cementoenamel junction, alveolar ridge, and periapical periodontium can be obtained from section examination, thermographic extreme values, manual calibration, or other methods that provide three-dimensional coordinates.

[0045] In step 104, the long axis of the tooth is determined based on the tooth region.

[0046] The long axis of a tooth describes the main extension direction of a single tooth from the crown to the root apex and is used as the third axis z of the local coordinate system. In one embodiment, multiple cross-sections are extracted from the tooth region along the initial principal axis direction, and the center position of the tooth region within each cross-section is calculated. The initial principal axis can be the principal component direction of the tooth region or the orientation direction obtained from tooth segmentation. The cross-section located from the crown to the middle of the root shaft, avoiding the irregular area of ​​the coronal occlusal surface and the root apex, is considered an effective cross-section. The center positions of these effective cross-sections are fitted with linear least squares to obtain the direction of the long axis of the tooth. The fitted direction vector, combined with the anatomical orientation of the maxillary or mandibular tooth, is conventionally aligned with the positive direction of the third axis. The long axis of the tooth is determined by the tooth region of that tooth.

[0047] In step 106, the mesiodistal reference axis is determined based on the tangent direction of the dental arch curve at the center of the target tooth.

[0048] Figure 2 This illustration shows a dental arch curve, edentulous interpolation, and tangent at the center of a tooth according to an embodiment of the present invention. The dental arch curve is extracted separately for the maxilla and mandible. The three-dimensional center points of existing teeth are arranged in dentition order. The edentulous position is filled by interpolation of the centers of adjacent existing teeth. The dental arch curve is then obtained by spline curve fitting; either cubic spline or polynomial fitting is acceptable. The tangent at the nearest point on the dental arch curve to the center of the target tooth serves as the source of the mesiodistal reference direction for that tooth. The center of the tooth can be the geometric center of the tooth region or the crown center; the same center definition is used for the entire mouth. The dentition order can be arranged according to tooth position numbering. For the maxilla, the order is from the third molar on one side through the anterior teeth to the third molar on the opposite side; the mandible is treated similarly.

[0049] Implants and obvious root remnants may not be included in the tangent calculation, or only their crown center may be used as the weak control point of the curve. The weight of the weak control point is lower than that of the center of a normal tooth. The edentulous position participates in the interpolation, but does not output the radiographic bone loss index for that position.

[0050] The nearest point of the target tooth center on the dental arch curve is taken, and the unit tangent vector at this point is used as the initial vector of the mesiodistal reference direction. The direction of this direction is uniformly defined for the whole mouth as pointing from the right side of the patient to the left side.

[0051] In step 108, the component parallel to the tooth long axis in the tangent direction is removed and normalized to obtain the orthogonalized mesiodistal reference axis; in step 110, the positive direction of this axis is unified to point from the patient's right side to the left side; in step 112, a single-tooth local coordinate system is established based on the tooth long axis and the orthogonalized mesiodistal reference axis.

[0052] Figure 3A local coordinate system for a single tooth according to an embodiment of the present invention is shown. Let t be the unit vector of the dental arch tangent, z be the unit vector of the tooth major axis, and z be the third axis. The first axis x is obtained by removing the component parallel to z from t and then normalizing it. The vector after removing the parallel component is orthogonal to z.

[0053] If the modulus is too small after removing the component parallel to the tooth's long axis, resulting in a unstable unit vector, it indicates that the tangent is almost parallel to the tooth's long axis. In this case, first project the tangent onto a plane perpendicular to the cephalic direction, then remove the component parallel to the tooth's long axis and normalize it. The sign of the first axis is corrected to point from the patient's right side to the left. The third axis is along the tooth's long axis, with the positive direction taken anatomically downwards. For maxillary teeth, the anatomical direction points downwards in the opposite direction to the crown direction, and for mandibular teeth, the anatomical direction points downwards in the crown direction. The second axis y is determined by the first axis x and the third axis z according to the right-hand rule. .

[0054] The second axis is oriented from the lingual side to the buccal side, and the sign is corrected according to this direction. The palatal side of the maxilla is the corresponding side of the lingual direction on the maxilla.

[0055] The origin of the coordinate system is taken as the geometric center of the tooth region. In an alternative method, the origin can also be translated to the center of the cementoenamel boundary reference plane. This implementation method takes the geometric center of the tooth region as the main point.

[0056] When calculating bone height and root length, the absolute value of the projection along the long axis of the tooth is taken, and the same formula is used for the maxilla and mandible.

[0057] In step 114, the measurement directions for at least two of the following tooth surfaces—mesian, distal, buccal, and lingual—are determined in the single-tooth local coordinate system. The clinical tooth surfaces are the mesian, distal, buccal, and lingual surfaces.

[0058] Figure 5 The diagram illustrates a tooth surface sector and a cross-section of the tooth's long axis according to an embodiment of the present invention. In the diagram, θ represents the angle between the cross-section and the orthogonalized mesiodistal reference axis. In a plane perpendicular to the tooth's long axis, with the orthogonalized mesiodistal reference axis as the 0° reference, the circumferential direction is divided into sectors corresponding to the mesial, distal, buccal, and lingual surfaces. In one embodiment, each of the four sectors occupies 90°. When the proximal surfaces of the anterior teeth are narrow, the circumferential angles of the mesial and distal sectors can be less than 90°, while the circumferential angles of the labial and lingual sectors can be greater than 90°. The sum of the circumferential angles of the four sectors is 360°. For anterior teeth, the labial side corresponds to the buccal side, and for maxillary posterior teeth, the palatal side corresponds to the lingual side.

[0059] The measurement slice is a plane passing through the long axis of the tooth and forming an angle with the orthogonalized mesiodistal reference axis. The angle is taken at intervals of 15°, 30°, or 45°. Based on the sector into which the angle is located, the measurement results of the slice are assigned to the corresponding tooth surface. Multiple slices can be contained on the same tooth surface.

[0060] One implementation outputs four tooth surfaces: mesial, distal, buccal, and lingual. Alternatively, only the adjacent surfaces or only the buccal and lingual surfaces can be output.

[0061] In step 116, reference points for the cementoenamel junction, alveolar ridge, and apex are determined along the measurement directions of each tooth surface. In one embodiment, the cementoenamel junction and alveolar ridge are determined on two-dimensional slices passing through the long axis of the tooth, and then mapped back to three dimensions. The apex can be determined on three-dimensional volume data. In another embodiment, the dentist marks the above reference points on the tooth surface in a local coordinate system. In yet another embodiment, the reference points are derived from samples taken from a previously obtained local curve.

[0062] When mapping 2D points on a slice back to 3D, the origin of the slice plane and two basis vectors are used. The slice orientation is determined by the tooth's long axis and the included angle. The plane normal is the unit vector obtained by the cross product of the tooth's long axis and the included angle. The two basis vectors in the plane are along the tooth's long axis and the cross product direction, respectively. The resampling grid step size is equal to the voxel resolution. If there are not enough effective slices in a certain tooth surface sector, the tooth surface can be marked as missing, or only the bone height on the existing slices can be output.

[0063] The cementoenamel boundary points obtained from multiple slices within the same tooth surface sector can be connected in a circumferential order to form a local curve of that tooth surface. The local curve is allowed to be broken. The alveolar ridge point can also form a local curve cut along the tooth surface. The apex point is usually one on a single-rooted tooth, while there can be multiple apical reference points on a multi-rooted tooth.

[0064] In step 118, in the local coordinate system of a single tooth, the radiographic bone loss index of the corresponding tooth surface is calculated based on three types of reference points in the measurement direction of each tooth surface.

[0065] Figure 6 Bone height and axial root length are illustrated in one embodiment of the present invention. The bone height, measured along the current tooth surface, from the cementoenamel junction reference point to the alveolar ridge reference point and parallel to the long axis of the tooth, is defined as the first bone height. The absolute value of the projection of the difference between the apical reference point and the cementoenamel junction reference point onto the long axis of the tooth is defined as the first root length. The radiographic bone loss index of this tooth surface is the ratio of the first bone height to the first root length. This ratio is a measurement of the degree of alveolar bone resorption on this tooth surface and does not need to be converted into another resorption amount. The index can be expressed as a percentage.

[0066] The cementoenamel-enamel junction reference point for this tooth surface is: The alveolar ridge reference point is The root apex reference point is A, the unit vector along the tooth's long axis is e, and e is a unit vector, and the bone height is... , axial root length , , and percentage of radiographic bone loss for: In the formula, ( (A- After taking the absolute value of ), the bone height and root length of both the maxilla and mandible are positive. When the first root length is less than 5mm, the first bone height is used as the output result for that tooth surface, and the root length of that tooth surface is marked as unreliable.

[0067] In one implementation, without deducting physiological distance, the ratio is obtained directly by dividing the height of the first bone by the length of the first root.

[0068] Indicators measured along multiple directions within the same tooth surface are summarized to obtain the summarized indices for that tooth surface. The summarization can be performed using one of the following methods: First, remove the largest and smallest indices within the tooth surface, and then take the maximum value of the remaining indices, which is recorded as the robust maximum. Second, take the 95th percentile value of each indices within the tooth surface, which is recorded as the quantile sum. Third, take the median. Fourth, take the mean.

[0069] In one implementation, the main output uses the 95th percentile (...). ) or robust maximum value ( The auxiliary output uses the median or mean.

[0070] Figure 4 This diagram illustrates a comparison of tooth surfaces of the same tortuous tooth under two references: the mesiodistal morphological axis and the dental arch tangent, according to an embodiment of the present invention. In the diagram, ψ represents the torsion angle, the angle between the tooth's own mesiodistal morphological axis m and the first axis x of the dental arch tangent. The torsion angle between the tooth's own mesiodistal morphological axis and the dental arch tangent can be calculated. Let m be the unit vector of the tooth's own mesiodistal morphological axis, and x be the first axis after orthogonalization of the dental arch tangent. The angle between them is: .

[0071] When the torsion angle exceeds the torsion threshold, the dental arch tangent is used as the mesial-distal reference axis, and the torsion angle can be given in the report. The threshold can be 15° or 20°.

[0072] The following is an example of a rotating premolar.

[0073] The target tooth is the first premolar on the right side of the maxilla, twisted about 35° along the long axis of the tooth. The geometric center of the tooth region is the origin. The long axis of the tooth is fitted from the center of twelve cross sections in the middle of the crown and root. The dental arch curve is obtained from the cubic spline of the center of the existing maxillary tooth. The tangent direction of the tooth center is at the nearest point on the dental arch, and the angle between the tangent direction and the left and right directions of the patient is about 8°. After orthogonalization, it is used as the first axis.

[0074] If we divide the sector using the mesial and distal morphological axes obtained from principal component analysis of the tooth region, the nominal mesial sector shows a first bone height of approximately 4.2 mm and a first root length of approximately 13 mm, accounting for approximately 32%. The mesial contact area marked by the dentist is located in the buccal sector of this division, where the first bone height is approximately 1.6 mm, accounting for approximately 12%.

[0075] After using the dental arch tangent as the first axis, the mesial sector is aligned with the contact area, with the mesial surface accounting for approximately 12% and the buccal surface accounting for approximately 31%. The torsion angle is approximately 35°, exceeding the threshold of 20°. The report indicates that the dental arch tangent has been used as the mesial-distal reference.

[0076] In the example of missing teeth, the first molar on the left side of the mandible is missing. The mandibular dental arch is fitted after interpolation and filling the gaps using the center of the second premolar and the center of the second molar. The first axis of the distal surface of the second premolar still follows the direction of the dental arch, and the missing tooth position itself does not output indicators.

[0077] In the implant embodiment, the first molar on the left side of the maxilla is the implant. The center of this position is not included in the tangent calculation, or is only used as a weak control point. The tangent of the dental arch of the adjacent teeth is determined by the centers of the other existing teeth.

[0078] After the dental arch curve is parameterized, the closest point from the center of the target tooth to the curve can be solved by arc length scanning or Newton iteration. For missing teeth, linear interpolation of the center of the adjacent existing teeth or arc length interpolation along the dental arch direction is used. The weight of the weak control point of the implant can be one-quarter to one-half of that of the normal tooth. If the center of the crown of the residual root is significantly deviated from the dentition, it can be excluded from the tangent calculation.

[0079] Each of the four sectors occupies 90°. For anterior teeth with narrower proximal surfaces, the circumferential angles of the mesial and distal sectors are less than 90°, while the circumferential angles of the labial and lingual sectors are greater than 90°. The sum of the circumferential angles of the four sectors is 360°. The included angle interval can be 15°, 30°, or 45°.

[0080] The system outputs radiographic bone loss indicators for each tooth and each tooth surface, simultaneously providing the first bone height and first root length for that surface. It can generate severity-enhancing indicators based on set thresholds. These indicators are for radiographic reference only and not as clinical diagnostic conclusions. The report may include visualizations, such as overlaying measurement directions and reference points onto trans-tooth long-axis slices. The thresholds are configurable. In one implementation, the system primarily outputs the mesial, distal, buccal, and lingual surfaces. In another implementation, additional directions such as mesial-buccal and distal-buccal can be added according to probing site preferences.

[0081] For multi-rooted teeth, the indices of the four tooth surfaces can still be output using a local coordinate system established by the tooth's long axis and the tangent of the dental arch. Further calculations based on the root axis of each tooth root can be used for subsequent processing.

[0082] The maxilla and mandible are processed separately. The three-dimensional center points of the existing teeth are arranged according to the dentition sequence. One implementation of the dentition sequence is by tooth position numbering. In the maxilla, the sequence starts from the third molar on one side, passes through the anterior teeth, and ends at the third molar on the opposite side. The mandible is processed in the same way. Missing edentulous positions are filled by interpolation of the centers of adjacent existing teeth. When there are consecutive missing teeth, linear interpolation can be performed using the centers of the nearest existing teeth on both sides of the edentulous space, or the space can be divided equally along the existing dental arch length according to the number of missing teeth. The interpolation points participate in spline fitting, but do not output radiographic bone loss indicators for that position.

[0083] Spline fitting can use cubic splines, polynomial fitting, or piecewise circular arcs. The fitted result is a spatial curve with arc length as the parameter. The closest point on the curve from the center of the target tooth can be scanned along the arc length, with an arc length step of, for example, 0.5 mm, selecting the point with the smallest Euclidean distance. Alternatively, Newton's iteration can be used. The tangent vector at this point is given by the first derivative of the spline with respect to the arc length, then normalized. For the entire orifice, this direction is uniformly defined as pointing from the patient's right side to the left side.

[0084] Implants and significant root remnants may be excluded from tangent calculations. In one implementation, the implant center is weighted at 0. In another implementation, only the crown center is used as a weak control point, with a weight of one-quarter to one-half that of a normal tooth. If the crown center of a root remnant is significantly deviated from the dentition, it can be excluded from tangent calculations.

[0085] The origin of the coordinate system is taken as the geometric center of the tooth region. In an alternative method, the origin can also be translated to the center of the cementoenamel junction reference plane. The first axis is corrected so that the patient's right side points to the left side. The third axis is along the long axis of the tooth, with the positive direction taken anatomically downward. For maxillary teeth, the anatomical direction is downward and points in the opposite direction to the crown direction, while for mandibular teeth, it points in the crown direction. The second axis is determined by the first and third axes according to the right-hand rule, with the positive direction pointing from the lingual side to the buccal side. The palatal side of the maxilla is used as the corresponding side of the lingual direction in the maxilla.

[0086] If the tangent is almost parallel to the long axis of the tooth, the denominator is too small. In this case, first project the tangent onto a plane perpendicular to the cephalic direction, then remove the component parallel to the long axis of the tooth and normalize it. For the cephalic direction, take the autologous data. When calculating bone height and root length, take the absolute value of the projection along the long axis of the tooth. Use the same formula for the maxilla and mandible.

[0087] In a plane perpendicular to the long axis of the tooth, with the orthogonalized mesiodistal reference axis as the zero-degree reference, in one embodiment, the mesial sector, buccal sector, distal sector, and lingual sector each occupy 90°. When the proximal surfaces of the anterior teeth are narrow, the circumferential angles of the mesial and distal sectors can be less than 90°, while the circumferential angles of the labial and lingual sectors can be greater than 90°. The sum of the circumferential angles of the four sectors is 360°. The labial side of the anterior teeth corresponds to the buccal side, and the palatal side of the maxillary posterior teeth corresponds to the lingual side.

[0088] The measurement slice passes through the long axis of the tooth and forms an angle with the orthogonalized mesiodistal reference axis. The angle is taken at intervals of 15°, 30°, or 45°. Based on the sector into which the angle is entered, the measurement result of the slice is assigned to the corresponding tooth surface. The same tooth surface can contain multiple slices. A slice is divided into two half-slices by the long axis of the tooth, corresponding to two opposite tooth surfaces.

[0089] For indicators measured along multiple directions on the same tooth surface, the maximum value can be obtained by removing the largest and smallest values, or by using the 95th percentile, median, or mean. The maximum value remaining after removing the largest and smallest values ​​is denoted as the robust maximum value. The 95th percentile value is denoted as the quantile summary. In one implementation, the primary output uses the 95th percentile or robust maximum value, while the auxiliary output uses the median or mean.

[0090] If the cementoenamel junction reference point or alveolar ridge reference point is missing in a certain measurement direction, that direction will not be included in the summary. If the periapical reference point is missing or the first root length is less than 5mm, only the first bone height can be output, without the proportion.

[0091] In the crowded lower anterior teeth example, the right mandibular lateral incisor is rotated labially. The angle between the tooth's mesial and distal morphological axis and the dental arch tangent is about 28°, which exceeds the threshold of 20°. After using the dental arch tangent as the first axis, the mesial sector is aligned with the contact area with the central incisor. The height of the first bone on the mesial surface is about 1.2 mm, and the length of the first root is about 12 mm, accounting for about 10%.

[0092] The report may include visualizations that overlay tooth sectors, measurement slices, and three types of reference points onto trans-tooth long axis slices or three-dimensional surfaces. The threshold for auxiliary prompts can be configured. These prompts are used for radiographic reference and are not intended as clinical diagnostic conclusions.

[0093] When extracting a 3D region of interest (ROI) based on tooth position, the ROI includes the target tooth and its adjacent bone tissue. The size of the ROI can be adjusted according to tooth position; the ROI for anterior teeth can be smaller than that for molars. The ROI is then segmented into tooth instances to obtain the tooth region. Segmentation can employ a 3D encoder-decoder structure. The input is single-channel grayscale data, and the output consists of two classes: background and target teeth. Post-processing can preserve the largest connected components and remove excessively small fragments.

[0094] Tooth numbering and missing tooth identification use the same set of dental arch parameters. In one implementation, a correspondence between the detection plane or curved surface layer and the voxel space is established based on the parameters of the dental arch curve. The detected tooth center is mapped to three-dimensional coordinates. The numbering results are used to extract regions of interest by tooth position and to distinguish between maxillary and mandibular teeth, thereby unifying the downward anatomical direction of the third axis.

[0095] The cementoenamel junction reference point, alveolar ridge reference point, and periapical reference point can be obtained from section examination, thermographic extreme values, manual calibration, or other methods that provide three-dimensional coordinates. In one embodiment, the cementoenamel junction point and alveolar ridge point on both sides of a two-dimensional section passing through the long axis of the tooth are determined, and then mapped back to three dimensions. The periapical point can be determined on three-dimensional volume data. Points obtained from multiple sections within the same tooth surface sector can be sorted circumferentially and connected to form a local curve of that tooth surface, and the local curve is allowed to be broken.

[0096] The torsion angle threshold can be set to 15° or 20°. If the threshold is not exceeded, the dental arch tangent can still be used as the mesial-distal reference axis. If the threshold is exceeded, the torsion angle will be given in the report, and it will be marked that the dental arch tangent has been used. The grading threshold for auxiliary prompts can be configured, for example, grading by 15% and 33%. The grading results are only used for radiographic reference.

[0097] After steps 102 to 118, the radiographic bone loss index of the tooth surface is obtained in the direction of the adjacent tooth row.

[0098] During preprocessing, the volume data can be spatially resampled, truncated in grayscale, and normalized in intensity. In one embodiment, the voxel resolution is set to 0.25 mm, and the grayscale truncation range is set according to the commonly used window width and window level in cone-beam CT, without any special restrictions. The normalized volume data is used for tooth instance segmentation and subsequent measurements.

[0099] The output report can include tooth position number, torsion angle, first bone height of each tooth surface, first root length, radiographic bone loss index, and summary method, as well as missing measurement markers. No indexes are output for edentulous positions and implant positions, but interpolation points or weak control points can be retained on the dental arch curve. Dental arch curves are fitted separately for the maxilla and mandible of the same patient, and local coordinate systems are established for each tooth separately. The same set of directional conventions is used for all tooth surface results.

[0100] According to another aspect of the present invention, an alveolar bone resorption measurement system is provided.

[0101] Figure 7 A schematic diagram of an alveolar bone resorption measurement system according to an embodiment of the present invention is shown. The alveolar bone resorption measurement system may include a data acquisition module 1002, a tooth long axis determination module 1004, a reference axis determination module 1006, a coordinate system establishment module 1008, a tooth surface direction determination module 1010, a reference point determination module 1012, and an index calculation module 1014.

[0102] The data acquisition module is used to acquire three-dimensional volumetric data of the oral cavity using cone-beam CT and to determine the tooth region of the target tooth. The tooth long axis determination module is used to determine the tooth long axis based on the tooth region. The reference axis determination module is used to determine the mesiodistal reference axis based on the tangent direction of the dental arch curve at the center of the target tooth. The coordinate system establishment module is used to establish a single-tooth local coordinate system based on the tooth long axis and the mesiodistal reference axis. The tooth surface direction determination module is used to determine the measurement direction corresponding to at least two tooth surfaces among the mesial, distal, buccal, and lingual surfaces in the single-tooth local coordinate system. The reference point determination module is used to determine the cementoenamel junction reference point, alveolar ridge reference point, and periapical reference point along the measurement direction of each tooth surface. The index calculation module is used to determine the distance from the cementoenamel junction reference point to the alveolar ridge reference point and parallel to the tooth long axis as the first bone height along the measurement direction of each tooth surface, determine the absolute value of the projection of the difference between the periapical reference point and the cementoenamel junction reference point in the direction of the tooth long axis as the first root length, and determine the ratio of the two as the radiographic bone loss index of the corresponding tooth surface. This index is a measurement value of the degree of alveolar bone resorption of that tooth surface.

[0103] In one implementation, the reference axis determination module may further include a dental arch fitting submodule, a missing tooth interpolation submodule, and a tangent orthogonalization submodule. The tooth surface direction determination module may further include a sector division submodule and a slice assignment submodule. The index calculation module may further include a summary submodule and an auxiliary prompt submodule. The specific processing logic of each submodule corresponds to the above-described method implementation, and will not be repeated here.

[0104] The system can be deployed on a local imaging workstation, on a server that interfaces with the hospital's information system, or through cloud services for analysis. After the server completes the analysis, it returns the radiographic bone loss indicators and auxiliary prompts for each tooth and each tooth surface to the client for physicians to view.

[0105] Figure 8 A schematic diagram of an electronic device according to an embodiment of the present invention is shown. The electronic device includes a memory 1300 and a processor 1200. The memory 1300 stores execution instructions, and the processor 1200 executes the execution instructions stored in the memory 1300 to implement a method for measuring alveolar bone resorption.

[0106] The device may include corresponding modules that perform one or more steps in the above process. Modules may be hardware modules specifically configured to perform the corresponding steps, or implemented by a processor configured to perform the corresponding steps, or stored in a computer-readable medium for implementation by a processor, or implemented by some combination thereof.

[0107] This hardware architecture can be implemented using a bus architecture, which can include any number of interconnect buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus connects various circuits, including one or more processors, memory, and hardware modules, and can also connect other circuits such as peripherals, voltage regulators, and power management circuits.

[0108] A bus can be an industry standard architecture bus, an external device interconnection bus, or an extended industry standard architecture bus, etc. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, only one connection line is used in the attached figure, but this does not mean that there is only one bus or one type of bus.

[0109] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process. The scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed in a different order than those shown or discussed.

[0110] The processor executes the various methods and processes described above. The method implementations of this invention can be implemented as software programs tangibly contained in a machine-readable medium, such as memory. When the software program is loaded into memory and executed by the processor, one or more steps of the methods described above can be performed. Alternatively, the processor can be configured in other suitable ways to execute the methods described above.

[0111] A readable storage medium can be any means that can contain, store, communicate, propagate, or transmit programs for use by an instruction execution system, apparatus, or device. More specific examples include: electrical connections having one or more wires, portable computer disk drives, random access memory, read-only memory, erasable and programmable read-only memory, fiber optic devices, and portable read-only memory.

[0112] Various parts of this invention can be implemented in hardware, software, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software stored in memory and executed by a suitable instruction execution system. If implemented in hardware, they can be implemented using discrete logic circuits, application-specific integrated circuits, programmable gate arrays, field-programmable gate arrays, etc., which are well known in the art.

[0113] Those skilled in the art will understand that all or part of the steps of the methods described above can be implemented by a program instructing related hardware. The program can be stored in a readable storage medium. When executed, the program includes one or a combination of the steps of the method implementation.

[0114] In the various embodiments of this invention, the functional units can be integrated into one processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module.

[0115] The present invention also provides an electronic device, comprising: a memory storing execution instructions; and a processor or other hardware module, wherein the processor or other hardware module executes the execution instructions stored in the memory, causing the processor or other hardware module to perform the above-described method.

[0116] The present invention also provides a readable storage medium storing executable instructions, which, when executed by a processor, are used to implement the above-described method.

[0117] In one implementation, the full-mouth procedure involves fitting dental arch curves separately for the maxilla and mandible, then establishing a local coordinate system for each tooth position and calculating tooth surface parameters. No parameters are output for edentulous positions and implant positions. Teeth with a torsion angle exceeding a threshold are marked in the report as having been aligned with the dental arch tangent. Output fields include tooth position number, first bone height of each tooth surface, first root length, radiographic bone loss index, and missing measurement markers.

[0118] This invention determines the mesial and distal reference axes based on the tangent of the dental arch curve at the center of the target tooth, establishes a single-tooth local coordinate system together with the tooth long axis, and then calculates the radiographic bone loss index according to the measurement directions in the mesial, distal, buccal, and lingual surfaces.

[0119] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," or "some examples," etc., indicate that a specific feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0120] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. Those skilled in the art should understand that the above embodiments are merely for clearly illustrating the present invention and are not intended to limit the scope of the invention. For those skilled in the art, other changes or modifications can be made based on the above disclosure, and these changes or modifications still fall within the scope of the present invention.

Claims

1. A method for measuring alveolar bone resorption, characterized in that, include: Acquire three-dimensional volumetric data of the oral cavity using cone-beam computed tomography (CBCT) to determine the tooth region of the target tooth; Determine the long axis of the tooth based on the described tooth region; Determine the mesiodistal reference axis based on the tangent direction of the dental arch curve at the center of the target tooth; Remove the component parallel to the tooth length axis in the tangential direction and normalize it to obtain the orthogonalized mesiodistal reference axis; The positive direction of the orthogonalized mesial and distal reference axes is unified so that it points from the patient's right side to the left side; A single-tooth local coordinate system is established based on the tooth long axis and the orthogonalized mesiodistal reference axis; In the single-tooth local coordinate system, determine the measurement directions corresponding to at least two of the tooth surfaces, including the mesial, distal, buccal, and lingual surfaces; Determine the cementoenamel junction reference point, alveolar ridge reference point, and periapical reference point along the measurement directions of each tooth surface; and Along the measurement direction of each tooth surface, the distance from the cementoenamel junction reference point to the alveolar ridge reference point, parallel to the tooth long axis, is determined as the first bone height. The absolute value of the projection of the difference between the root apex reference point and the cementoenamel junction reference point in the direction of the tooth long axis is determined as the first root length. The ratio of the first bone height to the first root length is determined as the radiographic bone loss index of the corresponding tooth surface. The radiographic bone loss index is a measurement value of the degree of alveolar bone resorption of the corresponding tooth surface.

2. The method as described in claim 1, characterized in that, The determination of the mesiodistal reference axis based on the tangent direction of the dental arch curve at the center of the target tooth includes: Extract dental arch curves for the maxilla and mandible separately; The three-dimensional center points of the existing teeth are arranged in the order of the dentition. For missing teeth, the center points of adjacent existing teeth are interpolated to fill the gaps, and the dental arch curve is obtained by fitting a spline curve. Determine the nearest point on the dental arch curve to the center of the target tooth, and use the tangent direction at that nearest point as the source of the mesiodistal reference direction.

3. The method as described in claim 1, characterized in that, The step of removing the component parallel to the tooth long axis in the tangential direction and normalizing it includes: When the modulus of the tangent direction after removing the component parallel to the tooth length axis is too small to obtain a stable unit vector, the tangent direction is first projected onto a plane perpendicular to the head-to-feet direction; and Then remove the components parallel to the tooth length axis from the projection result and normalize them.

4. The method as described in claim 1, characterized in that, The origin of the local coordinate system for a single tooth is taken as the geometric center of the tooth region; The single-tooth local coordinate system uses the orthogonalized mesiodistal reference axis as the first axis; The single-tooth local coordinate system uses the tooth's long axis as its third axis, with the positive direction anatomically downwards. For maxillary teeth, the anatomical downwards point in the opposite direction to the crown direction, and for mandibular teeth, the anatomical downwards point in the direction of the crown direction. The second axis of the single-tooth local coordinate system is determined by the first axis and the third axis according to the right-hand rule, with the positive direction pointing from the lingual side to the buccal side.

5. The method as described in claim 1, characterized in that, The determination of the measurement directions corresponding to at least two of the mesial, distal, buccal, and lingual surfaces in the single-tooth local coordinate system includes: In a plane perpendicular to the tooth's long axis, using the orthogonalized mesiodistal reference axis as the angular reference, the circumference is divided into sectors corresponding to the mesial, distal, buccal, and lingual surfaces, each sector occupying 90°; and The labial side of the anterior teeth corresponds to the buccal side, and the palatal side of the maxillary posterior teeth corresponds to the lingual side.

6. The method as described in claim 5, characterized in that, A measurement slice is generated that passes through the tooth's long axis and forms an angle with the orthogonalized mesiodistal reference axis; The included angle is taken at intervals of 15°, 30°, or 45°; and Based on the sector into which the angle is located, the measurement results of the measurement slice are assigned to the corresponding tooth surface.

7. The method as described in claim 1, characterized in that, When the length of the first bone is not less than 5 mm, the radiographic bone loss index is expressed as a percentage; and When the first root length is less than 5mm, the first bone height is used as the output result of the corresponding tooth surface, and the root length of the corresponding tooth surface is marked as unreliable.

8. The method as described in claim 1, characterized in that, Also includes: Determine the angle of twist between the mesial and distal morphological axes of the tooth and the tangent of the dental arch curve; as well as When the torsion angle exceeds the torsion threshold, the tangent of the dental arch curve is used as the mesiodistal reference axis, and the torsion threshold is 15° or 20°.

9. The method as described in claim 2, characterized in that, The edentulous position participates in the dental arch curve interpolation, but does not output radiographic bone loss indicators for the edentulous position; and Implants and residual roots are not included in the tangent calculation, or only the crown center is used as the weak control point of the dental arch curve. The weight of the weak control point is one-quarter to one-half of the weight of the normal tooth center.

10. The method as described in claim 1, characterized in that, The tooth region for determining the target tooth includes: The three-dimensional volume data is decompressed and converted into absorption coefficient data, where the absorption coefficient is the absorption coefficient of a substance to X-rays; Based on the dental arch curve parameters, the tooth detection results are mapped back to three-dimensional voxel coordinates to complete tooth numbering and missing tooth identification; and A three-dimensional sub-volume containing the target tooth and its adjacent bone tissue is extracted from the three-dimensional volume data according to tooth position. The three-dimensional sub-volume is a three-dimensional region of interest. Tooth instance segmentation is performed on the three-dimensional region of interest. The tooth instance segmentation divides the voxels in the three-dimensional region of interest into background voxels and target tooth voxels. The tooth region is obtained from the target tooth voxels.

11. The method as described in claim 1, characterized in that, Determining the long axis of the tooth based on the tooth region includes: Multiple cross-sections of the tooth region are extracted along the initial principal axis direction, where the initial principal axis is either the principal component direction of the tooth region or the orientation direction obtained from tooth segmentation. The effective cross-section is defined as the section located from the crown to the mid-root shaft, avoiding irregular areas of the coronal occlusal surface and the root apex. The center position of the tooth region within each effective cross-section is calculated; and... The direction of the tooth long axis is obtained by fitting a straight line to the center position of the tooth region within each effective cross section.

12. The method as described in claim 1, characterized in that, The radiographic bone loss indices in multiple measurement directions within the same tooth surface are summarized to obtain the summarized indices for that tooth surface. The summarization is one of the following: after removing the largest and smallest indices within the tooth surface, the maximum value of the remaining indices is taken; the 95th percentile value of each indices within the tooth surface is taken; the median value of each indices within the tooth surface is taken; or the mean value of each indices within the tooth surface is taken.

13. The method as described in claim 1, characterized in that, Also includes: Output radiographic bone loss indicators per tooth and per tooth surface; Generate severity-based auxiliary prompts based on a set threshold; as well as The supplementary information provided is for imaging reference only and should not be used as a clinical diagnostic conclusion.

14. A system for measuring alveolar bone resorption, characterized in that, include: The data acquisition module is used to acquire three-dimensional volumetric data of the oral cavity using cone-beam CT and to determine the tooth region of the target tooth. A tooth long axis determination module is used to determine the tooth long axis based on the tooth region; The reference axis determination module is used to determine the mesiodistal reference axis based on the tangent direction of the dental arch curve at the center of the target tooth. The component parallel to the tooth length axis in the tangent direction is removed and normalized to obtain the orthogonalized mesiodistal reference axis. The positive direction of the orthogonalized mesiodistal reference axis is unified to point from the patient's right side to the left side. The coordinate system establishment module is used to establish a single-tooth local coordinate system based on the tooth long axis and the orthogonalized mesiodistal reference axis. The tooth surface orientation determination module is used to determine the measurement orientation of at least two tooth surfaces among the mesial, distal, buccal, and lingual surfaces in the single tooth local coordinate system. The reference point determination module is used to determine the cementoenamel junction reference point, alveolar ridge reference point, and periapical reference point along the measurement directions of each tooth surface; and The index calculation module is used to determine the distance from the cementoenamel junction reference point to the alveolar ridge reference point, parallel to the long axis of the tooth, along the measurement direction of each tooth surface as the first bone height; to determine the absolute value of the projection of the difference between the root apex reference point and the cementoenamel junction reference point in the direction of the long axis of the tooth as the first root length; and to determine the ratio of the first bone height to the first root length as the radiographic bone loss index of the corresponding tooth surface, wherein the radiographic bone loss index is a measurement value of the degree of alveolar bone resorption of the corresponding tooth surface.

15. An electronic device, characterized in that, include: The memory stores execution instructions; as well as A processor that executes execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1 to 13.

16. A readable storage medium, characterized in that, The readable storage medium stores execution instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 13.

Images