CN114897924B - Tooth model segmentation method and device - Google Patents
Tooth model segmentation method and device Download PDFInfo
- Publication number
- CN114897924B CN114897924B CN202210434419.2A CN202210434419A CN114897924B CN 114897924 B CN114897924 B CN 114897924B CN 202210434419 A CN202210434419 A CN 202210434419A CN 114897924 B CN114897924 B CN 114897924B
- Authority
- CN
- China
- Prior art keywords
- point
- target
- reference point
- points
- effective
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30036—Dental; Teeth
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
Abstract
The invention provides a tooth model segmentation method and a device, wherein the tooth model segmentation method comprises the following steps: acquiring a three-dimensional dental model, and respectively selecting a first reference point and a second reference point at a groove on one side of the top surface of a single tooth based on the three-dimensional dental model; determining a reference point set formed by points with curvature smaller than a curvature threshold value on a single tooth based on the first reference point, the second reference point and the reference axis, and removing points in a reference range on the top surface of the single tooth from the reference point set to obtain a target point set; determining a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determining a target contour line based on the first effective point, the second effective point and the target point set; based on the target contour, a plurality of individual tooth models are segmented from the three-dimensional dental model. The tooth model segmentation method and the tooth model segmentation device can reduce the dependence on manual experience, reduce the labor cost, are simpler and more direct, and improve the tooth model segmentation efficiency.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for segmenting a tooth model.
Background
With the rapid development of digital imaging technology, digitization has brought convenience to many fields, and its convenience and high efficiency also affect the oral medical industry. In the field of stomatology, virtual orthodontic systems developed by computer graphics, digital media technology, graphic image processing and other technologies can be used as references. Tooth segmentation is a critical step in the orthodontic process and is the basis for subsequent functions. Tooth segmentation is the individual segmentation of each tooth on a three-dimensional dental model.
The conventional virtual orthodontic system mainly relies on human-computer operation by a user, tooth areas are determined through operations such as manually sketching gum lines and the like and then segmented, and then segmented results are modified again through manual intervention means, so that the tooth model segmentation process is complex, the labor cost is high and the efficiency is low due to the fact that the artificial experience is relied on.
Disclosure of Invention
The invention provides a tooth model segmentation method and a tooth model segmentation device, which are used for solving the defects that the tooth model segmentation process is complex, the labor cost is high and the efficiency is low due to the dependence on the labor experience in the prior art, reducing the dependence on the labor experience, reducing the labor cost, enabling the tooth model segmentation process to be simpler and more direct and improving the tooth model segmentation efficiency.
The invention provides a tooth model segmentation method, which comprises the following steps:
acquiring a three-dimensional dental model, and respectively selecting a first reference point and a second reference point which are positioned at a groove on one side of the top surface of a single tooth based on the three-dimensional dental model;
determining a reference point set formed by points with curvature smaller than a curvature threshold value on a single tooth based on the first reference point, the second reference point and a reference axis, and removing points in a reference range on the top surface of the single tooth from the reference point set to obtain a target point set, wherein the reference axis is a straight line pointing to the direction of the tooth tip from the tooth root of the single tooth, and the reference range is within the outer contour of the top surface of the single tooth;
determining a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determining a target contour line based on the first effective point, the second effective point and the target point set, wherein the first effective point and the second effective point are respectively positioned at grooves on one side of the top surface of a single tooth;
based on the target contour, a plurality of individual tooth models are segmented from the three-dimensional dental model.
According to the tooth model segmentation method provided by the invention, the reference point set formed by the points with the curvature smaller than the curvature threshold value on the single tooth is determined based on the first reference point, the second reference point and the reference axis, and the method comprises the following steps:
taking the midpoint of the first reference point and the second reference point as a third reference point;
determining a target range based on the third reference point, the reference axis, and a reference radius;
and selecting points with curvature smaller than the curvature threshold from points of the three-dimensional dental model in the target range as a reference point set.
According to the tooth model segmentation method provided by the invention, the three-dimensional dental model consists of a plurality of triangular plates, points in a reference range on the top surface of a single tooth are removed from the reference point set, and a target point set is obtained, wherein the method comprises the following steps:
starting from the third reference point, extending along the reference axis to intersect with the reference point set to obtain a fourth reference point;
acquiring a first triangular plate where the first reference point is located, a second triangular plate where the second reference point is located and a third triangular plate where the fourth reference point is located;
Starting to extend outwards from the third triangular plate until the third triangular plate extends to the first triangular plate and the second triangular plate to obtain a reference range, wherein points in the reference range are arranged according to the sequence of extension;
and removing points in the reference range from the reference point set to obtain a target point set.
According to the tooth model segmentation method provided by the invention, the first effective point and the second effective point are determined from the target point set based on the first reference point, the second reference point and the reference axis, and the method comprises the following steps:
determining a tangent line between a plane formed by the first reference point, the second reference point and the reference axis and the target point set;
determining a point closest to the first reference point from the set of target points as a first effective point along a direction from the second reference point to the first reference point on the tangent line;
and determining a point closest to the second reference point from the target point set along the direction from the first reference point to the second reference point on the tangent line as a second effective point.
According to the tooth model segmentation method provided by the invention, the three-dimensional dental model is composed of a plurality of triangular plates, and the method for determining the target contour line based on the first effective point, the second effective point and the target point set comprises the following steps:
Searching the shortest path connected to the second effective point from the target point set by taking the first effective point as a starting point to obtain a first contour line;
expanding all points except the first effective point and the second effective point on the first contour line outwards by a target number of triangular plates, and deleting the points in the target number of triangular plates from the target point set to obtain an alternative point set;
searching the shortest path connected to the second effective point from the alternative point set by taking the first effective point as a starting point, and determining a second contour line;
a target contour is determined based on the first contour and the second contour.
According to the tooth model segmentation method provided by the invention, after the target contour line is determined based on the first contour line and the second contour line, the method further comprises the following steps:
taking the midpoints of the first effective point and the second effective point as a fifth reference point;
determining a defined point based on the first effective point, the second effective point, the fifth reference point, the reference axis, and the set of target points;
and adjusting the target contour line based on the target contour line and the limiting point to obtain an updated contour line.
According to the tooth model segmentation method provided by the invention, after the target contour line is determined based on the first contour line and the second contour line, the method further comprises the following steps:
acquiring a control point on the target contour line at intervals of reference length;
generating a smooth curve based on a plurality of control points;
finding a point closest to each point on the smooth curve in the target point set to obtain a plurality of mark points;
a smooth contour line is generated based on the plurality of marker points.
The present invention also provides a tooth model segmentation apparatus including:
the acquisition module is used for acquiring a three-dimensional dental model and respectively selecting a first reference point and a second reference point which are positioned at a groove on one side of the top surface of a single tooth based on the three-dimensional dental model;
the first determining module is used for determining a reference point set formed by points with curvature smaller than a curvature threshold value on a single tooth based on the first reference point, the second reference point and a reference axis, removing points in a reference range on the top surface of the single tooth from the reference point set to obtain a target point set, wherein the reference axis is a straight line pointing to the cusp direction from the root of the single tooth, and the reference range is within the outer contour of the top surface of the single tooth;
A second determining module, configured to determine a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determine a target contour line based on the first effective point, the second effective point and the target point set, where the first effective point and the second effective point are located at a groove on a top surface side of a single tooth, respectively;
and the segmentation module is used for segmenting a plurality of single tooth models from the three-dimensional dental model based on the target contour line.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing any one of the tooth model segmentation methods described above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a tooth model segmentation method as described in any of the above.
According to the tooth model segmentation method and device, the three-dimensional tooth model is obtained, the curvatures of all the points on the three-dimensional tooth model are determined, the target contour lines are utilized to segment a plurality of single tooth models, dependence on manual experience can be reduced, labor cost is reduced, the tooth model segmentation process is simpler and more direct, and tooth model segmentation efficiency is improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a tooth model segmentation method provided by the invention;
FIG. 2 is a schematic view of selected reference points of a tooth model segmentation method according to the present invention;
FIG. 3 is a schematic illustration of a set of determined reference points of a tooth model segmentation method provided by the present invention;
FIG. 4 is a schematic illustration of a tooth model segmentation method of the present invention for generating a first contour line;
FIG. 5 is a schematic illustration of a tooth model segmentation method of the present invention for generating a second contour;
FIG. 6 is a schematic illustration of the tooth model segmentation method of the present invention with additional defined points avoiding holes;
FIG. 7 is a schematic illustration of an optimized contour path for a tooth model segmentation method provided by the present invention;
FIG. 8 is a schematic view of a tooth model segmentation method according to the present invention;
FIG. 9 is a schematic diagram of triangular mesh segmentation of the tooth model segmentation method provided by the invention;
FIG. 10 is a schematic view of a tooth model segmentation apparatus according to the present invention;
fig. 11 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The tooth model segmentation method and apparatus of the present invention are described below with reference to fig. 1-11.
As shown in fig. 1, the present invention provides a tooth model segmentation method including the following steps 110 to 140.
Step 110, acquiring a three-dimensional dental model, and respectively selecting a first reference point and a second reference point which are positioned at a groove on one side of the top surface of a single tooth based on the three-dimensional dental model.
It will be appreciated that oral scanning is a common digital operation in dentistry, and that teeth in a patient's mouth may be digitally modeled to obtain a three-dimensional curved model, which may be described discretely and approximately in terms of triangular patches as basic units, as a surface of a three-dimensional solid model, which may be referred to as a three-dimensional dental model.
As shown in fig. 2, one reference point, i.e., the first reference point P1 and the second reference points P2, may be selected on both sides of each tooth in the dental arch line direction, and the first reference point P1 and the second reference points P2 may be required to be positioned at the grooves on both sides of the tooth.
And 120, determining a reference point set formed by points with curvature smaller than a curvature threshold value on the single tooth based on the first reference point, the second reference point and the reference axis, and removing points in a reference range on the top surface of the single tooth from the reference point set to obtain a target point set, wherein the reference axis is a straight line pointing to the tooth tip direction from the root of the single tooth, and the reference range is within the outer contour of the top surface of the single tooth.
It will be appreciated that, as shown in fig. 2, a straight line directed from the root of a single tooth in the cusp direction may be set as the reference axis AxisDir. The minimum curvature may be calculated for each point on the three-dimensional dental model, wherein the value of the curvature of the points of the projections on the three-dimensional dental model is positive and the value of the curvature of the points of the recesses is negative.
A range may be formed from the first reference point, the second reference point, and the reference axis, the range may generally define a range in which points on a single tooth are located, points from the range of points are selected to form a set of reference points having a curvature less than a curvature threshold, the curvature threshold may be less than 0, such as-0.7, and points within the range having a curvature less than-0.7 may be put together to form the set of reference points.
After the reference point set is obtained, points in a reference range on the top surface of the single tooth are removed from the reference point set to obtain a target point set, wherein the reference range is smaller than the range of the top surface of the single tooth, the reference range can be preset or determined by adopting a geometric method, the determination method of the reference range is not limited, and the target point set can be set by a person skilled in the art according to actual conditions.
Step 130, determining a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determining a target contour line based on the first effective point, the second effective point and the target point set, wherein the first effective point and the second effective point are respectively positioned at grooves on one side of the top surface of the single tooth.
It will be appreciated that the first reference point and the second reference point selected in step 110 are roughly selected and are not necessarily located in the target point set, where the endpoints are determined again from the grooves on both sides of the top surface of the single tooth according to the first reference point, the second reference point and the reference axis, and the first effective point and the second effective point are correspondingly obtained, where the first effective point corresponds to the first reference point, and the second effective point corresponds to the second reference point, that is, the first effective point may be substituted for the first reference point, and the second effective point may be substituted for the second reference point.
Step 140, based on the target contour, a plurality of single tooth models are segmented from the three-dimensional dental model.
It will be appreciated that, according to steps 110 to 140, a plurality of target contours may be obtained, the target contours corresponding to boundaries between the plurality of individual teeth, through which the plurality of individual tooth models in the three-dimensional dental model may be separated from each other, where the plurality of individual tooth models may be segmented from the three-dimensional dental model, such that an automatic segmentation of the three-dimensional dental model is achieved.
It is worth mentioning that the current common virtual orthodontic system mainly relies on the user to perform man-machine operation, the tooth area is determined through operations such as manually sketching gum line and the like and then is segmented, then the segmented result is modified again through manual intervention means, the tooth model segmentation process is complex, the manual experience is relied on, the labor cost is high, and the efficiency is low.
Compared with a manual segmentation mode, the method of the embodiment can automatically and accurately segment the three-dimensional dental model without depending on manual experience, can reduce labor cost, enables the tooth model segmentation process to be simpler and more direct, and can improve the tooth model segmentation efficiency.
According to the tooth model segmentation method provided by the invention, the three-dimensional tooth jaw model is obtained, the curvature of each point on the three-dimensional tooth jaw model is determined, the target contour is utilized to segment a plurality of single tooth models, the dependence on the artificial experience can be reduced, the labor cost is reduced, the tooth model segmentation process is simpler and more direct, and the tooth model segmentation efficiency is improved.
As shown in fig. 3, in some embodiments, determining the set of reference points on the individual teeth that includes points with curvature less than the curvature threshold based on the first reference point, the second reference point, and the reference axis in step 120 includes: taking the midpoint of the first reference point and the second reference point as a third reference point; determining a target range based on the third reference point, the reference axis, and the reference radius; and selecting points with curvature smaller than a curvature threshold value from points of the three-dimensional dental model in the target range as a reference point set.
It can be understood that an effective range can be formed according to the first reference point, the second reference point and the reference axis, and a model in the effective range can be extracted to reduce the calculation amount and improve the subsequent calculation performance.
As shown in fig. 3, a midpoint between the first reference point P1 and the second reference point P2 may be calculated as a third reference point center, a model point set within a cylindrical range with a reference radius of a radius is denoted as M1 with the reference axis AxisDir as an axis direction centered on the third reference point center, and a point with a curvature smaller than a curvature threshold value is selected from the model point set M1 as a reference point set, wherein the reference radius may be 8mm.
In some embodiments, the three-dimensional dental model is comprised of a plurality of triangular plates, and removing points lying within a reference range on the top surface of a single tooth from a set of reference points to obtain a set of target points, comprising: starting from the third reference point, extending along the reference axis to intersect with the reference point set to obtain a fourth reference point; acquiring a first triangular plate where a first reference point is located, a second triangular plate where a second reference point is located and a third triangular plate where a fourth reference point is located; starting to extend outwards from the third triangular plate until the third triangular plate extends to the first triangular plate and the second triangular plate, obtaining a reference range, and arranging points in the reference range according to the sequence of extension; and removing points in the reference range from the reference point set to obtain a target point set.
It will be appreciated that a three-dimensional dental model is made up of a plurality of triangular plates that discretely approximate the surface of the three-dimensional solid model, with points at the tooth and gum boundaries generally being concave inward, and the three-dimensional dental model being segmented by connecting the points into contours. But the concave points exist not only at the grooves around the teeth but also at other parts, such as grooves at the tops of the teeth, so that the concave points at other parts on the three-dimensional dental model need to be excluded as much as possible to block the path of the contour line passing through the other parts.
The third reference point center can be extended along the direction of the reference axis AxisDir, and intersects with the reference point set at a fourth reference point P, the fourth reference point P is located on the top surface of the tooth, and the triangular plate serial numbers id of the fourth reference point P and the first reference point P1 and the second reference point P2 are found respectively, so as to obtain a first triangular plate C1 where the first reference point is located, a second triangular plate C2 where the second reference point is located, and a third triangular plate C where the fourth reference point is located.
The third gusset C can be expanded outwardly, loop by loop, until either the first gusset C1 or the second gusset C2 is found, and the set of points found is noted as Pset.
Taking points from the set of Pset points that are within the reference range, which may be, for example, the first two-thirds points, which are empirical values, may cover the area of the top surface of the tooth, resetting the curvature values of these points to 1, i.e., indicating exclusion from the set of points of the depression. And removing points in the reference range from the reference point set to obtain a target point set.
The points on the triangular plate far from the third triangular plate C may be recorded in the front of the point set group Pset in the order of traversal recording, that is, the points on the triangular plate near from the third triangular plate C are recorded in the rear of the point set group Pset. If the data is recorded and stored in the form of an array, the first two-thirds points can be determined directly according to the length of the array.
The fourth reference point P is located on the third triangular plate C, and traverses from three vertexes of the third triangular plate C to find all adjacent triangular plates including the vertexes, then continues traversing from the vertexes of the adjacent triangular plates, records the vertexes of the triangular plates found in the process, and stops traversing until traversing to the first triangular plate C1 or the second triangular plate C2, and the recorded point set is recorded as Pset. Corresponding to the extension from the third triangular piece C, which contains the fourth reference point P, outwards along the tooth contour, i.e. all around, in order to find the part which can contain the area of the top surface of the tooth. The specific implementation of the outward expansion can be realized in a recursive iteration mode or a cyclic mode.
In some embodiments, determining the first and second effective points from the set of target points based on the first reference point, the second reference point, and the reference axis comprises: determining a tangent line between a plane formed by the first reference point, the second reference point and the reference axis and the target point set; determining a point closest to the first reference point from the set of target points as a first effective point along a direction from the second reference point to the first reference point on the tangent line; and determining a point closest to the second reference point from the target point set as a second effective point along the direction from the first reference point to the second reference point on the tangent line.
It will be appreciated that a curvature threshold of-0.7 may be provided, i.e. a point where the curvature is less than this threshold is considered to be an effective point. The direction in which the second reference point P2 points to the first reference point P1 is denoted dir1, and a first effective point is found from the first reference point P1 along the dir1 direction, denoted as a new P1, i.e. the first effective point.
In the same way a new P2 is found in the opposite direction, i.e. the second effective point. This step ensures that the points at which P1 and P2 are both valid points, as the reference point initially selected, although at the groove, may not be a valid point.
Specifically, the first reference point P1 and the second reference point P2 and the reference axis AxisDir may form a plane, and tangent to the tooth model to obtain a tangent line, and an intersection point coordinate of the tangent line and the triangular mesh of the tooth model may be obtained. Finding the next intersection point Pt along the direction of P2-P1 on the tangent line, judging the grid surface where the Pt point is located after finding the Pt point on the tangent line, traversing the vertex on the grid surface, searching an effective point, and if the effective point is found, replacing P1 with the effective point; if no effective point is found on the grid, the traversal is continued to be performed around until the effective point is found and used as a new P1, so that a first effective point and a second effective point can be obtained.
As shown in fig. 4 and 5, in some embodiments, the three-dimensional dental model is comprised of a plurality of triangular plates, and determining the target contour based on the first effective point, the second effective point, and the target point set includes: searching the shortest path connected to the second effective point from the target point set by taking the first effective point as a starting point to obtain a first contour line; expanding all points except the first effective point and the second effective point on the first contour line outwards by a target number of triangular plates, deleting the points in the target number of triangular plates from the target point set, and obtaining an alternative point set; searching the shortest path connected to the second effective point from the alternative point set by taking the first effective point as a starting point, and determining a second contour line; a target contour is determined based on the first contour and the second contour.
It will be appreciated that all points on the target point set may be traversed, the weights of the valid points are set to 6, the weights of the invalid points are set to 1, and the shortest geodesic between the first valid point and the second valid point, that is, the line formed by connecting the edges of each adjacent triangular plate, is calculated and recorded as a first contour line1. The shortest path between two points on the triangular mesh will tend to be selected to pass through the point with the greater weight. Because the weight of the effective point is far greater than that of the ineffective point, the geodesic line can be searched along the effective point connected with the first effective point and the second effective point, and if the effective point is interrupted, the shortest path connection of the adjacent ineffective points at the interruption position is passed. Because the path through the rest of the tooth is blocked, the geodesic found by this method is the groove line around half of the tooth.
As shown in fig. 5, the other half of the contour lines from between the first effective point and the second effective point are next generated. And (3) expanding all points except for the first point and the last point in the first contour line1 outwards for 5 layers, setting the traversed points as invalid points, and calculating the shortest geodesic line between the first valid point and the second valid point by using the same method again to obtain a second contour line2, namely a groove connecting line of the other half around the teeth, and connecting the first contour line1 and the second contour line2 to obtain a complete contour line.
Wherein, the 5 layers are the target number, which is the number of iterations of traversing from these points to the outside, traversing from the points on the first contour to the outside for 5 iterations, finding all the areas, and setting the points on the triangular plates in these areas as invalid points, namely, setting an invalid area along the first contour, namely, an area of "forbidden passage". The subsequent shortest path generation avoids this invalid region, i.e. the other half of the path, i.e. the second contour, is taken.
In some embodiments, after determining the target contour based on the first contour and the second contour, further comprising: taking the midpoints of the first effective point and the second effective point as a fifth reference point; determining a defined point based on the first effective point, the second effective point, the fifth reference point, the reference axis, and the set of target points; and adjusting the target contour line based on the target contour line and the limiting point to obtain an updated contour line.
It will be appreciated that there may be holes in the scanned tooth model due to oral scanning instrument errors, etc., resulting in contours passing through the holes, which is not a desirable result. It is necessary to add defined points to the contour line, i.e. the path must pass through these intermediate points.
As shown in fig. 6 and 7, a plane is first formed through the center points of the first target point and the second target point and the reference axis AxisDir, and two intersections of the contour line and the plane are obtained and denoted as P3 and P4 (not shown in the figures). Secondly, respectively finding the 5 th point on two sides of the first target point on the contour line, and marking the points as P11 and P12 (not shown in the figure); the 5 th points, denoted as P21 (not shown) and P22, are found on both sides of the contour line P2, and a new contour line is generated in the order of P1→P11→P3→P22→P2→P21→P4→P12→P1 according to the method of generating the contour line, and the new contour line avoids the holes between teeth.
The weights of the effective points are uniformly set to 6 in the previous algorithm for generating the contour line, so that the points through which the contour line passes may not be the points with the minimum curvature, but the edges of the effective point set, which may lead to the generated contour line not being accurate enough and further needs to be optimized continuously. Firstly, resetting weights of all points of a target point set to 1, then outwards expanding a contour line by 5 layers, setting weights of effective points in the obtained point set to be 3+ curvature absolute value 5, and generating a new contour line by taking a first target point and a second target point as control points. This step corresponds to setting a weight according to the curvature value of each effective point within a certain range of the original path, and recalculating an optimal path. This path takes into account the difference in curvature of different points, and a weight is uniformly set according to the curvature threshold value when the path is generated before. Therefore, the regenerated contour line path in this step is more accurate.
At the same time, the starting point of the path, the first target point and the second target point, may not be at the optimal contour positions. The 5 th point can be found again on both sides of the first target point: p11 and P12; finding the 5 th point on two sides of the second target point on the contour line respectively: p21 and P22. And (3) making a plane again through the central points of the first target point and the second target point and the reference axis AxisDir, and obtaining two intersection points of the contour line and the plane: p3, P4. Then the points P11, P12, P21, P22, P3, P4 are all the points located on the best path. After deleting the first target point and the second target point at the two ends, generating a final contour line according to the sequence of P11→P3→P22→P21→P4→P12→P11. I.e. it is equivalent to adjusting the local path at the end point of the original path, which is optimized.
In some embodiments, after determining the target contour based on the first contour and the second contour, further comprising: acquiring a control point on a target contour line at intervals of a reference length; generating a smooth curve based on the plurality of control points; finding a point closest to each point on the smooth curve in the target point set to obtain a plurality of mark points; a smooth contour line is generated based on the plurality of marker points.
It will be appreciated that the previously obtained contour is geodesic, i.e. the path is along the edges of the model triangular mesh, which edges may be jagged and not smooth, and may be smoothed.
Specifically, a point is taken as a control point of the spline curve at regular intervals on the contour line. And generating a smooth spline curve spline according to the control points. Each point on the spline curve spline is traversed, the point closest to the spline curve is found on the model (the point may be inside the triangular plate), the original point is replaced, and the obtained new curve is the smoothed contour line. The contour line obtained by the method can draw the boundary of teeth under most conditions, and if individual error conditions occur, a user can manually adjust the control points to adjust the shape of the spline curve and regenerate a smooth contour line.
As shown in fig. 8, in some embodiments, segmenting a plurality of individual tooth models from a three-dimensional dental model based on a target contour may include the steps of:
first, each point on the contour line is traversed, the nearest grid vertex is found on the model, the grid vertices are connected to generate a geodesic contour line, scalar quantities of all vertices are set to 0, and scalar quantities of the other points are set to-1.
And a second step, taking a point fourth reference point of the top surface of the tooth as a seed point to expand outwards until traversing to a point with a scalar of 0, finding all points inside the contour line, and setting the scalar of 1.
And thirdly, if the model is directly segmented according to the result, the edge of the model triangle sheet may be saw-toothed as the geodesic contour line is along the edge of the model triangle sheet, and the segmented model boundary may be unsmooth. The segmentation may be based on scalar values of vertices in the region near the contour line. All points on the geodesic contour line can be extended outwards by one layer to obtain a new point set (excluding points on the line). Traversing the point set, calculating the shortest distance dist from each point to the obtained target contour line, setting the scalar of the point to dist if the scalar of the point is greater than 0, otherwise setting the scalar of the point to-dist.
And step four, traversing each point on the geodesic contour line, calculating the shortest distance dist from the point to the smooth contour line generated in the step three, obtaining the point with the largest scalar absolute value on the triangular plate where the point is located, setting the scalar of the point as dist if the scalar is larger than 0, otherwise setting the scalar of the point as-dist.
And fifthly, cutting the three-dimensional dental model by taking the scalar 0 as a boundary to obtain a segmented dental model.
It should be noted that, as shown in fig. 9, the scalar of the vertexes on the geodesic line calculated by the false design is 1, -2, -1, so that points with the value of 0 can be found on the sides of (1, -2) and (1, -1) respectively according to the distance proportion in the triangle formed by the three vertexes, and the two points are connected to form a new side, and the triangle is cut. The same process is performed on all geodesic vertices, and the individual tooth model is segmented by a relatively smooth boundary.
The tooth model segmenting device provided by the invention is described below, and the tooth model segmenting device described below and the tooth model segmenting method described above can be referred to correspondingly.
As shown in fig. 10, the present invention also provides a tooth model segmenting device comprising: an acquisition module 101, a first determination module 102, a second determination module 103 and a segmentation module 104.
The obtaining module 101 is configured to obtain a three-dimensional dental model, and select a first reference point and a second reference point located at a groove on one side of a top surface of a single tooth based on the three-dimensional dental model.
The first determining module 102 is configured to determine a reference point set formed by points with curvature smaller than a curvature threshold on a single tooth based on a first reference point, a second reference point and a reference axis, and remove points located in a reference range on a top surface of the single tooth from the reference point set to obtain a target point set, where the reference axis is a straight line pointing from a root of the single tooth to a cusp direction, and the reference range is within an outer contour of the top surface of the single tooth.
The second determining module 103 is configured to determine a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determine a target contour line based on the first effective point, the second effective point and the target point set, where the first effective point and the second effective point are located at the groove on the top surface side of the single tooth, respectively.
The segmentation module 104 is configured to segment a plurality of single tooth models from the three-dimensional dental model based on the target contour line.
Fig. 11 illustrates a physical structure diagram of an electronic device, as shown in fig. 11, which may include: processor (processor) 111, communication interface (Communications Interface) 112, memory (memory) 113 and communication bus 114, wherein processor 111, communication interface 112, memory 113 accomplish each other's communication through communication bus 114. The processor 111 may invoke logic instructions in the memory 113 to perform a tooth model segmentation method comprising: acquiring a three-dimensional dental model, and respectively selecting a first reference point and a second reference point which are positioned at a groove on one side of the top surface of a single tooth based on the three-dimensional dental model; determining a reference point set formed by points with curvature smaller than a curvature threshold value on a single tooth based on the first reference point, the second reference point and a reference axis, and removing points in a reference range on the top surface of the single tooth from the reference point set to obtain a target point set, wherein the reference axis is a straight line pointing to the direction of the tooth tip from the tooth root of the single tooth, and the reference range is within the outer contour of the top surface of the single tooth; determining a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determining a target contour line based on the first effective point, the second effective point and the target point set, wherein the first effective point and the second effective point are respectively positioned at grooves on one side of the top surface of a single tooth; based on the target contour, a plurality of individual tooth models are segmented from the three-dimensional dental model.
Further, the logic instructions in the memory 113 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of performing the tooth model segmentation method provided by the above methods, the method comprising: acquiring a three-dimensional dental model, and respectively selecting a first reference point and a second reference point which are positioned at a groove on one side of the top surface of a single tooth based on the three-dimensional dental model; determining a reference point set formed by points with curvature smaller than a curvature threshold value on a single tooth based on the first reference point, the second reference point and a reference axis, and removing points in a reference range on the top surface of the single tooth from the reference point set to obtain a target point set, wherein the reference axis is a straight line pointing to the direction of the tooth tip from the tooth root of the single tooth, and the reference range is within the outer contour of the top surface of the single tooth; determining a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determining a target contour line based on the first effective point, the second effective point and the target point set, wherein the first effective point and the second effective point are respectively positioned at grooves on one side of the top surface of a single tooth; based on the target contour, a plurality of individual tooth models are segmented from the three-dimensional dental model.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the tooth model segmentation method provided by the above methods, the method comprising: acquiring a three-dimensional dental model, and respectively selecting a first reference point and a second reference point which are positioned at a groove on one side of the top surface of a single tooth based on the three-dimensional dental model; determining a reference point set formed by points with curvature smaller than a curvature threshold value on a single tooth based on the first reference point, the second reference point and a reference axis, and removing points in a reference range on the top surface of the single tooth from the reference point set to obtain a target point set, wherein the reference axis is a straight line pointing to the direction of the tooth tip from the tooth root of the single tooth, and the reference range is within the outer contour of the top surface of the single tooth; determining a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determining a target contour line based on the first effective point, the second effective point and the target point set, wherein the first effective point and the second effective point are respectively positioned at grooves on one side of the top surface of a single tooth; based on the target contour, a plurality of individual tooth models are segmented from the three-dimensional dental model.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method of segmenting a tooth model, comprising:
acquiring a three-dimensional dental model, and respectively selecting a first reference point and a second reference point which are positioned at a groove on one side of the top surface of a single tooth based on the three-dimensional dental model;
determining a reference point set formed by points with curvature smaller than a curvature threshold value on a single tooth based on the first reference point, the second reference point and a reference axis, and removing points in a reference range on the top surface of the single tooth from the reference point set to obtain a target point set, wherein the reference axis is a straight line pointing to the direction of the tooth tip from the tooth root of the single tooth, and the reference range is within the outer contour of the top surface of the single tooth;
Determining a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determining a target contour line based on the first effective point, the second effective point and the target point set, wherein the first effective point and the second effective point are respectively positioned at grooves on one side of the top surface of a single tooth;
dividing a plurality of single tooth models from the three-dimensional dental model based on the target contour line;
the determining a first effective point and a second effective point from the set of target points based on the first reference point, the second reference point, and the reference axis, comprising:
determining a tangent line between a plane formed by the first reference point, the second reference point and the reference axis and the target point set;
determining a point closest to the first reference point from the set of target points as a first effective point along a direction from the second reference point to the first reference point on the tangent line;
determining a point closest to a second reference point from the set of target points as a second effective point along a direction from the first reference point to the second reference point on the tangent line;
The three-dimensional dental model is composed of a plurality of triangular plates, and the determining of the target contour line based on the first effective point, the second effective point and the target point set comprises the following steps:
searching the shortest path connected to the second effective point from the target point set by taking the first effective point as a starting point to obtain a first contour line;
expanding all points except the first effective point and the second effective point on the first contour line outwards by a target number of triangular plates, and deleting the points in the target number of triangular plates from the target point set to obtain an alternative point set;
searching the shortest path connected to the second effective point from the alternative point set by taking the first effective point as a starting point, and determining a second contour line;
a target contour is determined based on the first contour and the second contour.
2. The method of tooth model segmentation as set forth in claim 1, wherein the determining a set of reference points comprising points on a single tooth having a curvature less than a curvature threshold based on the first reference point, the second reference point, and a reference axis comprises:
taking the midpoint of the first reference point and the second reference point as a third reference point;
Determining a target range based on the third reference point, the reference axis, and a reference radius;
and selecting points with curvature smaller than the curvature threshold from points of the three-dimensional dental model in the target range as a reference point set.
3. The method of tooth model segmentation according to claim 2, wherein the three-dimensional dental model is composed of a plurality of triangular plates, and wherein the removing points located within a reference range on the top surface of a single tooth from the set of reference points results in a set of target points, comprising:
starting from the third reference point, extending along the reference axis to intersect with the reference point set to obtain a fourth reference point;
acquiring a first triangular plate where the first reference point is located, a second triangular plate where the second reference point is located and a third triangular plate where the fourth reference point is located;
starting to extend outwards from the third triangular plate until the third triangular plate extends to the first triangular plate and the second triangular plate to obtain a reference range, wherein points in the reference range are arranged according to the sequence of extension;
and removing points in the reference range from the reference point set to obtain a target point set.
4. The tooth model segmentation method as set forth in claim 1, further comprising, after the determining a target contour based on the first contour and the second contour:
taking the midpoints of the first effective point and the second effective point as a fifth reference point;
determining a defined point based on the first effective point, the second effective point, the fifth reference point, the reference axis, and the set of target points;
and adjusting the target contour line based on the target contour line and the limiting point to obtain an updated contour line.
5. The tooth model segmentation method as set forth in claim 1, further comprising, after the determining a target contour based on the first contour and the second contour:
acquiring a control point on the target contour line at intervals of reference length;
generating a smooth curve based on a plurality of control points;
finding a point closest to each point on the smooth curve in the target point set to obtain a plurality of mark points;
a smooth contour line is generated based on the plurality of marker points.
6. A tooth model segmentation apparatus, comprising:
The acquisition module is used for acquiring a three-dimensional dental model and respectively selecting a first reference point and a second reference point which are positioned at a groove on one side of the top surface of a single tooth based on the three-dimensional dental model;
the first determining module is used for determining a reference point set formed by points with curvature smaller than a curvature threshold value on a single tooth based on the first reference point, the second reference point and a reference axis, removing points in a reference range on the top surface of the single tooth from the reference point set to obtain a target point set, wherein the reference axis is a straight line pointing to the cusp direction from the root of the single tooth, and the reference range is within the outer contour of the top surface of the single tooth;
a second determining module, configured to determine a first effective point and a second effective point from the target point set based on the first reference point, the second reference point and the reference axis, and determine a target contour line based on the first effective point, the second effective point and the target point set, where the first effective point and the second effective point are located at a groove on a top surface side of a single tooth, respectively;
a segmentation module for segmenting a plurality of single tooth models from the three-dimensional dental model based on the target contour line;
The second determining module is specifically configured to:
determining a tangent line between a plane formed by the first reference point, the second reference point and the reference axis and the target point set;
determining a point closest to the first reference point from the set of target points as a first effective point along a direction from the second reference point to the first reference point on the tangent line;
determining a point closest to a second reference point from the set of target points as a second effective point along a direction from the first reference point to the second reference point on the tangent line;
the three-dimensional dental model is composed of a plurality of triangular plates, and the second determining module is specifically further used for:
searching the shortest path connected to the second effective point from the target point set by taking the first effective point as a starting point to obtain a first contour line;
expanding all points except the first effective point and the second effective point on the first contour line outwards by a target number of triangular plates, and deleting the points in the target number of triangular plates from the target point set to obtain an alternative point set;
searching the shortest path connected to the second effective point from the alternative point set by taking the first effective point as a starting point, and determining a second contour line;
A target contour is determined based on the first contour and the second contour.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the tooth model segmentation method of any one of claims 1 to 5 when the program is executed by the processor.
8. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the tooth model segmentation method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210434419.2A CN114897924B (en) | 2022-04-24 | 2022-04-24 | Tooth model segmentation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210434419.2A CN114897924B (en) | 2022-04-24 | 2022-04-24 | Tooth model segmentation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114897924A CN114897924A (en) | 2022-08-12 |
| CN114897924B true CN114897924B (en) | 2023-10-17 |
Family
ID=82716669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210434419.2A Active CN114897924B (en) | 2022-04-24 | 2022-04-24 | Tooth model segmentation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114897924B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228549A (en) * | 2016-07-14 | 2016-12-14 | 嘉兴学院 | A kind of triangle gridding tooth dividing method based on path planning |
| CN108470365A (en) * | 2018-03-07 | 2018-08-31 | 天津工业大学 | A kind of arch wire method for drafting based on upper lower tooth jaw |
| CN108986111A (en) * | 2018-07-02 | 2018-12-11 | 西安增材制造国家研究院有限公司 | A kind of three-dimensional dentognathic model dividing method for area of computer aided stealth correction |
| KR20200005844A (en) * | 2018-07-09 | 2020-01-17 | 오스템임플란트 주식회사 | Tooth Setup Apparatus And Method Using Ideal Arch |
| CN111968146A (en) * | 2020-07-14 | 2020-11-20 | 电子科技大学 | Three-dimensional tooth jaw mesh model segmentation method |
| CN112085740A (en) * | 2020-08-21 | 2020-12-15 | 江苏微云人工智能有限公司 | Tooth fast segmentation method based on three-dimensional tooth jaw model |
| WO2021110938A1 (en) * | 2019-12-06 | 2021-06-10 | 3Shape A/S | Method for generating edge curve for dental devices |
-
2022
- 2022-04-24 CN CN202210434419.2A patent/CN114897924B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228549A (en) * | 2016-07-14 | 2016-12-14 | 嘉兴学院 | A kind of triangle gridding tooth dividing method based on path planning |
| CN108470365A (en) * | 2018-03-07 | 2018-08-31 | 天津工业大学 | A kind of arch wire method for drafting based on upper lower tooth jaw |
| CN108986111A (en) * | 2018-07-02 | 2018-12-11 | 西安增材制造国家研究院有限公司 | A kind of three-dimensional dentognathic model dividing method for area of computer aided stealth correction |
| KR20200005844A (en) * | 2018-07-09 | 2020-01-17 | 오스템임플란트 주식회사 | Tooth Setup Apparatus And Method Using Ideal Arch |
| WO2021110938A1 (en) * | 2019-12-06 | 2021-06-10 | 3Shape A/S | Method for generating edge curve for dental devices |
| CN111968146A (en) * | 2020-07-14 | 2020-11-20 | 电子科技大学 | Three-dimensional tooth jaw mesh model segmentation method |
| CN112085740A (en) * | 2020-08-21 | 2020-12-15 | 江苏微云人工智能有限公司 | Tooth fast segmentation method based on three-dimensional tooth jaw model |
Non-Patent Citations (3)
| Title |
|---|
| 吴婷 ; 张礼兵 ; .3维牙颌模型牙齿分割的路径规划方法.中国图象图形学报.2018,(第01期),全文. * |
| 吴婷 ; 张礼兵 ; .水平集活动轮廓模型的3维牙齿重建.中国图象图形学报.2016,(第08期),全文. * |
| 马亚奇 ; 李忠科 ; 王先泽 ; .基于测地路径的牙齿模型交互分割算法研究.中国图象图形学报.2011,(第04期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114897924A (en) | 2022-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110189352B (en) | Tooth root extraction method based on oral cavity CBCT image | |
| CN106228549B (en) | A kind of triangle gridding tooth dividing method based on path planning | |
| CN105761252B (en) | The method and device of image segmentation | |
| CN110033519B (en) | Three-dimensional modeling method, device and system based on implicit function and storage medium | |
| JP2019536561A (en) | Method and system for brace removal from dentition mesh | |
| CN108648283B (en) | Tooth segmentation method and device | |
| CN112136157B (en) | Method, system and computer program for segmenting dental pulp area from image | |
| CN111991106B (en) | Automatic tooth socket cutting line generation method and application | |
| CN102254317A (en) | Method for automatically extracting dental arch curved surface in dental implantation navigation | |
| CN111968146A (en) | Three-dimensional tooth jaw mesh model segmentation method | |
| CN114549540A (en) | Method for automatically fusing oral scanning tooth data and CBCT (Cone Beam computed tomography) data and application thereof | |
| CN114897924B (en) | Tooth model segmentation method and device | |
| CN112308861B (en) | Tooth and gum segmentation method, tooth segmentation method and electronic equipment | |
| CN114663621A (en) | Three-dimensional dental crown model optimization method based on geometric information | |
| CN108242056B (en) | Three-dimensional tooth grid data segmentation method based on harmonic field algorithm | |
| CN115641325A (en) | Tooth width calculation method of oral tooth scanning model, storage medium and electronic equipment | |
| CN112206064B (en) | Digital dental model generation method and system | |
| CN108198213B (en) | Method and device for marking tubular structure and processing terminal of tubular structure | |
| CN115375720A (en) | Gum margin line generation method, device, computer device and storage medium | |
| US20220391548A1 (en) | Filling a mesh hole | |
| CN114329964A (en) | Filling concave state optimization method and device for tooth digital model | |
| CN114974523A (en) | Fusion method of tooth three-dimensional digital model | |
| CN114652467B (en) | Tooth bracket-free invisible correction method based on computer assistance | |
| CN113920253B (en) | Tooth model fast cutting method based on three-dimensional oral cavity model | |
| CN116385474B (en) | Tooth scanning model segmentation method and device based on deep learning and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |