CN105741288B - Tooth image segmentation method and apparatus - Google Patents
Tooth image segmentation method and apparatus Download PDFInfo
- Publication number
- CN105741288B CN105741288B CN201610066016.1A CN201610066016A CN105741288B CN 105741288 B CN105741288 B CN 105741288B CN 201610066016 A CN201610066016 A CN 201610066016A CN 105741288 B CN105741288 B CN 105741288B
- Authority
- CN
- China
- Prior art keywords
- tooth
- contour line
- slice image
- initial
- tooth slice
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003709 image segmentation Methods 0.000 title abstract description 17
- 230000011218 segmentation Effects 0.000 claims abstract description 46
- 230000003993 interaction Effects 0.000 claims description 10
- 210000000515 tooth Anatomy 0.000 description 376
- 238000007408 cone-beam computed tomography Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 210000002295 maxillary tooth Anatomy 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000002591 computed tomography Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 210000004871 mandibular tooth Anatomy 0.000 description 2
- 241000270295 Serpentes Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Classifications
-
- 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
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20116—Active contour; Active surface; Snakes
-
- 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
- Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a tooth image segmentation method and apparatus, which relate to the technical field of computers and can solve the problem of relatively low tooth image segmentation efficiency in the prior art. The method mainly comprises the steps of obtaining an initial profile line corresponding to each tooth on an initial tooth slice image; according to an active profile model and the tooth on the initial tooth slice image, adjusting a corresponding initial profile line; based on the adjusted profile line on the initial tooth slice image, segmenting other tooth slice images according to a preset segmentation rule; according to a preset profile line clustering algorithm, clustering profile lines of all teeth to obtain a profile line set corresponding to each tooth; and according to a regional filling algorithm, performing regional filling on each profile line in the profile line set corresponding to each tooth to obtain a pixel space model of each tooth, and calculating the pixel space model of each tooth through an MC algorithm to obtain a three-dimensional grid model of each tooth.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a tooth image segmentation method and device.
Background
With the progress of science and technology, the method for obtaining the tooth image is gradually developed from the traditional Computed Tomography (CT) technology to the Cone Beam Computed Tomography (CBCT) technology, and the two-dimensional tooth image based on the CBCT can be reconstructed to obtain the three-dimensional mesh model of the tooth, so as to help a doctor to make a more accurate judgment on the tooth condition based on the three-dimensional mesh model.
In practical application, the concrete implementation method for reconstructing the two-dimensional tooth image of the CBCT into the three-dimensional grid model image comprises the following steps: the method comprises the steps of firstly segmenting a two-dimensional tooth image to obtain a pixel space model of each tooth, then calculating the pixel space model of each tooth according to algorithms such as MC (MarchingCubes) and the like, and finally obtaining a set of three-dimensional mesh models of the teeth. In the prior art, software for segmenting a tooth image based on CBCT mainly comprises Amira software and Mimics software. However, both the segmentation based on Amira software and the segmentation based on Mimics software require manual participation and can only segment a single tooth, but cannot segment multiple teeth simultaneously, so that it takes a long time to obtain pixel space models of all teeth, and the efficiency of obtaining a set of three-dimensional mesh models of teeth is low.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for segmenting a dental image, which can solve the problem of low efficiency in segmenting a dental image in the prior art.
According to an aspect of the present invention, there is provided a method of segmenting a dental image, the method comprising:
acquiring an initial contour line corresponding to each tooth on an initial tooth slice image, wherein the initial tooth slice image is an image which is selected by a user from all tooth slice images and contains maxillary teeth or mandibular teeth;
adjusting the corresponding initial contour line according to the active contour model and the teeth on the initial tooth slice image to obtain an adjusted contour line;
based on the adjusted contour line on the initial tooth slice image, segmenting other tooth slice images according to a preset segmentation rule to obtain a contour line corresponding to each tooth on the other tooth slice images;
clustering the contour lines of all teeth according to a preset contour line clustering algorithm to obtain a contour line set corresponding to each tooth;
and according to a region filling algorithm, performing region filling on each contour line in the contour line set corresponding to each tooth to obtain a pixel space model of each tooth, so that after pixel space models of all maxillary teeth and all mandibular teeth are obtained, the pixel space model of each tooth is calculated through an MC algorithm to obtain a three-dimensional mesh model of each tooth.
According to another aspect of the present invention, there is provided a dental image segmentation apparatus, comprising:
the system comprises an acquisition unit, a comparison unit and a processing unit, wherein the acquisition unit is used for acquiring an initial contour line corresponding to each tooth on an initial tooth slice image, and the initial tooth slice image is an image which is selected by a user from all tooth slice images and contains maxillary teeth or mandibular teeth;
the adjusting unit is used for adjusting the corresponding initial contour line obtained by the obtaining unit according to the active contour model and the teeth on the initial tooth slice image to obtain an adjusted contour line;
the segmentation unit is used for segmenting other tooth slice images according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image obtained by the adjustment unit to obtain a contour line corresponding to each tooth on the other tooth slice images;
the clustering unit is used for clustering the contour lines of all teeth according to a preset contour line clustering algorithm to obtain a contour line set corresponding to each tooth;
and the filling unit is used for performing region filling on each contour line in the contour line set corresponding to each tooth obtained by the clustering unit according to a region filling algorithm to obtain a pixel space model of each tooth, so that after pixel space models of all maxillary teeth and all mandibular teeth are obtained, the pixel space model of each tooth is calculated through an MC algorithm to obtain a three-dimensional mesh model of each tooth.
By means of the technical scheme, the tooth image segmentation method and the tooth image segmentation device provided by the invention can be used for firstly obtaining the initial contour line corresponding to each tooth on the initial tooth slice image; secondly, simultaneously adjusting each initial contour line on the initial tooth slice image according to the active contour model, and segmenting other tooth slice images according to a preset segmentation rule on the basis of the adjusted contour line on the initial tooth slice image to obtain the contour line corresponding to each tooth on the other tooth slice images; thirdly, clustering the contour lines of all teeth according to a preset contour line clustering algorithm, and simultaneously obtaining a contour line set corresponding to each tooth; and finally, simultaneously carrying out region filling on each contour line in the contour line set corresponding to each tooth according to a region filling algorithm to obtain a pixel space model of each tooth. Therefore, the method can adjust different initial contour lines on the same tooth slice image, cluster the contour lines after obtaining all contour lines, simultaneously obtain contour line sets of all teeth, and finally simultaneously fill the regions of all contour lines, thereby realizing the simultaneous segmentation of a plurality of teeth (namely simultaneously obtaining pixel space models of a plurality of teeth), improving the efficiency of segmenting the tooth image and further improving the efficiency of reconstructing a tooth three-dimensional grid model based on the CBCT tooth image.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart illustrating a method for segmenting a dental image according to an embodiment of the present invention;
FIG. 2 is a block diagram illustrating a dental image segmentation apparatus according to an embodiment of the present invention;
fig. 3 is a block diagram illustrating another dental image segmentation apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The embodiment of the invention provides a method for segmenting a tooth image, which mainly comprises the following steps of:
101. and acquiring an initial contour line corresponding to each tooth on the initial tooth slice image.
Wherein, the tooth slice image is a two-dimensional image which is obtained based on CBCT scanning and represents different tissues of the tooth. The initial tooth slice image is an image including maxillary teeth or mandibular teeth selected by the user from all the tooth slice images, and each tooth on the initial tooth slice image is relatively clear. After the user selects the initial tooth slice image, the rough contour lines of each tooth on the initial tooth slice image can be manually drawn by using a tooth image segmentation tool, and the rough contour lines are used as the initial contour lines so as to adjust the initial contour lines in the following process and obtain more accurate contour lines. In practical applications, in the tooth slice images of CBCT, the tooth slice images at the middle level are relatively clear, and therefore, in general, the selected initial tooth slice image is located at the middle level.
The initial tooth slice image may be an image including all of the maxillary teeth or all of the mandibular teeth, or an image including only a part of the maxillary teeth or a part of the mandibular teeth, which is not limited herein. When the initial tooth slice image is an image including all maxillary teeth or all mandibular teeth, the segmentation of all maxillary teeth or all mandibular teeth can be realized by executing the steps 101-105, a pixel space model of each tooth is obtained, and then a three-dimensional mesh model of each tooth is obtained through an MC algorithm; when the initial tooth slice image is an image including a part of maxillary teeth or a part of mandibular teeth, the segmentation of the part of maxillary teeth or the part of mandibular teeth can be realized by executing step 101-. Therefore, the tooth can be segmented at one time or multiple times.
102. And adjusting the corresponding initial contour line according to the active contour model and the teeth on the initial tooth slice image to obtain the adjusted contour line.
The active contour model is called Snake model, and is a curve deformation method based on an energy minimization framework, and can approximate the contour of an object in an image by gradually changing the shape of a closed curve. Specifically, the implementation process of the active contour model requires the construction of an energy equation: esnake(S)＝Einternal(S)+Eexternal(S), wherein S represents an initial closed curve, Einternal(S) is an item aimed at normalizing the shape of the curve, called internal energy; eexternal(S) is an item that aims to approach the edge of the target object, called the external energy. According to the energy equation, meterAnd calculating an Euler equation representing the stress of the curve, deforming the curve according to the stress of each point of the curve until the stress is 0, and converging the curve to the edge of the target object when the energy equation reaches the minimum value.
Therefore, after the initial contour line corresponding to each tooth on the initial tooth slice image is adjusted by the active contour model, the obtained adjusted contour line is closer to the actual contour line of the tooth than the initial contour line.
103. And based on the adjusted contour line on the initial tooth slice image, segmenting other tooth slice images according to a preset segmentation rule to obtain the contour line corresponding to each tooth on the other tooth slice images.
After the initial contour line on the initial tooth slice image is adjusted to be closer to the actual contour line of the tooth, the adjusted contour line on the initial tooth slice image can be used as a basis and is sequentially transmitted to two ends, and other tooth slice images are respectively segmented through the active contour model to obtain the contour line corresponding to each tooth on the other tooth slice images.
If the current initial tooth slice image belongs to an image corresponding to a maxillary tooth, other tooth slice images segmented based on the initial tooth slice image also belong to an image corresponding to a maxillary tooth; if the current initial tooth slice image belongs to the image corresponding to the lower jaw teeth, other tooth slice images segmented based on the initial tooth slice image also belong to the image corresponding to the lower jaw teeth.
104. And clustering the contour lines of all teeth according to a preset contour line clustering algorithm to obtain a contour line set corresponding to each tooth.
After the tooth slice image of the maxillary tooth or the tooth slice image of the mandibular tooth is segmented to obtain the contour line of each tooth on the tooth slice image, the tooth image segmentation tool can perform clustering processing on the contour lines of all teeth according to a preset contour line clustering algorithm, and respectively obtain a contour line set corresponding to each tooth, namely a set of the contour lines of each tooth at different fault positions, so as to reconstruct a three-dimensional mesh model of the corresponding tooth based on the contour line sets.
105. And according to a region filling algorithm, performing region filling on each contour line in the contour line set corresponding to each tooth to obtain a pixel space model of each tooth, so that after pixel space models of all maxillary teeth and all mandibular teeth are obtained, the pixel space model of each tooth is calculated through an MC algorithm to obtain a three-dimensional mesh model of each tooth.
Wherein, region filling means filling a certain color or pattern completely in the closed region of the output plane. After the contour line set corresponding to each tooth is obtained, region filling can be performed on each contour line in the contour line set corresponding to each tooth to obtain a pixel space model, namely, a set of contour line regions of the same tooth in different faults is obtained. In practical application, the region filling algorithm may be specifically a seed filling algorithm, and may also be other algorithms, which are not limited herein.
In addition, since the lengths of the middle 10 teeth are similar, the lengths of the two side 4 teeth are similar (for example, 28 teeth in total), and the length difference between the middle 10 teeth and the two side 4 teeth is large in the maxillary tooth or the mandibular tooth, in general, the other 4 teeth may not be completely present when all the middle 10 teeth appear in a certain tooth slice image. Therefore, in practical applications, the middle 10 teeth may be divided from the two side 4 teeth, for example, the middle 10 teeth are divided first, the two side 4 teeth are divided, and finally the pixel space model of all the upper jaw teeth or all the lower jaw teeth is obtained.
According to the tooth image segmentation method provided by the embodiment of the invention, the initial contour line corresponding to each tooth on the initial tooth slice image can be obtained firstly; secondly, simultaneously adjusting each initial contour line on the initial tooth slice image according to the active contour model, and segmenting other tooth slice images according to a preset segmentation rule on the basis of the adjusted contour line on the initial tooth slice image to obtain the contour line corresponding to each tooth on the other tooth slice images; thirdly, clustering the contour lines of all teeth according to a preset contour line clustering algorithm, and simultaneously obtaining a contour line set corresponding to each tooth; and finally, simultaneously carrying out region filling on each contour line in the contour line set corresponding to each tooth according to a region filling algorithm to obtain a pixel space model of each tooth. Therefore, the method can adjust different initial contour lines on the same tooth slice image, cluster the contour lines after obtaining all contour lines, simultaneously obtain contour line sets of all teeth, and finally simultaneously fill the regions of all contour lines, thereby realizing the simultaneous segmentation of a plurality of teeth (namely simultaneously obtaining pixel space models of a plurality of teeth), improving the efficiency of segmenting the tooth image and further improving the efficiency of reconstructing a tooth three-dimensional grid model based on the CBCT tooth image.
Further, the specific implementation manner of the step 103 may be: from the tooth slice image adjacent to the initial tooth slice image, taking the contour line on the tooth slice image which is adjacent to the current tooth slice image and already contains the contour line as the initial contour line of the corresponding tooth on the current tooth slice image; and adjusting the corresponding initial contour line according to the active contour model and the teeth on the current tooth slice image to obtain the adjusted contour line.
For example, if there are 45 tooth slice images corresponding to the mandibular teeth and the selected initial tooth slice image is the 23 rd image (in order from the top of the crown to the bottom of the root), then after obtaining the adjusted contour line on the 23 rd tooth slice image, it is necessary to propagate to both ends based on the contour line. Specifically, the contour lines are first copied to the same positions of the 22 th and 24 th dental slice images (i.e., the same positions as those of the 23 th dental slice image), and are used as the initial contour lines of the corresponding teeth on the 22 th and 24 th dental slice images (i.e., the teeth are corresponding to which the region of the contour line containing which tooth is the largest), and then the initial contour lines are adjusted based on the active contour model, so as to obtain the adjusted contour lines. Secondly, copying the adjusted contour line on the 22 nd tooth slice image to the 21 st tooth slice image, taking the contour line as an initial contour line of a corresponding tooth on the 21 st tooth slice image, and then adjusting the initial contour line based on the active contour model to obtain an adjusted contour line; and simultaneously copying the adjusted contour line on the 24 th tooth slice image to the 25 th tooth slice image, taking the copied contour line as the initial contour line of the corresponding tooth on the 25 th tooth slice image, and adjusting the initial contour line based on the active contour model to obtain the adjusted contour line. According to the propagation method, the segmentation operations of the 22 st to 1 st tooth slice images and the 24 th to 45 th tooth slice images are sequentially realized, and finally tooth contour lines on the tooth slice images are obtained.
Further, in order to further make the corresponding contour line of each tooth smoother and closer to the actual contour line, and further correct the contour line, the embodiment of the present invention provides the following improvement: and secondly adjusting the adjusted contour line on the initial tooth slice image based on the preset user interaction force before the adjusted contour line on the initial tooth slice image is segmented according to the preset segmentation rule to obtain the contour line corresponding to each tooth on the other tooth slice images, so as to obtain the contour line after the secondary adjustment. And after the contour line after the secondary adjustment is obtained, segmenting other tooth slice images according to a preset segmentation rule based on the contour line after the secondary adjustment on the initial tooth slice image to obtain the contour line corresponding to each tooth on the other tooth slice images.
Specifically, the specific algorithm of the user interaction force is as follows:
wherein, SEEDuserSet of seed points specified for the user, Nradius(x, y) represents a circular range with the center of the circle (x, y) and radius as the radius,representative point (x)0,y0) And the euclidean distance of point (x, y). After a user mouse selects the seed points on the initial tooth slice image, the tooth image segmentation tool provides an amplitude-wise thrust to the contour line by using the user interaction force algorithm and the seed points selected by the user, so that the effects of accelerating the convergence of the contour line and correcting the contour line are achieved.
Similar to the initial tooth slice image, after the other tooth slice images are adjusted through the active contour model, in order to further enable the contour lines on the other tooth slice images to be smoother and to be closer to the real-time contour lines, the adjusted contour lines on the initial tooth slice image can be used for segmenting the other tooth slice images according to preset segmentation rules, after the contour lines corresponding to each tooth on the other tooth slice images are obtained, the contour lines corresponding to each tooth on the obtained other tooth slice images are adjusted based on preset user interaction force, and then subsequent clustering operation is performed.
Further, the specific implementation manner of the step 104 may be:
and A1, numbering each tooth on the initial tooth slice image.
The teeth may be numbered sequentially from small to large in a clockwise direction, or sequentially from small to large in a counterclockwise direction, and the numbering manner is not limited herein.
And A2, clustering the contour lines on the tooth slice images at the two ends by taking the contour lines on the initial tooth slice image as starting points based on the obtained tooth numbers to obtain a contour line set corresponding to each tooth.
Specifically, the tooth image segmentation tool may first vertically project a contour line on the tooth slice image, which is adjacent to the current tooth slice image and subjected to the clustering process, onto the current tooth slice image, then respectively determine a projection with the largest intersection area with each contour line on the current tooth slice image, and determine a tooth number corresponding to the projection with the largest intersection area with the current contour line on the current tooth slice image as the tooth number corresponding to the current contour line.
For example, if the 30 th dental slice image is subjected to clustering processing, and the 31 st dental slice image is not subjected to clustering processing, when the 31 st dental slice image is subjected to clustering processing, it is required to vertically project each contour line on the 30 th dental slice image onto the 31 st dental slice image, then determine that a current contour line on the 31 st dental slice image intersects with a projection of a contour line of a3 rd tooth and a projection of a contour line of a4 th tooth on the 30 th dental slice image respectively, and an area of intersection with the projection of the contour line of the 4 th tooth is the largest, and finally determine the tooth number 4 as a tooth number corresponding to the current contour line, where the tooth included in the current contour line is the 4 th tooth.
Further, in order to further improve the efficiency of obtaining each tooth pixel model, after the adjusted contour line on the initial tooth slice image is obtained, the tooth slice image to be segmented may be selected from the remaining tooth slice images according to a preset selection rule, and then only the selected tooth slice image to be segmented is segmented by the preset segmentation rule, so as to obtain the contour line corresponding to each tooth on the tooth slice image to be segmented, while the unselected tooth slice image is directly segmented by adopting a preset interpolation algorithm when the subsequent region is filled.
The preset selection rule may be selected in an equal difference manner (for example, every other image is selected by one image), may also be selected in a non-equal difference manner, and may also be selected by a user in a self-defined manner.
Further, if only a part of the tooth slice image is segmented by the active contour model, the specific implementation manner of the step 105 is:
and B1, determining the contour line corresponding to each tooth on the non-segmented tooth slice image according to a preset interpolation algorithm.
Specifically, the dental image segmentation tool may first determine two dental slice images that are adjacent to an undivided dental slice image and that already contain a contour line, wherein the undivided dental slice image is located between the two determined dental slice images; secondly, calculating the central point of each contour line on the two determined tooth slice images; thirdly, determining the intersection point of the ray in the preset direction and the corresponding contour line by taking the central point of each contour line as a starting point; and finally, connecting the intersection points corresponding to the same preset direction on the two contour lines corresponding to the same tooth to obtain the intersection points of the connecting lines and the tooth slice images which are not segmented, and connecting the intersection points corresponding to the preset directions to obtain the contour lines of the corresponding tooth on the tooth slice images which are not segmented.
For example, if the 13 th dental slice image is not divided and the 12 th and 14 th dental slice images are divided, the center points of the contour lines on the 12 th and 14 th dental slice images are calculated, and then the intersection points of the rays in the preset direction and the corresponding contour lines are determined using the center point of each contour line as a starting point, for example, the intersection points of a contour line and the rays in the upper, lower, left and right directions on the 12 th dental slice image are a1, a2, a3, and a4 in this order, the intersection points of a contour line and the rays in the upper, lower, left and right directions on the 12 th dental slice image are b1, b2, b3, and b4 in this order, the intersection points of a1 and b1, a2 and b2, a3 and b3, and a4 and b4 in this order, and the intersection points of the connecting lines and the dental slice image are 1 c2, and c respectively, c3 and c4, at which time c1, c2, c3 and c4 are connected in sequence, the contour of the tooth on the 13 th tooth slice image can be obtained.
And B2, adding the determined contour lines into the contour line sets of the corresponding teeth to obtain updated contour line sets corresponding to each tooth.
And B3, according to a region filling algorithm, performing region filling on each contour line in the updated contour line set corresponding to each tooth to obtain a pixel space model of each tooth.
After the tooth slice images corresponding to all the maxillary teeth or the tooth slice images corresponding to all the mandibular teeth are segmented, all contour line sets corresponding to each tooth can be obtained, at this time, each contour line in each contour line set is filled in a region, a pixel space model corresponding to each tooth can be obtained, and therefore a three-dimensional mesh model of the whole set of teeth can be obtained by utilizing an MC algorithm subsequently.
Further, according to the above method embodiment, another embodiment of the present invention further provides a device for segmenting a dental image, as shown in fig. 2, the device mainly includes: an acquisition unit 21, an adjustment unit 22, a segmentation unit 23, a clustering unit 24, and a padding unit 25. Wherein,
an obtaining unit 21, configured to obtain an initial contour line corresponding to each tooth on an initial tooth slice image, where the initial tooth slice image is an image including maxillary teeth or mandibular teeth selected by a user from all tooth slice images;
the adjusting unit 22 is configured to adjust the corresponding initial contour line obtained by the obtaining unit 21 according to the active contour model and the tooth on the initial tooth slice image, so as to obtain an adjusted contour line;
a segmentation unit 23, configured to segment other tooth slice images according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image obtained by the adjustment unit 22, so as to obtain a contour line corresponding to each tooth on the other tooth slice images;
the clustering unit 24 is configured to cluster the contour lines of all teeth according to a preset contour line clustering algorithm to obtain a contour line set corresponding to each tooth;
and a filling unit 25, configured to perform region filling on each contour line in the contour line set corresponding to each tooth obtained by the clustering unit 24 according to a region filling algorithm to obtain a pixel space model of each tooth, so that after the pixel space models of all maxillary teeth and all mandibular teeth are obtained, the pixel space model of each tooth is calculated through an MC algorithm to obtain a three-dimensional mesh model of each tooth.
The tooth image segmentation device provided by the embodiment of the invention can be used for firstly acquiring the initial contour line corresponding to each tooth on the initial tooth slice image; secondly, simultaneously adjusting each initial contour line on the initial tooth slice image according to the active contour model, and segmenting other tooth slice images according to a preset segmentation rule on the basis of the adjusted contour line on the initial tooth slice image to obtain the contour line corresponding to each tooth on the other tooth slice images; thirdly, clustering the contour lines of all teeth according to a preset contour line clustering algorithm, and simultaneously obtaining a contour line set corresponding to each tooth; and finally, simultaneously carrying out region filling on each contour line in the contour line set corresponding to each tooth according to a region filling algorithm to obtain a pixel space model of each tooth. Therefore, the method can adjust different initial contour lines on the same tooth slice image, cluster the contour lines after obtaining all contour lines, simultaneously obtain contour line sets of all teeth, and finally simultaneously fill the regions of all contour lines, thereby realizing the simultaneous segmentation of a plurality of teeth (namely simultaneously obtaining pixel space models of a plurality of teeth), improving the efficiency of segmenting the tooth image and further improving the efficiency of reconstructing a tooth three-dimensional grid model based on the CBCT tooth image.
Further, as shown in fig. 3, the dividing unit 23 includes:
a setting module 231, configured to use, from a tooth slice image adjacent to the initial tooth slice image, a contour line on a tooth slice image adjacent to the current tooth slice image and already containing a contour line as an initial contour line of a corresponding tooth on the current tooth slice image;
and an adjusting module 232, configured to adjust the corresponding initial contour line according to the active contour model and the tooth on the current tooth slice image, so as to obtain an adjusted contour line.
Further, as shown in fig. 3, the adjusting unit 22 is further configured to, before the segmenting unit 23 segments other tooth slice images according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image and obtains a contour line corresponding to each tooth on the other tooth slice images, perform secondary adjustment on the adjusted contour line on the initial tooth slice image based on a preset user interaction force to obtain a contour line after secondary adjustment;
and the segmentation unit 23 is configured to segment the other tooth slice images according to a preset segmentation rule based on the contour line after the secondary adjustment on the initial tooth slice image, so as to obtain a contour line corresponding to each tooth on the other tooth slice images.
Further, as shown in fig. 3, the adjusting unit 22 is further configured to, after the segmenting unit 23 segments the other tooth slice images according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image to obtain a contour line corresponding to each tooth on the other tooth slice images, adjust the contour line corresponding to each tooth on the obtained other tooth slice images based on a preset user interaction force.
Further, as shown in fig. 3, the clustering unit 24 includes:
a numbering module 241, configured to number each tooth on the initial tooth slice image;
the clustering module 242 is configured to cluster the contour lines on the tooth slice images at the two ends by using the contour lines on the initial tooth slice image as starting points based on the tooth numbers obtained by the numbering module 241, so as to obtain a contour line set corresponding to each tooth;
a clustering module 242, comprising:
a projection submodule 2421, configured to vertically project a contour line on the tooth slice image, which is adjacent to the current tooth slice image and has undergone the clustering process, onto the current tooth slice image;
the determining submodule 2422 is configured to determine the projection with the largest intersection area with each contour line on the current tooth slice image, and determine the tooth number corresponding to the projection with the largest intersection area with the current contour line on the current tooth slice image as the tooth number corresponding to the current contour line.
Further, as shown in fig. 3, the apparatus further includes:
a selecting unit 26, configured to select a tooth slice image to be segmented from the remaining tooth slice images according to a preset selection rule before the segmenting unit 23 segments the other tooth slice images according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image and obtains a contour line corresponding to each tooth on the other tooth slice images;
and the segmentation unit 23 is configured to segment the tooth slice image to be segmented according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image, so as to obtain a contour line corresponding to each tooth on the tooth slice image to be segmented.
Further, as shown in fig. 3, the filling unit 25 includes:
a determining module 251, configured to determine, according to a preset interpolation algorithm, a contour line corresponding to each tooth on the non-segmented tooth slice image;
an adding module 252, configured to add the contour lines determined by the determining module 251 to the contour line sets of the corresponding teeth, to obtain an updated contour line set corresponding to each tooth;
and a filling module 253, configured to perform region filling on each contour line in the updated contour line set corresponding to each tooth according to a region filling algorithm, so as to obtain a pixel space model of each tooth.
Further, as shown in fig. 3, the determining module 251 includes:
a first determining sub-module 2511 for determining two dental slice images which are adjacent to the non-segmented dental slice image and already contain contour lines, wherein the non-segmented dental slice image is located in the middle of the determined two dental slice images;
a calculating sub-module 2512 for calculating the center point of each contour line on the two tooth slice images determined by the first determining sub-module 2511;
a second determining submodule 2513, configured to determine, using the center point of each contour line obtained by the calculating submodule 2512 as a starting point, an intersection point between a ray in the preset direction and the corresponding contour line;
and a connecting sub-module 2514 for connecting the intersection points corresponding to the same preset direction on the two contour lines corresponding to the same tooth to obtain the intersection points of the connecting line and the non-segmented tooth slice image, and connecting the intersection points corresponding to the preset directions to obtain the contour lines of the corresponding tooth on the non-segmented tooth slice image.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It will be appreciated that the relevant features of the method and apparatus described above are referred to one another. In addition, "first", "second", and the like in the above embodiments are for distinguishing the embodiments, and do not represent merits of the embodiments.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the method, device, server and system for status detection of a walk-on electronic anti-loss device according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Claims (9)
1. A method of segmentation of a dental image, the method comprising:
acquiring an initial contour line corresponding to each tooth on an initial tooth slice image, wherein the initial tooth slice image is an image which is selected by a user from all tooth slice images and contains maxillary teeth or mandibular teeth;
adjusting the corresponding initial contour line according to the active contour model and the teeth on the initial tooth slice image to obtain an adjusted contour line;
based on the adjusted contour line on the initial tooth slice image, segmenting other tooth slice images according to a preset segmentation rule to obtain a contour line corresponding to each tooth on the other tooth slice images;
clustering the contour lines of all teeth according to a preset contour line clustering algorithm to obtain a contour line set corresponding to each tooth;
according to a region filling algorithm, performing region filling on each contour line in a contour line set corresponding to each tooth to obtain a pixel space model of each tooth, so that after pixel space models of all maxillary teeth and all mandibular teeth are obtained, the pixel space model of each tooth is calculated through an MC algorithm to obtain a three-dimensional mesh model of each tooth;
the method is characterized in that based on the adjusted contour line on the initial tooth slice image, other tooth slice images are segmented according to a preset segmentation rule, and the contour line corresponding to each tooth on the other tooth slice images is obtained, and the method comprises the following steps:
from the tooth slice image adjacent to the initial tooth slice image, taking a contour line on the tooth slice image adjacent to the current tooth slice image and containing the contour line as an initial contour line of the corresponding tooth on the current tooth slice image;
adjusting the corresponding initial contour line according to the active contour model and the teeth on the current tooth slice image to obtain an adjusted contour line;
before segmenting other tooth slice images according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image and obtaining the contour line corresponding to each tooth on the other tooth slice images, the method further comprises the following steps:
performing secondary adjustment on the adjusted contour line on the initial tooth slice image based on a preset user interaction force to obtain a secondarily adjusted contour line;
after segmenting other tooth slice images based on the adjusted contour line on the initial tooth slice image according to a preset segmentation rule to obtain a contour line corresponding to each tooth on the other tooth slice images, the method further comprises the following steps:
and adjusting the contour line corresponding to each tooth on the obtained other tooth slice images based on the preset user interaction force.
2. The method of claim 1, wherein clustering the contours of all teeth according to a predetermined contour clustering algorithm to obtain a set of contours corresponding to each tooth comprises:
numbering each tooth on the initial tooth slice image;
based on the obtained tooth numbers, clustering the contour lines on the tooth slice images at two ends by taking the contour lines on the initial tooth slice images as starting points to obtain a contour line set corresponding to each tooth;
based on the obtained tooth numbers, clustering the contour lines on the tooth slice images at two ends by taking the contour lines on the initial tooth slice images as starting points, and the clustering method comprises the following steps:
vertically projecting a contour line on the tooth slice image which is adjacent to the current tooth slice image and is subjected to clustering processing onto the current tooth slice image;
and respectively determining the projection with the maximum intersection area of each contour line on the current tooth slice image, and determining the tooth number corresponding to the projection with the maximum intersection area of the current contour line on the current tooth slice image as the tooth number corresponding to the current contour line.
3. The method according to claim 1, wherein before the other tooth slice images are segmented based on the adjusted contour lines on the initial tooth slice image according to a preset segmentation rule to obtain the contour lines corresponding to each tooth on the other tooth slice images, the method further comprises:
selecting a tooth slice image to be segmented from the rest tooth slice images according to a preset selection rule;
and based on the adjusted contour line on the initial tooth slice image, segmenting the tooth slice image to be segmented according to a preset segmentation rule to obtain the contour line corresponding to each tooth on the tooth slice image to be segmented.
4. The method of claim 3, wherein region filling each contour line in the set of contour lines corresponding to each tooth according to a region filling algorithm to obtain a pixel space model of each tooth comprises:
determining a contour line corresponding to each tooth on the non-segmented tooth slice image according to a preset interpolation algorithm;
adding the determined contour lines into the contour line sets of the corresponding teeth to obtain updated contour line sets corresponding to each tooth;
and according to the region filling algorithm, performing region filling on each contour line in the updated contour line set corresponding to each tooth to obtain a pixel space model of each tooth.
5. The method of claim 4, wherein determining the contour line corresponding to each tooth on the non-segmented tooth slice image according to a preset interpolation algorithm comprises:
determining two dental slice images which are adjacent to the non-segmented dental slice image and already contain contour lines, wherein the non-segmented dental slice image is positioned in the middle of the determined two dental slice images;
calculating the central point of each contour line on the two determined tooth slice images;
determining the intersection point of the ray in the preset direction and the corresponding contour line by taking the central point of each contour line as a starting point;
connecting the intersection points corresponding to the same preset direction on the two contour lines corresponding to the same tooth to obtain the intersection points of the connecting lines and the tooth slice images which are not segmented, and connecting the intersection points corresponding to the preset directions to obtain the contour lines of the corresponding tooth on the tooth slice images which are not segmented.
6. An apparatus for segmenting a dental image, the apparatus comprising:
the system comprises an acquisition unit, a comparison unit and a processing unit, wherein the acquisition unit is used for acquiring an initial contour line corresponding to each tooth on an initial tooth slice image, and the initial tooth slice image is an image which is selected by a user from all tooth slice images and contains maxillary teeth or mandibular teeth;
the adjusting unit is used for adjusting the corresponding initial contour line obtained by the obtaining unit according to the active contour model and the teeth on the initial tooth slice image to obtain an adjusted contour line;
the segmentation unit is used for segmenting other tooth slice images according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image obtained by the adjustment unit to obtain a contour line corresponding to each tooth on the other tooth slice images;
the clustering unit is used for clustering the contour lines of all teeth according to a preset contour line clustering algorithm to obtain a contour line set corresponding to each tooth;
the filling unit is used for performing region filling on each contour line in the contour line set corresponding to each tooth obtained by the clustering unit according to a region filling algorithm to obtain a pixel space model of each tooth, so that after pixel space models of all maxillary teeth and all mandibular teeth are obtained, the pixel space model of each tooth is calculated through an MC algorithm to obtain a three-dimensional mesh model of each tooth;
wherein the dividing unit includes:
the setting module is used for taking a contour line on a tooth slice image which is adjacent to the current tooth slice image and already contains a contour line as an initial contour line of a corresponding tooth on the current tooth slice image from a tooth slice image which is adjacent to the initial tooth slice image;
the adjusting module is used for adjusting the corresponding initial contour line according to the active contour model and the teeth on the current tooth slice image to obtain an adjusted contour line;
the adjusting unit is further configured to perform secondary adjustment on the adjusted contour line on the initial tooth slice image based on a preset user interaction force before the segmentation unit segments other tooth slice images according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image to obtain a contour line corresponding to each tooth on the other tooth slice images, so as to obtain a contour line after secondary adjustment;
the adjusting unit is further configured to, after the segmenting unit segments other tooth slice images according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image and obtains a contour line corresponding to each tooth on the other tooth slice images, adjust the contour line corresponding to each tooth on the obtained other tooth slice images based on a preset user interaction force;
the clustering unit includes:
the numbering module is used for numbering each tooth on the initial tooth slice image;
the clustering module is used for clustering the contour lines on the tooth slice images at two ends by taking the contour lines on the initial tooth slice image as starting points based on the tooth numbers obtained by the numbering module to obtain a contour line set corresponding to each tooth;
the clustering module comprises:
the projection submodule is used for vertically projecting the contour line on the tooth slice image which is adjacent to the current tooth slice image and is subjected to clustering processing to the current tooth slice image;
and the determining submodule is used for respectively determining the projection with the maximum intersection area of each contour line on the current tooth slice image and determining the tooth number corresponding to the projection with the maximum intersection area of the current contour line on the current tooth slice image as the tooth number corresponding to the current contour line.
7. The apparatus of claim 6, further comprising:
the selection unit is used for selecting the tooth slice image to be segmented from the rest tooth slice images according to a preset selection rule before the segmentation unit segments other tooth slice images according to the adjusted contour line on the initial tooth slice image and the preset segmentation rule to obtain the contour line corresponding to each tooth on the other tooth slice images;
and the segmentation unit is used for segmenting the tooth slice image to be segmented according to a preset segmentation rule based on the adjusted contour line on the initial tooth slice image to obtain a contour line corresponding to each tooth on the tooth slice image to be segmented.
8. The apparatus of claim 7, wherein the filling unit comprises:
the determining module is used for determining a contour line corresponding to each tooth on the non-segmented tooth slice image according to a preset interpolation algorithm;
the adding module is used for adding the contour line determined by the determining module into the contour line set of the corresponding tooth to obtain an updated contour line set corresponding to each tooth;
and the filling module is used for performing region filling on each contour line in the updated contour line set corresponding to each tooth according to the region filling algorithm to obtain a pixel space model of each tooth.
9. The apparatus of claim 8, wherein the determining module comprises:
a first determining sub-module for determining two dental slice images adjacent to an undivided dental slice image and having a contour line, wherein the undivided dental slice image is located in the middle of the determined two dental slice images;
the calculating sub-module is used for calculating the central point of each contour line on the two tooth slice images determined by the first determining sub-module;
the second determining submodule is used for determining the intersection point of the ray in the preset direction and the corresponding contour line by taking the central point of each contour line obtained by the calculating submodule as a starting point;
and the connecting sub-module is used for connecting the intersection points corresponding to the same preset direction on the two contour lines corresponding to the same tooth to obtain the intersection points of the connecting lines and the tooth slice images which are not divided, and connecting the intersection points corresponding to the preset directions to obtain the contour lines of the corresponding tooth on the tooth slice images which are not divided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610066016.1A CN105741288B (en) | 2016-01-29 | 2016-01-29 | Tooth image segmentation method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610066016.1A CN105741288B (en) | 2016-01-29 | 2016-01-29 | Tooth image segmentation method and apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105741288A CN105741288A (en) | 2016-07-06 |
| CN105741288B true CN105741288B (en) | 2017-04-12 |
Family
ID=56247997
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610066016.1A Active CN105741288B (en) | 2016-01-29 | 2016-01-29 | Tooth image segmentation method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105741288B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109816661A (en) * | 2019-03-22 | 2019-05-28 | 电子科技大学 | A kind of tooth CT image partition method based on deep learning |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106214175B (en) * | 2016-08-26 | 2020-06-16 | 中国科学院深圳先进技术研究院 | Method and device for estimating three-dimensional tooth axis |
| CN109598703B (en) * | 2018-11-19 | 2021-05-11 | 影为医疗科技(上海)有限公司 | Method, system, computer-readable storage medium and device for processing dental image |
| CN110647851B (en) * | 2019-09-27 | 2022-12-09 | 普联技术有限公司 | Production line capacity monitoring method, device and system |
| CN111968120B (en) * | 2020-07-15 | 2022-03-15 | 电子科技大学 | Tooth CT image segmentation method for 3D multi-feature fusion |
| CN112308867B (en) * | 2020-11-10 | 2022-07-22 | 上海商汤智能科技有限公司 | Tooth image processing method and device, electronic equipment and storage medium |
| CN113506302B (en) * | 2021-07-27 | 2023-12-12 | 四川九洲电器集团有限责任公司 | Interactive object updating method, device and processing system |
| CN115205469A (en) * | 2022-09-06 | 2022-10-18 | 汉斯夫(杭州)医学科技有限公司 | Tooth and alveolar bone reconstruction method, equipment and medium based on CBCT |
| CN115330820B (en) * | 2022-10-14 | 2023-03-24 | 江苏启灏医疗科技有限公司 | Tooth image segmentation method based on X-ray film |
| CN115880286B (en) * | 2023-02-16 | 2023-06-27 | 极限人工智能有限公司 | Method, system, medium and electronic equipment for intelligently planning and recommending oral implant |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489198A (en) * | 2013-10-21 | 2014-01-01 | 钟映春 | Method for partitioning brainstem areas automatically from MR (magnetic resonance) sequence images |
| CN105279762B (en) * | 2015-11-20 | 2017-12-15 | 北京航空航天大学 | A kind of oral cavity hard and soft tissue CT sequences and three-dimensional grid model method for registering |
-
2016
- 2016-01-29 CN CN201610066016.1A patent/CN105741288B/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109816661A (en) * | 2019-03-22 | 2019-05-28 | 电子科技大学 | A kind of tooth CT image partition method based on deep learning |
| CN109816661B (en) * | 2019-03-22 | 2022-07-01 | 电子科技大学 | Tooth CT image segmentation method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105741288A (en) | 2016-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105741288B (en) | Tooth image segmentation method and apparatus | |
| JP2021521993A5 (en) | ||
| JP2015100702A5 (en) | ||
| JP2013500536A5 (en) | ||
| CN107301673B (en) | Algorithm for constructing local coordinate system of tooth by using standard model library | |
| CN108320325A (en) | The generation method and device of dental arch model | |
| US9427197B2 (en) | Method and apparatus to generate a panoramic radiography | |
| US9652673B2 (en) | Method for identifying calcification portions in dual energy CT contrast agent enhanced scanning image | |
| CN115619773B (en) | Three-dimensional tooth multi-mode data registration method and system | |
| JP2015513945A6 (en) | Tooth graph cut-based interactive segmentation method in 3D CT volumetric data | |
| JP2015513945A (en) | Tooth graph cut based interactive segmentation method in 3D CT solid data | |
| CN110533738B (en) | Reconstruction data processing method and device, medical imaging system and storage medium | |
| CN113344950A (en) | CBCT image tooth segmentation method combining deep learning with point cloud semantics | |
| CN110598333A (en) | Method and device for determining light source position and electronic equipment | |
| JP2013175006A (en) | Device, method, and program for generating mesh | |
| CN116630513A (en) | Human body high-quality rendering method and device, electronic equipment and storage medium | |
| EP3566205A1 (en) | Method of obtaining 3d model data of a plurality of components of an object | |
| CN106308836B (en) | Computer tomography image correction system and method | |
| CN101080747A (en) | High quality accurate surface triangulation from a simplex mesh | |
| CN114972634A (en) | Multi-view three-dimensional deformable human face reconstruction method based on feature voxel fusion | |
| CN114549540A (en) | Method for automatically fusing oral scanning tooth data and CBCT (Cone Beam computed tomography) data and application thereof | |
| CN112085811B (en) | Method and device for CT local reconstruction | |
| CN108090953A (en) | Area-of-interest method for reconstructing, system and computer readable storage medium | |
| CN113140016B (en) | Metal artifact correction method and system for CBCT equipment | |
| JPWO2013005455A1 (en) | Shape extraction method and shape extraction system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |