CN115984529B - Automatic segmentation method for tooth three-dimensional model in oral cavity - Google Patents
Automatic segmentation method for tooth three-dimensional model in oral cavity Download PDFInfo
- Publication number
- CN115984529B CN115984529B CN202310264434.1A CN202310264434A CN115984529B CN 115984529 B CN115984529 B CN 115984529B CN 202310264434 A CN202310264434 A CN 202310264434A CN 115984529 B CN115984529 B CN 115984529B
- Authority
- CN
- China
- Prior art keywords
- tooth
- value
- list
- model
- grid
- 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
Landscapes
- Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
Abstract
The invention provides an automatic segmentation method of an intraoral tooth three-dimensional model, which comprises the steps of obtaining the tooth three-dimensional model through an intraoral CBCT, loading the tooth three-dimensional model into medical modeling software, and in the medical modeling software, carrying out grid division on the tooth three-dimensional model through a grid division algorithm to obtain a tooth three-dimensional finite element model, calculating a curvature edge line through the tooth three-dimensional finite element model, and completing automatic segmentation of the tooth three-dimensional model by utilizing the curvature edge line. The method can improve the segmentation precision of automatic segmentation of the three-dimensional model of the teeth in the oral cavity, accurately segment the individual model of each tooth, avoid over-segmentation or failure of segmentation, improve the actual application quality of the digital oral cavity, reduce the segmentation error caused by the blurring of the edge of the teeth and reduce the diagnosis difficulty of modeling data.
Description
Technical Field
The invention relates to the field of image processing, in particular to an automatic segmentation method for a tooth three-dimensional model in an oral cavity.
Background
In the field of stomatology, medical image scanning is needed to be carried out on teeth in an oral cavity when treatment projects such as implant surgery, implant restoration, orthodontics and periodontal disease are carried out, oral cavity CBCT is a mainstream mode of obtaining oral cavity three-dimensional images by using annular DR, a three-dimensional visual model of the teeth in the oral cavity is obtained by a three-dimensional reconstruction technology, a specific operation scheme can be designed in an assisted manner in the treatment process, and meanwhile, more detailed and visual oral cavity data can be provided by the three-dimensional model, so that diagnosis difficulty is greatly reduced.
Tooth segmentation is the technical foundation of automatic tooth arrangement, and automatic segmentation is completed on the teeth in the three-dimensional model through the technologies of 3D digital imaging, digital oral cavity and the like, so that each tooth is separated for clinical diagnosis, and the working efficiency and the service quality in the diagnosis process can be fully improved. However, due to different three-dimensional characteristics of teeth in the oral cavity of different patients, for example, the teeth of some patients have the phenomena of nonstandard structure, missing teeth, decayed teeth or malformation, and the like, the automatic segmentation of the teeth has wrong recognition results, and the tooth model still needs to be manually adjusted according to the actual situation. Therefore, how to complete high-precision automatic segmentation of teeth in a three-dimensional model of oral teeth is a key to complete the design of a digital surgical scheme.
Disclosure of Invention
The invention aims to provide an automatic segmentation method of an intraoral tooth three-dimensional model, which aims to solve one or more technical problems in the prior art and at least provides a beneficial selection or creation condition.
The invention provides an automatic segmentation method of an intraoral tooth three-dimensional model, which comprises the steps of obtaining the tooth three-dimensional model through an intraoral CBCT, loading the tooth three-dimensional model into medical modeling software, and in the medical modeling software, carrying out grid division on the tooth three-dimensional model through a grid division algorithm to obtain a tooth three-dimensional finite element model, calculating a curvature edge line through the tooth three-dimensional finite element model, and completing automatic segmentation of the tooth three-dimensional model by utilizing the curvature edge line. The method can improve the segmentation precision of automatic segmentation of the three-dimensional model of the teeth in the oral cavity, accurately segment the individual model of each tooth, avoid excessive segmentation or failure in segmentation, improve the actual application quality of the digital oral cavity, reduce the segmentation error caused by the blurring of the edge of the teeth, and reduce the diagnosis difficulty of modeling data.
To achieve the above object, according to an aspect of the present disclosure, there is provided an automatic segmentation method of an intraoral dental three-dimensional model, the method comprising the steps of:
s100, acquiring a tooth three-dimensional model through oral cavity CBCT, and loading the tooth three-dimensional model into medical modeling software;
s200, in medical modeling software, carrying out grid division on the tooth three-dimensional model through a grid division algorithm to obtain a tooth three-dimensional finite element model;
s300, calculating curvature edge lines through a tooth three-dimensional finite element model;
s400, utilizing the curvature edge line to complete automatic segmentation of the tooth three-dimensional model.
Further, in step S100, the Medical modeling software is any one of 3D-vector, geomic Wrap, within Medical, medical Design Studio.
Optionally, in step S100, the method for obtaining the three-dimensional model of the tooth through oral CBCT specifically includes: the method comprises the steps of scanning teeth of a patient through oral CBCT to obtain a plurality of DICOM-format tooth images, inputting the DICOM-format tooth images into Mimics software, opening a New Mask panel in a SEGMENT menu in the Mimics software, setting a Min parameter item to 3000HU in the New Mask panel, and clicking for determination to obtain a three-dimensional model of the teeth.
Optionally, in step S200, in the medical modeling software, the method for obtaining the three-dimensional finite element model of the tooth specifically includes: importing a tooth three-dimensional model into medical modeling software, setting a first boundary condition that the minimum quadrilateral internal angle is larger than D1 degrees and the maximum quadrilateral internal angle is smaller than D2 degrees, setting a second boundary condition that the minimum triangle internal angle is larger than D3 degrees and the minimum triangle internal angle is smaller than D4 degrees, taking the first boundary condition and the second boundary condition as model constraints, and in the medical modeling software, selecting Free parameters in a Mesh Generation panel to complete grid division (selecting Free parameters to complete division by using a Free grid division algorithm) to obtain a tooth three-dimensional finite element model; wherein D1 is set as [30,40], D2 is set as [130,140], D3 is set as [10,20], D4 is set as [140,150], and D1, D2, D3, D4 are angles.
Further, in step S300, the method for calculating the curvature edge line by the tooth three-dimensional finite element model specifically includes:
s301, importing the tooth three-dimensional finite element model into finite element analysis software, calculating the stress magnitude of each grid in the tooth three-dimensional finite element model through stress analysis in the finite element analysis software, and recording the stress magnitude of the ith grid as N i I=1, 2, …, M is the number of all grids in the three-dimensional finite element model of the tooth (after grid division), and the number of M is N 1 ,N 2 ,…,N M Forming a stress sequence, and respectively recording the element with the largest value and the element with the smallest value in the stress sequence as a first intersecting element N c1 And sub-cross element N c2 Go to S302;
s302, initializing integer variables j=1, j epsilon [1, M ], setting two zero-value variables to be roll_a=0 and roll_b=0 respectively, and creating two blank sequences to be list_a and list_b respectively;
s303, updating the value of roll_a to N c1 Subtracting N j Updating roll_b to a value of N j Subtracting N c2 Comparing the current value of roll_a with the value of roll_b; when roll_a>When roll_b is executed, adding the value of the current variable j into the sequence list_a; when roll_a is less than or equal to roll_b, adding the value of the current variable j into the sequence list_b;
s304, if the value of the current variable j is smaller than M, the value of the variable j is increased by 1, and the process goes to S303; if the value of the current variable j is equal to M, creating a blank array Am, and turning to S305;
s305, list_a(k1) For the kth 1 element in sequence list_a, note that list_b (k 2) is the kth 2 element in sequence list_b, k1=1, 2, …, M1, k2=1, 2, …, M2, M1 is the number of all elements in sequence list_a, M2 is the number of all elements in sequence list_b, note that na1= [ N list_a(1) +N list_a(2) +…+N list_a(M1) ]M1, NA2 = [ N list_b(1) +N list_b(2) +…+N list_b(M2) ]M2; wherein k1 and k2 are serial numbers;
s306, when NA1 is not equal to N c1 When the value of (2) is not equal to N, or c2 If the value of (2) is equal to or greater than the value of (S307); when NA1 has a value equal to N c1 When the value of (2) or when the value of NA2 is equal to N c2 When the value of (2) is equal to or greater than the value of (3), go to S308;
s307, a1= [ list_a (1) +list_a (2) + … +list_a (M1)]M1, note a2= [ list_b (1) +list_b (2) + … +list_b (M2)]M2, first crossing element N c1 Updates the value of (1) to the current value of NA1, and crosses the first element N c2 Updating the value of (a) to the current value of NA2, and adding the value of A1 and the value of A2 into an array Am; resetting the value of the variable j to 1, resetting the value of the variable roll_a to 0, resetting the value of the variable roll_b to 0, clearing all elements in the sequence list_a, clearing all elements in the sequence list_b, and turning to S303;
s308, recording Am (k) as the kth element in the array Am, wherein k is a sequence number, sequentially updating the value of each Am (k) in the array to INT (Am (k)), wherein INT () represents the upward rounding of the number in brackets, initializing variables k3=1, k3 epsilon [1, L ], and L as the number of all elements in the array Am;
s309, from k3=1, traversing k3 in the value range of k3, and screening out the jurisdictional shrinkage grids belonging to the Am (k 3) th grid from all grids of the tooth three-dimensional finite element model, and recording curvature edge lines as follows: connecting the center of each jurisdictional shrinkage grid belonging to the Am (k 3) grid with the center of the Am (k 3) grid in sequence in a straight line to obtain a line segment;
the method for screening the jurisdictional grids belonging to the Am (k 3) grid specifically comprises the following steps: recording any grid in the tooth three-dimensional finite element model as A, connecting the center of the A with the center of the Am (k 3) th grid to obtain a LINE segment, and recording the length of the LINE segment as D; and constructing a circle O1 by taking the midpoint of the LINE as the center and taking D/2 as the radius, and recording the current grid A as a contracted grid belonging to the Am (k 3) th grid when the center of no grid in the tooth three-dimensional finite element model is contained in the circle O1.
The beneficial effects of this step are: in the process of establishing a three-dimensional tooth model through CT images to complete tooth segmentation, because of large differences in shape characteristics and growth positions of different teeth, independent segmentation of a single tooth is difficult, and under the conditions that adjacent teeth are adhered, excessive embedded in gum or tooth root structure differences are large, each tooth is difficult to separate clearly and correctly through a common tooth segmentation algorithm, curvature edge lines in the tooth model can be calculated by the method of the step, the area with fuzzy degree of distinction can be correctly divided by the curvature edge lines, the area belonging to correct division can be prevented from being incorrectly segmented by constructing a contracted grid, the phenomenon of segmentation error is avoided, and the segmentation accuracy and the model quality of automatic tooth arrangement can be improved by adding the curvature edge lines in the model.
Further, in step S400, the method for automatically segmenting the tooth three-dimensional model by using the curvature edge line specifically includes: and loading the tooth three-dimensional model into the chemicals software, adding all curvature edge lines into the tooth three-dimensional model through an Edit Masks tool in the chemicals software to serve as auxiliary parting lines, and loading the auxiliary parting lines through a Region Grow function (namely, a Region growing algorithm is called to finish parting) in the chemicals software to finish parting the teeth.
Because of the phenomenon of excessive segmentation in the automatic tooth segmentation process, the segmentation area is wrongly divided, which is easy to cause inaccurate tooth segmentation, in order to solve the problem and improve the automatic segmentation precision, the method for completing the automatic segmentation of the tooth three-dimensional model by using the curvature edge line can also be as follows:
preferably, in the tooth three-dimensional finite element model, a closed area formed by all curvature edge lines with an intersection relationship is recorded as a jurisdiction shrinkage area, a stress intersection value of each jurisdiction shrinkage area is calculated, two adjacent jurisdiction shrinkage areas are screened out from all jurisdiction shrinkage areas and recorded as manifold areas, whether the manifold areas belong to point state areas is judged, the manifold areas belonging to the point state areas are combined (namely, the two jurisdiction shrinkage areas in the manifold areas are combined into one jurisdiction shrinkage area), the curvature edge lines in the combined manifold areas are deleted, the tooth three-dimensional model is loaded in Mimics software, all curvature edge lines are added to the tooth three-dimensional model through an Edit Masks tool in the Mimics software to serve as auxiliary dividing lines, and the auxiliary dividing lines are loaded through a Region Grow function (namely, dividing is completed by calling a Region growing algorithm) in the Mimics software to complete tooth dividing;
the method for calculating the stress crossing value of each jurisdiction shrinkage area comprises the following steps: the stress on the (r) th grid in the jurisdiction shrinkage area is Q r R is a variable, r=1, 2, …, R and R are the number of all grids in the jurisdiction shrinkage region, and the stress of the grid with the largest stress value in the jurisdiction shrinkage region is recorded as Q M Starting from r=1, Q is sequentially taken up M Subtracting each Q r Obtaining R values T 1 ,T 2 ,…,T R Let sum (T) =t 1 + T 2 +…+ T R The sqrt (1/(R-1) sum (T)) is recorded as a stress crossing value of a contracted area, and the sqrt () represents root number calculation of numbers in brackets;
the method for judging whether the manifold area belongs to the point state area comprises the following steps: respectively marking two jurisdictional areas in the manifold area as A1 and A2 (the manifold area is formed by two adjacent jurisdictional areas), marking the number of grids in the A1 as G1 and marking the number of grids in the A2 as G2;
when the value of G1 is larger than the value of G2, storing the values of the stress magnitudes of all grids in A2 by using a SET2, arbitrarily selecting G2 grids in A1 to be marked as observation grids, storing the values of the stress magnitudes of all observation grids by using the SET1, and storing the values of the stress magnitudes of all non-observation grids by using a SET3, wherein the non-observation grids are grids which are not selected as observation grids in A1;
when the value of G1 is smaller than the value of G2, storing the values of the stress magnitudes of all grids in A1 by using a SET2, arbitrarily selecting G1 grids in A2 to be marked as observation grids, storing the values of the stress magnitudes of all observation grids by using the SET2, and storing the values of the stress magnitudes of all non-observation grids by using a SET3, wherein the non-observation grids are grids which are not selected as observation grids in A2;
note that S (n) =sqrt (SET 1 (n)). SET2 (n), where SET1 (n) represents the nth element in SET1, SET2 (n) represents the nth element in SET2, n=1, 2, …, min { G1, G2}, sqrt () represents a root operation on the number in brackets, min { } represents a minimum value on the number in { }; when sum (S (n))/sum (SET 3) is greater than A1_CR/A2_CR, the manifold region belongs to the point state region; where sum (S (n))=s (1) +s (2) + … +s (G2), sum (SET 3) represents the sum of all elements in SET3, a1_cr is the stress crossing value of jurisdictional region A1, and a2_cr is the stress crossing value of jurisdictional region A2.
The beneficial effects of this step are: because the model is excessively segmented, namely an incomplete tooth individual model is generated, the step integrates manifold areas by calculating stress crossing values of the jurisdiction shrinkage areas, eliminates curvature edge lines influencing segmentation results, improves segmentation accuracy to the greatest extent while keeping the model integrity, avoids the problem of excessive segmentation, and can further improve segmentation accuracy.
The beneficial effects of the invention are as follows: the method can improve the segmentation precision of automatic segmentation of the three-dimensional model of the teeth in the oral cavity, accurately segment the individual model of each tooth, avoid excessive segmentation or failure in segmentation, improve the actual application quality of the digital oral cavity, reduce the segmentation error caused by the blurring of the edge of the teeth, and reduce the diagnosis difficulty of modeling data.
Drawings
The above and other features of the present disclosure will become more apparent from the detailed description of the embodiments illustrated in the accompanying drawings, in which like reference numerals designate like or similar elements, and which, as will be apparent to those of ordinary skill in the art, are merely some examples of the present disclosure, from which other drawings may be made without inventive effort, wherein:
FIG. 1 is a flow chart of a method for automatically segmenting a three-dimensional model of teeth in an oral cavity;
Detailed Description
The conception, specific structure, and technical effects produced by the present disclosure will be clearly and completely described below in connection with the embodiments and the drawings to fully understand the objects, aspects, and effects of the present disclosure. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
In the description of the present invention, a number means one or more, a number means two or more, and greater than, less than, exceeding, etc. are understood to not include the present number, and above, below, within, etc. are understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
Referring to fig. 1, a flowchart of an automatic intra-oral tooth three-dimensional model segmentation method according to the present invention is shown, and an automatic intra-oral tooth three-dimensional model segmentation method according to an embodiment of the present invention is described below with reference to fig. 1.
The present disclosure proposes an automatic segmentation method of an intraoral dental three-dimensional model, the method comprising the steps of:
s100, acquiring a tooth three-dimensional model through oral cavity CBCT, and loading the tooth three-dimensional model into medical modeling software;
s200, in medical modeling software, carrying out grid division on the tooth three-dimensional model through a grid division algorithm to obtain a tooth three-dimensional finite element model;
s300, calculating curvature edge lines through a tooth three-dimensional finite element model;
s400, utilizing the curvature edge line to complete automatic segmentation of the tooth three-dimensional model.
Further, in step S100, the Medical modeling software is any one of 3D-vector, geomic Wrap, within Medical, medical Design Studio.
Optionally, in step S100, the method for obtaining the three-dimensional model of the tooth through oral CBCT specifically includes: the method comprises the steps of scanning teeth of a patient through oral CBCT to obtain a plurality of DICOM-format tooth images, inputting the DICOM-format tooth images into Mimics software, opening a New Mask panel in a SEGMENT menu in the Mimics software, setting a Min parameter item to 3000HU in the New Mask panel, and clicking for determination to obtain a three-dimensional model of the teeth.
Optionally, in step S200, in the medical modeling software, the method for obtaining the three-dimensional finite element model of the tooth specifically includes: importing a tooth three-dimensional model into medical modeling software, setting a first boundary condition that the minimum quadrilateral internal angle is larger than D1 degrees and the maximum quadrilateral internal angle is smaller than D2 degrees, setting a second boundary condition that the minimum triangle internal angle is larger than D3 degrees and the minimum triangle internal angle is smaller than D4 degrees, taking the first boundary condition and the second boundary condition as model constraints, and in the medical modeling software, selecting Free parameters in a Mesh Generation panel to complete grid division (selecting Free parameters to complete division by using a Free grid division algorithm) to obtain a tooth three-dimensional finite element model; wherein D1 is set as [30,40], D2 is set as [130,140], D3 is set as [10,20], D4 is set as [140,150], and D1, D2, D3, D4 are angles.
Further, in step S300, the method for calculating the curvature edge line by the tooth three-dimensional finite element model specifically includes:
s301, importing the tooth three-dimensional finite element model into finite element analysis software, calculating the stress magnitude of each grid in the tooth three-dimensional finite element model through stress analysis in the finite element analysis software, and recording the stress magnitude of the ith grid as N i I=1, 2, …, M is the number of all grids in the three-dimensional finite element model of the tooth (after grid division), and the number of M is N 1 ,N 2 ,…,N M Forming a stress sequence, and respectively recording the element with the largest value and the element with the smallest value in the stress sequence as a first intersecting element N c1 And sub-cross element N c2 Go to S302;
s302, initializing integer variables j=1, j epsilon [1, M ], setting two zero-value variables to be roll_a=0 and roll_b=0 respectively, and creating two blank sequences to be list_a and list_b respectively;
s303, updating the value of roll_a to N c1 Subtracting N j Updating roll_b to a value of N j Subtracting N c2 Comparing the current value of roll_a with the value of roll_b; when roll_a>When roll_b is executed, adding the value of the current variable j into the sequence list_a; when roll_a is less than or equal to roll_b, adding the value of the current variable j into the sequence list_b;
s304, if the value of the current variable j is smaller than M, the value of the variable j is increased by 1, and the process goes to S303; if the value of the current variable j is equal to M, creating a blank array Am, and turning to S305;
s305, note that list_a (k 1) is the kth 1 element in sequence list_a, note that list_b (k 2) is the kth 2 element in sequence list_b, k1=1, 2, …, M1, k2=1, 2, …, M2, M1 is the number of all elements in sequence list_a, M2 is the number of all elements in sequence list_b, note that na1= [ N list_a(1) +N list_a(2) +…+N list_a(M1) ]M1, NA2 = [ N list_b(1) +N list_b(2) +…+N list_b(M2) ]M2; wherein k1 and k2 are serial numbers;
s306, when NA1 is not equal to N c1 When the value of (2) is not equal to N, or c2 If the value of (2) is equal to or greater than the value of (S307); when NA1 has a value equal to N c1 When the value of (2) or when the value of NA2 is equal to N c2 When the value of (2) is equal to or greater than the value of (3), go to S308;
s307, a1= [ list_a (1) +list_a (2) + … +list_a (M1)]M1, note a2= [ list_b (1) +list_b (2) + … +list_b (M2)]M2, first crossing element N c1 Updates the value of (1) to the current value of NA1, and crosses the first element N c2 Updating the value of (a) to the current value of NA2, and adding the value of A1 and the value of A2 into an array Am; resetting the value of the variable j to 1, resetting the value of the variable roll_a to 0, resetting the value of the variable roll_b to 0, clearing all elements in the sequence list_a, clearing all elements in the sequence list_b, and turning to S303;
s308, recording Am (k) as the kth element in the array Am, wherein k is a sequence number, sequentially updating the value of each Am (k) in the array to INT (Am (k)), wherein INT () represents the upward rounding of the number in brackets, initializing variables k3=1, k3 epsilon [1, L ], and L as the number of all elements in the array Am;
s309, from k3=1, traversing k3 in the value range of k3, and screening out the jurisdictional shrinkage grids belonging to the Am (k 3) th grid from all grids of the tooth three-dimensional finite element model, and recording curvature edge lines as follows: connecting the center of each jurisdictional shrinkage grid belonging to the Am (k 3) grid with the center of the Am (k 3) grid in sequence in a straight line to obtain a line segment;
the method for screening the jurisdictional grids belonging to the Am (k 3) grid specifically comprises the following steps: recording any grid in the tooth three-dimensional finite element model as A, connecting the center of the A with the center of the Am (k 3) th grid to obtain a LINE segment, and recording the length of the LINE segment as D; and constructing a circle O1 by taking the midpoint of the LINE as the center and taking D/2 as the radius, and recording the current grid A as a contracted grid belonging to the Am (k 3) th grid when the center of no grid in the tooth three-dimensional finite element model is contained in the circle O1.
Further, in step S400, the method for automatically segmenting the tooth three-dimensional model by using the curvature edge line specifically includes: and loading the tooth three-dimensional model into the chemicals software, adding all curvature edge lines into the tooth three-dimensional model through an Edit Masks tool in the chemicals software to serve as auxiliary parting lines, and loading the auxiliary parting lines through a Region Grow function (namely, a Region growing algorithm is called to finish parting) in the chemicals software to finish parting the teeth.
Because of the phenomenon of excessive segmentation in the automatic tooth segmentation process, the segmentation area is wrongly divided, which is easy to cause inaccurate tooth segmentation, in order to solve the problem and improve the automatic segmentation precision, the method for completing the automatic segmentation of the tooth three-dimensional model by using the curvature edge line can also be as follows:
preferably, in the tooth three-dimensional finite element model, a closed area formed by all curvature edge lines with an intersection relationship is recorded as a jurisdiction shrinkage area, a stress intersection value of each jurisdiction shrinkage area is calculated, two adjacent jurisdiction shrinkage areas are screened out from all jurisdiction shrinkage areas and recorded as manifold areas, whether the manifold areas belong to point state areas is judged, the manifold areas belonging to the point state areas are combined (namely, the two jurisdiction shrinkage areas in the manifold areas are combined into one jurisdiction shrinkage area), the curvature edge lines in the combined manifold areas are deleted, the tooth three-dimensional model is loaded in Mimics software, all curvature edge lines are added to the tooth three-dimensional model through an Edit Masks tool in the Mimics software to serve as auxiliary dividing lines, and the auxiliary dividing lines are loaded through a Region Grow function (namely, dividing is completed by calling a Region growing algorithm) in the Mimics software to complete tooth dividing;
the method for calculating the stress crossing value of each jurisdiction shrinkage area comprises the following steps: the stress on the (r) th grid in the jurisdiction shrinkage area is Q r R is a variable, r=1, 2, …, R and R are the number of all grids in the jurisdiction shrinkage region, and the stress of the grid with the largest stress value in the jurisdiction shrinkage region is recorded as Q M Starting from r=1, Q is sequentially taken up M Subtracting each Q r Obtaining R values T 1 ,T 2 ,…,T R Let sum (T) =t 1 + T 2 +…+ T R The sqrt (1/(R-1) sum (T)) is recorded as a stress crossing value of a contracted area, and the sqrt () represents root number calculation of numbers in brackets;
the method for judging whether the manifold area belongs to the point state area comprises the following steps: respectively marking two jurisdictional areas in the manifold area as A1 and A2 (the manifold area is formed by two adjacent jurisdictional areas), marking the number of grids in the A1 as G1 and marking the number of grids in the A2 as G2;
when the value of G1 is larger than the value of G2, storing the values of the stress magnitudes of all grids in A2 by using a SET2, arbitrarily selecting G2 grids in A1 to be marked as observation grids, storing the values of the stress magnitudes of all observation grids by using the SET1, and storing the values of the stress magnitudes of all non-observation grids by using a SET3, wherein the non-observation grids are grids which are not selected as observation grids in A1;
when the value of G1 is smaller than the value of G2, storing the values of the stress magnitudes of all grids in A1 by using a SET2, arbitrarily selecting G1 grids in A2 to be marked as observation grids, storing the values of the stress magnitudes of all observation grids by using the SET2, and storing the values of the stress magnitudes of all non-observation grids by using a SET3, wherein the non-observation grids are grids which are not selected as observation grids in A2;
note that S (n) =sqrt (SET 1 (n)). SET2 (n), where SET1 (n) represents the nth element in SET1, SET2 (n) represents the nth element in SET2, n=1, 2, …, min { G1, G2}, sqrt () represents a root operation on the number in brackets, min { } represents a minimum value on the number in { }; when sum (S (n))/sum (SET 3) is greater than A1_CR/A2_CR, the manifold region belongs to the point state region; where sum (S (n))=s (1) +s (2) + … +s (G2), sum (SET 3) represents the sum of all elements in SET3, a1_cr is the stress crossing value of jurisdictional region A1, and a2_cr is the stress crossing value of jurisdictional region A2.
The invention provides an automatic segmentation method of an intraoral tooth three-dimensional model, which comprises the steps of obtaining the tooth three-dimensional model through an intraoral CBCT, loading the tooth three-dimensional model into medical modeling software, and in the medical modeling software, carrying out grid division on the tooth three-dimensional model through a grid division algorithm to obtain a tooth three-dimensional finite element model, calculating a curvature edge line through the tooth three-dimensional finite element model, and completing automatic segmentation of the tooth three-dimensional model by utilizing the curvature edge line. The method can improve the segmentation precision of automatic segmentation of the three-dimensional model of the teeth in the oral cavity, accurately segment the individual model of each tooth, avoid excessive segmentation or failure in segmentation, improve the actual application quality of the digital oral cavity, reduce the segmentation error caused by the blurring of the edge of the teeth, and reduce the diagnosis difficulty of modeling data.
Although the description of the present disclosure has been illustrated in considerable detail and with particularity, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively cover the intended scope of the present disclosure. Furthermore, the foregoing description of the present disclosure has been presented in terms of embodiments foreseen by the inventor for the purpose of providing a enabling description for enabling the enabling description to be available, notwithstanding that insubstantial changes in the disclosure, not presently foreseen, may nonetheless represent equivalents thereto.
Claims (6)
1. An automatic segmentation method for a tooth three-dimensional model in an oral cavity, which is characterized by comprising the following steps of:
s100, acquiring a tooth three-dimensional model through oral cavity CBCT, and loading the tooth three-dimensional model into medical modeling software;
s200, in medical modeling software, carrying out grid division on the tooth three-dimensional model through a grid division algorithm to obtain a tooth three-dimensional finite element model;
s300, calculating curvature edge lines through a tooth three-dimensional finite element model;
s400, utilizing curvature edge lines to complete automatic segmentation of the tooth three-dimensional model;
in step S300, the method for calculating the curvature edge line through the tooth three-dimensional finite element model specifically includes:
s301, importing the tooth three-dimensional finite element model into finite element analysis software, calculating the stress magnitude of each grid in the tooth three-dimensional finite element model through stress analysis in the finite element analysis software, and recording the stress magnitude of the ith grid as N i I=1, 2, …, M is the number of all meshes in the three-dimensional finite element model of the tooth, and the number of M is N 1 ,N 2 ,…,N M Forming a stress sequence, and respectively recording the element with the largest value and the element with the smallest value in the stress sequence as a first intersecting element N c1 And sub-cross element N c2 Go to S302;
s302, initializing integer variables j=1, j epsilon [1, M ], setting two zero-value variables to be roll_a=0 and roll_b=0 respectively, and creating two blank sequences to be list_a and list_b respectively;
s303, updating the value of roll_a to N c1 Subtracting N j Updating roll_b to a value of N j Subtracting N c2 Comparing the current value of roll_a with the value of roll_b; when roll_a>When roll_b is executed, adding the value of the current variable j into the sequence list_a; when roll_a is less than or equal to roll_b, adding the value of the current variable j into the sequence list_b;
s304, if the value of the current variable j is smaller than M, the value of the variable j is increased by 1, and the process goes to S303; if the value of the current variable j is equal to M, creating a blank array Am, and turning to S305;
s305. note that list_a (k 1) is the kth 1 element in sequence list_a, list_b (k 2) is the kth 2 element in sequence list_b, k1=1, 2, …, M1, k2=1, 2, …M2, M1 is the number of all elements in the sequence list_a, M2 is the number of all elements in the sequence list_b, and Na1= [ N ] list_a(1) +N list_a(2) +…+N list_a(M1) ]M1, NA2 = [ N list_b(1) +N list_b(2) +…+N list_b(M2) ]M2; wherein k1 and k2 are serial numbers;
s306, when NA1 is not equal to N c1 When the value of (2) is not equal to N, or c2 If the value of (2) is equal to or greater than the value of (S307); when NA1 has a value equal to N c1 When the value of (2) or when the value of NA2 is equal to N c2 When the value of (2) is equal to or greater than the value of (3), go to S308;
s307, a1= [ list_a (1) +list_a (2) + … +list_a (M1)]M1, note a2= [ list_b (1) +list_b (2) + … +list_b (M2)]M2, first crossing element N c1 Updates the value of (1) to the current value of NA1, and crosses the first element N c2 Updating the value of (a) to the current value of NA2, and adding the value of A1 and the value of A2 into an array Am; resetting the value of the variable j to 1, resetting the value of the variable roll_a to 0, resetting the value of the variable roll_b to 0, clearing all elements in the sequence list_a, clearing all elements in the sequence list_b, and turning to S303;
s308, recording Am (k) as the kth element in the array Am, wherein k is a sequence number, sequentially updating the value of each Am (k) in the array to INT (Am (k)), wherein INT () represents the upward rounding of the number in brackets, initializing variables k3=1, k3 epsilon [1, L ], and L as the number of all elements in the array Am;
s309, from k3=1, traversing k3 in the value range of k3, and screening out the jurisdictional shrinkage grids belonging to the Am (k 3) th grid from all grids of the tooth three-dimensional finite element model, and recording curvature edge lines as follows: and connecting the center of each jurisdictional grid belonging to the Am (k 3) grid with the center of the Am (k 3) grid in sequence in a straight line to obtain a line segment.
2. The method according to claim 1, wherein in step S100, the Medical modeling software is any one of 3D-vector, geomic Wrap, within Medical, medical Design Studio.
3. The method for automatically segmenting the three-dimensional model of the tooth in the oral cavity according to claim 1, wherein in the step S100, the method for acquiring the three-dimensional model of the tooth by oral cavity CBCT is specifically as follows: the method comprises the steps of scanning teeth of a patient through oral CBCT to obtain a plurality of DICOM-format tooth images, inputting the DICOM-format tooth images into Mimics software, opening a New Mask panel in a SEGMENT menu in the Mimics software, setting a Min parameter item to 3000HU in the New Mask panel, and clicking for determination to obtain a three-dimensional model of the teeth.
4. The method according to claim 1, wherein in step S200, in the medical modeling software, the three-dimensional model of the tooth is meshed by a meshing algorithm, and the method for obtaining the three-dimensional finite element model of the tooth specifically comprises: importing a tooth three-dimensional model into medical modeling software, setting a first boundary condition that the minimum quadrilateral internal angle is larger than D1 degrees and the maximum quadrilateral internal angle is smaller than D2 degrees, setting a second boundary condition that the minimum triangle internal angle is larger than D3 degrees and the minimum triangle internal angle is smaller than D4 degrees, taking the first boundary condition and the second boundary condition as model constraints, and selecting Free parameters in a Mesh Generation panel in the medical modeling software to complete grid division to obtain a tooth three-dimensional finite element model; wherein D1 is set as [30,40], D2 is set as [130,140], D3 is set as [10,20], D4 is set as [140,150], and D1, D2, D3, D4 are angles.
5. The method for automatically segmenting the three-dimensional model of the tooth in the oral cavity according to claim 1, wherein the method for screening out the jurisdictional shrinkage grids belonging to the Am (k 3) th grid comprises the following steps: recording any grid in the tooth three-dimensional finite element model as A, connecting the center of the A with the center of the Am (k 3) th grid to obtain a LINE segment, and recording the length of the LINE segment as D; and constructing a circle O1 by taking the midpoint of the LINE as the center and taking D/2 as the radius, and recording the current grid A as a contracted grid belonging to the Am (k 3) th grid when the center of no grid in the tooth three-dimensional finite element model is contained in the circle O1.
6. The method according to claim 1, wherein in step S400, the method for automatically segmenting the three-dimensional model of the tooth by using the curvature edge line is specifically as follows: and loading the tooth three-dimensional model into the chemicals software, adding all curvature edge lines into the tooth three-dimensional model through an Edit Masks tool in the chemicals software to serve as auxiliary dividing lines, and loading the auxiliary dividing lines through a Region Grow function in the chemicals software to complete tooth division.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310264434.1A CN115984529B (en) | 2023-03-20 | 2023-03-20 | Automatic segmentation method for tooth three-dimensional model in oral cavity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310264434.1A CN115984529B (en) | 2023-03-20 | 2023-03-20 | Automatic segmentation method for tooth three-dimensional model in oral cavity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115984529A CN115984529A (en) | 2023-04-18 |
| CN115984529B true CN115984529B (en) | 2023-07-18 |
Family
ID=85963476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310264434.1A Active CN115984529B (en) | 2023-03-20 | 2023-03-20 | Automatic segmentation method for tooth three-dimensional model in oral cavity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115984529B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260672A (en) * | 2019-12-26 | 2020-06-09 | 北京大学口腔医学院 | Method for guiding and segmenting teeth by using morphological data |
| WO2021238673A1 (en) * | 2020-05-29 | 2021-12-02 | 先临三维科技股份有限公司 | Tooth scanning method and apparatus, computer device, and computer-readable storage medium |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9421074B2 (en) * | 2001-04-13 | 2016-08-23 | Orametrix, Inc. | Unified three dimensional virtual craniofacial and dentition model and uses thereof |
| US20040064295A1 (en) * | 2002-09-26 | 2004-04-01 | Jiping Zhang | Methods for modular-parametric-finite-element modeling |
| KR100539949B1 (en) * | 2003-11-17 | 2005-12-28 | 삼성전자주식회사 | Method and apparatus for generating 3-dimensional finite element mesh |
| US10426578B2 (en) * | 2006-10-16 | 2019-10-01 | Natural Dental Implants, Ag | Customized dental prosthesis for periodontal or osseointegration and related systems |
| US8359114B2 (en) * | 2006-11-28 | 2013-01-22 | Dentsable, Inc. | Haptically enabled dental modeling system |
| EP2280651A2 (en) * | 2008-05-16 | 2011-02-09 | Geodigm Corporation | Method and apparatus for combining 3d dental scans with other 3d data sets |
| EP3503839B1 (en) * | 2016-08-24 | 2020-10-28 | Carestream Dental Technology Topco Limited | Method and apparatus for hybrid mesh segmentation |
| CN108022247B (en) * | 2016-11-03 | 2021-06-11 | 北京大学口腔医学院 | Method for extracting three-dimensional tooth root morphology of living tooth based on periodontal ligament imaging anatomical features |
| US10722328B2 (en) * | 2017-10-05 | 2020-07-28 | Align Technology, Inc. | Virtual fillers for virtual models of dental arches |
| FR3092427B1 (en) * | 2019-02-04 | 2022-07-08 | Borea | automatic tooth segmentation method |
| CN109903396B (en) * | 2019-03-20 | 2022-12-16 | 洛阳中科信息产业研究院 | Tooth three-dimensional model automatic segmentation method based on curved surface parameterization |
| KR102255592B1 (en) * | 2019-11-19 | 2021-05-25 | 주식회사 레이 | method of processing dental CT images for improving precision of margin line extracted therefrom |
| CN114241173B (en) * | 2021-12-09 | 2023-03-21 | 电子科技大学 | Tooth CBCT image three-dimensional segmentation method and system |
| CN114757960B (en) * | 2022-06-15 | 2022-09-09 | 汉斯夫(杭州)医学科技有限公司 | Tooth segmentation and reconstruction method based on CBCT image and storage medium |
| CN115272585A (en) * | 2022-08-12 | 2022-11-01 | 杭州口腔医院集团有限公司 | Three-dimensional dentition model construction device and method |
-
2023
- 2023-03-20 CN CN202310264434.1A patent/CN115984529B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260672A (en) * | 2019-12-26 | 2020-06-09 | 北京大学口腔医学院 | Method for guiding and segmenting teeth by using morphological data |
| WO2021238673A1 (en) * | 2020-05-29 | 2021-12-02 | 先临三维科技股份有限公司 | Tooth scanning method and apparatus, computer device, and computer-readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于CBCT三维重建数据的尖牙冠根形态研究;艾毅龙;吴斯媛;邹晨;;口腔疾病防治(第06期);第38-42页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115984529A (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11925522B2 (en) | Dental restoration molds | |
| CN115983082B (en) | Method for generating tooth model after predictive orthodontic treatment | |
| CN108735292B (en) | Removable partial denture scheme decision method and system based on artificial intelligence | |
| CN113520641B (en) | Method for constructing a prosthesis | |
| AU2016370731B2 (en) | One-piece dental restoration molds | |
| CN106806030B (en) | A kind of crown root threedimensional model fusion method | |
| CN108986111B (en) | Three-dimensional dental model segmentation method for computer-aided invisible orthodontics | |
| CN108888372B (en) | Intelligent recommendation-based virtual removable denture design method and system | |
| CN109948271B (en) | False tooth repair scheme design method and system based on data decision | |
| KR102004449B1 (en) | method for designing Virtual prosthesis | |
| KR20190074062A (en) | Method for setting Gingival line to design prosthesis | |
| CN216455394U (en) | Prepared guide plate and removable partial denture support | |
| CN111709959A (en) | Digital intelligent diagnosis method for orthodontic treatment | |
| CN113925635B (en) | Construction method and manufacturing method of preparation guide plate and removable partial denture framework model | |
| CN115984529B (en) | Automatic segmentation method for tooth three-dimensional model in oral cavity | |
| CN115272359A (en) | Tooth segmentation method, tooth surface data acquisition method and oral CT (computed tomography) equipment | |
| CN112308861B (en) | Tooth and gum segmentation method, tooth segmentation method and electronic equipment | |
| CN110403725B (en) | Post-operation precision measuring method for implant operation | |
| CN111524065A (en) | Dental crown-based automatic generation method for individual implant abutment | |
| CN112237492B (en) | Method for manufacturing fixed denture matched with dental embolus type attachment | |
| CN112070897B (en) | Preparation method of shell-shaped tooth appliance | |
| CN115252174A (en) | Tooth arrangement method, tooth orthodontics simulation method, storage medium and oral CT (computed tomography) equipment | |
| CN115798728B (en) | Tooth preparation digital model design method based on computer assistance | |
| KR102512005B1 (en) | Automated method for aligning three dimensional single dental model to three dimensional oral scan data and computer readable medium having program for performing the method | |
| KR102670048B1 (en) | Automated method for aligning three dimensional single dental model to three dimensional oral scan data and computer readable medium having program for performing the method |
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 |