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
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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
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 present invention relates to field of computer technology, the dividing method and device of more particularly to a kind of dental imaging.
Background technology
With the progress of science and technology, the method for dental imaging is obtained gradually by traditional computed tomography (Computed
Tomography, abbreviation CT) technology develops into cone beam computed tomography (Cone Beam Computed
Tomography, abbreviation CBCT) technology, and can carry out rebuilding the three-dimensional for obtaining tooth based on the two-dimentional dental imaging of CBCT
Grid model, is more accurately judged so as to help doctor to be made to dental cases based on three-dimensional grid model.
In actual applications, the two-dimentional dental imaging of CBCT is redeveloped into into the concrete methods of realizing of three-dimensional grid model picture
For：First two-dimentional dental imaging is split, the pixel space model of every tooth is obtained, further according to MC (Marching
Cubes) scheduling algorithm is calculated the pixel space model of every tooth, finally obtains the three-dimensional grid mould of a whole set of tooth
Type.In the prior art, the software to being split based on the dental imaging of CBCT mainly includes that Amira softwares and Mimics are soft
Part.However, no matter being split based on Amira softwares, be also based on Mimics softwares and split, be required for it is artificial participate in and
Can only be split for single tooth, and cannot be realized to splitting while multiple teeth, the picture dentulous so as to obtain
Plain spatial model needs to take a long time, and then so that obtains the less efficient of the three-dimensional grid model of a whole set of tooth.
The content of the invention
In view of this, the present invention provides a kind of dividing method and device of dental imaging, can solve the problem that in prior art and divides
Cut the less efficient problem of dental imaging.
According to one aspect of the invention, there is provided a kind of dividing method of dental imaging, methods described includes：
The corresponding initial profile line of every tooth is obtained on initial tooth slice image, the initial tooth slice image is
The image comprising maxillary teeth or mandibular teeth that user selects from all tooth slice images；
According to the tooth on active contour model and the initial tooth slice image, corresponding initial profile line is entered
Row adjustment, the contour line after being adjusted；
Based on the contour line after the adjustment on the initial tooth slice image, according to default segmentation rule, to other teeth
Tooth sectioning image is split, and obtains on other tooth slice images the corresponding contour line of every tooth；
According to default contour line clustering algorithm, institute's contour line dentulous is clustered, obtained every tooth corresponding
Contour line set；
According to region-filling algorithm, region is carried out to each contour line in the corresponding contour line set of every tooth and is filled out
Fill, obtain the pixel space model of every tooth, so as to empty in the pixel for obtaining all maxillary teeths and all mandibular teeths
Between after model, the pixel space model of every tooth is calculated by MC algorithms, obtain the three-dimensional grid mould of every tooth
Type.
According to another aspect of the invention, there is provided a kind of segmenting device of dental imaging, described device includes：
Acquiring unit, it is described initial for obtaining on initial tooth slice image the corresponding initial profile line of every tooth
Tooth slice image is the figure comprising maxillary teeth or mandibular teeth that user selects from all tooth slice images
Picture；
Adjustment unit, for according to the tooth on active contour model and the initial tooth slice image, to described
The corresponding initial profile line that acquiring unit is obtained is adjusted, the contour line after being adjusted；
Cutting unit, for the wheel after the adjustment on the described initial tooth slice image based on adjustment unit acquisition
Other tooth slice images, according to default segmentation rule, are split by profile, obtain every tooth on other tooth slice images
The corresponding contour line of tooth；
Cluster cell, for according to default contour line clustering algorithm, institute's contour line dentulous being clustered, obtains every
The corresponding contour line set of tooth；
Fills unit, for according to region-filling algorithm, the corresponding profile of every tooth obtained to the cluster cell
Each contour line in line set carries out area filling, obtains the pixel space model of every tooth, to obtain on all
After the pixel space model of jaw tooth and all mandibular teeths, the pixel space model of every tooth is carried out by MC algorithms
Calculate, obtain the three-dimensional grid model of every tooth.
The dividing method and device of the dental imaging provided by above-mentioned technical proposal, the present invention, can first obtain initial
The corresponding initial profile line of every tooth on tooth slice image；Secondly, according to active contour model, while cutting to initial tooth
Each initial profile line on picture is adjusted, and based on the contour line after the adjustment on the initial tooth slice image,
According to default segmentation rule, other tooth slice images are split, obtain every tooth pair on other tooth slice images
The contour line answered；Again, according to default contour line clustering algorithm, clustering processing is carried out to institute's contour line dentulous, while obtaining
The corresponding contour line set of every tooth；Finally, according to region-filling algorithm, while to the corresponding contour line collection of each tooth
Each contour line in conjunction carries out area filling, obtains the pixel space model of each tooth.It follows that the present invention can be right
Different initial profile lines on same tooth slice image are adjusted, and after all contour lines are obtained, contour line are carried out
Cluster, while the contour line set of each tooth is obtained, it is last simultaneously area filling to be carried out to each contour line, it is right so as to realize
Segmentation (obtaining the pixel space model of multiple teeth simultaneously), improves the effect of segmentation dental imaging while multiple teeth
Rate, and then improve the efficiency that tooth three-dimensional grid model is rebuild based on CBCT dental imagings.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of description, and in order to allow the above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the specific embodiment of the present invention.
Description of the drawings
By the detailed description for reading hereafter preferred implementation, various other advantages and benefit is common for this area
Technical staff will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation, and is not considered as to the present invention
Restriction.And in whole accompanying drawing, it is denoted by the same reference numerals identical part.In the accompanying drawings：
Fig. 1 shows a kind of flow chart of the dividing method of dental imaging provided in an embodiment of the present invention；
Fig. 2 shows a kind of composition frame chart of the segmenting device of dental imaging provided in an embodiment of the present invention；
Fig. 3 shows the composition frame chart of the segmenting device of another kind of dental imaging provided in an embodiment of the present invention.
Specific embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure and should not be by embodiments set forth here
Limited.On the contrary, there is provided these embodiments are able to be best understood from the disclosure, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
A kind of dividing method of dental imaging is embodiments provided, as shown in figure 1, the method mainly includes：
101st, the corresponding initial profile line of every tooth is obtained on initial tooth slice image.
Wherein, tooth slice image is the X-Y scheme that the representative tooth different tissues for obtaining are scanned based on CBCT.Initial tooth
Tooth sectioning image is the image comprising maxillary teeth or mandibular teeth that user selects from all tooth slice images,
And each tooth on initial tooth slice image is relatively clear.After user selects initial tooth slice image, it is possible to use
Dental imaging partition tools Manual description goes out the rough contour line of every tooth on the initial tooth slice image, and these are thick
Slightly contour line to be subsequently adjusted to initial profile line, obtains more accurate contour line as initial profile line.In reality
Using in, in the tooth slice image of CBCT, the tooth slice image positioned at the intermediate level is relatively more visible, therefore, typically
In the case of, the initial tooth slice image of selection is located at intermediate layer.
It should be noted that initial tooth slice image can be comprising all maxillary teeths or all mandibular teeths
Image, or the image only comprising part maxillary teeth or part mandibular teeth, it is not limited thereto.When initial tooth
When sectioning image is the image comprising all maxillary teeths or all mandibular teeths, by execution step 101-105, it is capable of achieving
Segmentation to all maxillary teeths or all mandibular teeths, obtains the pixel space model of every tooth, then by MC algorithms,
Obtain the three-dimensional grid model of every tooth；When initial tooth slice image is comprising part maxillary teeth or part lower jaw tooth
During the image of tooth, by execution step 101-105, it is capable of achieving to divide the part maxillary teeth or the part mandibular teeth
Cut, obtain the pixel space model of every tooth in the part maxillary teeth or the part mandibular teeth, one is then chosen again
The individual image comprising other teeth in maxillary teeth or comprising other teeth in mandibular teeth is used as new initial tooth slice
Image, repeats 101-105, obtains the pixel space model of remaining tooth, the pixel space model dentulous obtaining
Afterwards, then by MC algorithms calculated, obtained the three-dimensional grid model of every tooth.It follows that the present invention can be to tooth
Disposably split, can be also divided into repeated segmentation.
102nd, according to the tooth on active contour model and initial tooth slice image, corresponding initial profile line is entered
Row adjustment, the contour line after being adjusted.
Wherein, active contour model is referred to as Snake models, is a kind of curve deformation side based on energy minimization framework
Method, can by the way that the shape of closed curve is altered in steps to approach image in target profile.Specifically, active contour model
The process of realization needs to build energy equation：Esnake(S)=Einternal(S)+Eexternal(S), wherein, S represents that first closure is bent
Line, Einternal(S) it is item for the purpose of the curve shape that standardizes, referred to as interior energy；Eexternal(S) it is near target object
Item for the purpose of edge, referred to as external enwergy.According to the energy equation, the Eulerian equation for representing curve stress is calculated, according to curve
Deforming to curve, until stress is 0, energy equation reaches minima to the stress of each point, and curve can converge to target
Object edge.
It follows that on to initial tooth slice image the corresponding initial profile line Jing active contour models of every tooth
After adjustment, the contour line after the adjustment of acquisition than initial profile line closer to tooth real contour line.
103rd, based on the contour line after the adjustment on initial tooth slice image, according to default segmentation rule, to other teeth
Tooth sectioning image is split, and obtains on other tooth slice images the corresponding contour line of every tooth.
After the initial profile line on initial tooth slice image is adjusted to real contour line closer to tooth, can be with
Based on by the contour line after the adjustment on initial dental imaging, propagate to two ends successively, distinguished by active contour model
Other tooth slice images are split, the corresponding contour line of every tooth is obtained on other tooth slice images.
If first based on this it should be noted that current initial tooth slice image belongs to the corresponding image of maxillary teeth
Other tooth slice images of beginning tooth slice image segmentation fall within the corresponding image of maxillary teeth；If current initial tooth is cut
Picture belongs to the corresponding image of mandibular teeth, then other tooth slice images based on the initial tooth slice image segmentation
Belong to the corresponding image of mandibular teeth.
104th, according to default contour line clustering algorithm, institute's contour line dentulous is clustered, is obtained every tooth pair
The contour line set answered.
When the tooth slice image of the tooth slice image to maxillary teeth or mandibular teeth is split, tooth is obtained
On sectioning image after the contour line of every tooth, dental imaging partition tools can be according to default contour line clustering algorithm, to institute
Contour line dentulous carries out clustering processing, and the corresponding contour line set of every tooth is obtained respectively, i.e., every tooth is in difference
The set of the profile at tomography, so as to the follow-up three-dimensional grid model based on contour line collection occlusal reconstruction correspondence tooth.
105th, according to region-filling algorithm, region is carried out to each contour line in the corresponding contour line set of every tooth
Filling, obtains the pixel space model of every tooth, so as in the pixel for obtaining all maxillary teeths and all mandibular teeths
After spatial model, the pixel space model of every tooth is calculated by MC algorithms, obtain the three-dimensional grid of every tooth
Model.
Wherein, area filling refers to and certain color or pattern is intactly filled in the enclosed region of output plane.When obtaining
After the corresponding contour line set of every tooth, each contour line in the corresponding contour line set of every tooth can be carried out
Area filling, obtains pixel space model, that is, obtain set of the same tooth in the contour line region of different tomographies.In reality
Using in, region-filling algorithm is specifically as follows seed fill algorithm, or and other algorithms, here is not limited.
Further, since in maxillary teeth or mandibular teeth, the length of 10 middle teeth is more similar, the 4 of both sides
The length more similar (by taking a total of 28 teeth as an example) of tooth, and the length of the 10 of centre teeth and 4 teeth on both sides
Degree differs greatly, so generally, when 10 middle teeth all occur in a certain tooth slice image, other 4
Tooth may not exclusively be present.Therefore, in actual applications, 10 middle teeth can be divided with 4 teeth on both sides
Open segmentation, for example, first split 10 teeth of centre, then split 4 teeth on both sides, finally obtain all maxillary teeths or
The pixel space model of all mandibular teeths.
The dividing method of dental imaging provided in an embodiment of the present invention, can first obtain per on initial tooth slice image
The corresponding initial profile line of tooth；Secondly, according to active contour model, while initial to each on initial tooth slice image
Contour line is adjusted, and based on the contour line after the adjustment on the initial tooth slice image, it is right according to default segmentation rule
Other tooth slice images are split, and obtain on other tooth slice images the corresponding contour line of every tooth；Again, according to
Default contour line clustering algorithm, to institute's contour line dentulous clustering processing is carried out, while the corresponding profile of every tooth of acquisition
Line set；Finally, according to region-filling algorithm, while carrying out to each contour line in the corresponding contour line set of each tooth
Area filling, obtains the pixel space model of each tooth.It follows that the present invention can be on same tooth slice image
Different initial profile lines are adjusted, and after all contour lines are obtained, contour line are clustered, while obtaining each tooth
Contour line set, it is last simultaneously area filling to be carried out to each contour line, so as to realize to segmentation while multiple teeth (i.e.
The pixel space model of multiple teeth is obtained simultaneously), the efficiency of segmentation dental imaging is improve, and then improve based on CBCT teeth
The efficiency of tooth image reconstruction tooth three-dimensional grid model.
Further, the specific implementation of above-mentioned steps 103 can be：From the tooth adjacent with initial tooth slice image
Tooth sectioning image rises, by contour line adjacent with current dental sectioning image, on the tooth slice image containing contour line
As the initial profile line of correspondence tooth on current dental sectioning image；According to active contour model and current dental slice map
As upper tooth, corresponding initial profile line is adjusted, the contour line after being adjusted.
Exemplary, if the corresponding tooth slice image of mandibular teeth has 45, and the initial tooth slice image chosen
(press from the top of corona to the order of root of the tooth bottom) for the 23rd image, then after adjusting on the 23rd tooth slice image is obtained
Contour line after, need based on the contour line to two ends propagate.Specifically, first, respectively the contour line copied to into the 22nd, 24
Same position (i.e. identical with the position on the 23rd tooth slice image) place of individual tooth slice image, and it is made respectively
For correspondence tooth on the 22nd, 24 tooth slice images, (i.e. region of the contour line comprising which tooth is maximum with regard to which tooth of correspondence
Tooth) initial profile line, be then based on active contour model and initial profile line be adjusted, the contour line after being adjusted.
Secondly, the contour line after the adjustment on the 22nd tooth slice image is copied on the 21st tooth slice image, and by its
As the initial profile line of correspondence tooth on the 21st tooth slice image, it is then based on active contour model and initial profile is entered
Row adjustment, the contour line after being adjusted；Meanwhile, the contour line after the adjustment on the 24th tooth slice image is copied to into
On 25 tooth slice images, and as the initial profile line of correspondence tooth on the 25th tooth slice image, Ran Houji
Initial profile is adjusted in active contour model, the contour line after being adjusted.According to above-mentioned transmission method, realize successively
To the 22nd to the 1st tooth slice image, the cutting operation of the 24th to the 45th tooth slice image, each tooth is finally obtained
Contour line on sectioning image.
Further, in order to further such that the corresponding contour line of every tooth is smoother, closer to actual contour line,
The further correction to contour line is realized, following improvement project is embodiments provided：Based on initial tooth slice figure
As the contour line after upper adjustment, according to default segmentation rule, other tooth slice images are split, obtain other teeth
On sectioning image before the corresponding contour line of every tooth, based on pre-set user reciprocal force, on initial tooth slice image
Contour line after adjustment carries out secondary adjustment, obtains the contour line after secondary adjustment.After contour line after secondary adjustment is obtained,
Again based on the contour line after the secondary adjustment on initial tooth slice image, according to default segmentation rule, to other tooth slices
Image is split, and obtains on other tooth slice images the corresponding contour line of every tooth.
Specifically, the specific algorithm of user mutual power is as follows：
Wherein, SEEDuserFor the seed point set that user specifies, Nradius(x, y) is represented with (x, y) center of circle, with radius
For the circular scope of radius,Represent point (x0,y0) and point (x, y) Euclidean distance.When user's mouse is cut in initial tooth
Select on picture after seed point, the seed point that dental imaging partition tools are selected using user mutual power algorithm and user is given
One width of contour line to thrust, so as to play a part of accelerate contour line convergence and correct contour line.
It is similar with initial tooth slice image, other tooth slice images are being adjusted by active contour model
After whole, in order to further such that the contour line on other tooth slice images is smoother, closer to real time profile line, can be in base
Other tooth slice images, according to default segmentation rule, are carried out by the contour line after adjustment on initial tooth slice image
Segmentation, after obtaining on other tooth slice images the corresponding contour line of every tooth, based on pre-set user reciprocal force, to obtaining
Other tooth slice images on the corresponding contour line of every tooth be adjusted, follow-up cluster operation is then carried out again.
Further, the specific implementation of above-mentioned steps 104 can be：
A1, each tooth on initial tooth slice image is numbered.
Wherein, order tooth being numbered can be according to clockwise direction each tooth is carried out successively from it is little to
Big numbering, or according to counter clockwise direction each tooth is carried out from little big numbering successively, its numbering here is not done
Limit.
A2, the numbering teeth based on acquisition, with the contour line on initial tooth slice image as starting point, cut to two ends tooth
Contour line on picture is clustered, the corresponding contour line set of every tooth of acquisition.
Specifically, dental imaging partition tools can first by it is adjacent with current tooth slice image, clustered
Contour line upright projection on the tooth slice image of process on current tooth slice image, then determine respectively with it is current
The maximum projection of the intersecting area of each contour line on tooth slice image, and by with current tooth slice image on work as front-wheel
The maximum corresponding numbering teeth of projection of the intersecting area of profile is defined as the corresponding numbering teeth of current contour line.
Exemplary, if the 30th tooth slice image has carried out clustering processing, and the 31st tooth slice image is also not
Clustering processing is carried out, then when clustering processing is carried out to the 31st tooth slice image, is needed first by the 30th tooth slice figure
As in each upper contour line upright projection to the 31st tooth slice image, it is then determined that on the 31st tooth slice image
Current outline line respectively with the projection of the contour line of the 3rd tooth and the profile of the 4th tooth on the 30th tooth slice image
The projection of line is intersected, and the area intersected with the projection of the contour line of the 4th tooth is maximum, is finally defined as numbering teeth 4
The corresponding numbering teeth of current outline line, the tooth that current outline line is included is the 4th tooth.
Further, in order to further improve the efficiency for obtaining every tooth pixel model, initial tooth slice is being obtained
After the contour line after adjustment on image, first rule can be selected according to default, be selected from remaining tooth slice image
Tooth slice image to be split, is then only carried out to the tooth slice image to be split selected by default segmentation rule
Segmentation, obtains on tooth slice image to be split the corresponding contour line of every tooth, and non-selected tooth slice image
Then directly split using default interpolation algorithm when subsequent sections are filled.
Wherein, preset and select rule to be to be selected (such as every an image selection one according to equal difference mode
Image), it is also possible to selected according to non-equal difference mode, it is also possible to selected by User Defined.
Further, if only tooth slice image in part is split by way of active contour model, above-mentioned step
Rapid 105 specific implementation is changed into：
B1, according to default interpolation algorithm, it is determined that the corresponding contour line of every tooth on not divided tooth slice image.
Specifically, dental imaging partition tools can first determine adjacent with not divided tooth slice image and contain
There are two tooth slice images of contour line, wherein, not divided tooth slice image is located at two tooth slices for determining
In the middle of image；Secondly, the central point of each contour line on two tooth slice images of determination is calculated；Again, with each wheel
The central point of profile is starting point, determines the intersection point of the ray on preset direction and correspondence profile line；Finally, by identical tooth correspondence
Two contour lines on the corresponding intersection point of same preset direction be connected, obtain the friendship of line and not divided tooth slice image
Point, and the corresponding intersection point of each preset direction is connected, obtain the profile of correspondence tooth on not divided tooth slice image
Line.
Exemplary, if the 13rd tooth slice image is not divided, and the 12nd tooth slice image and the 14th tooth
Tooth sectioning image is divided, then calculate each wheel on the 12nd tooth slice image and the 14th tooth slice image first
The central point of profile, then the central point with each contour line is as starting point, determines ray and correspondence profile line on preset direction
Intersection point, such as a certain contour line is followed successively by with the intersection point of the ray of four direction up and down on the 12nd tooth slice image
A1, a2, a3 and a4, the ray of the corresponding contour line of same tooth and four direction up and down on the 14th tooth slice image
Intersection point be followed successively by b1, b2, b3 and b4, then a1 is connected with b1 respectively, a2 and b2 connections, a3 and b3 connections and a4 and b4 companies
Connect, and the intersection point of line and the 13rd tooth slice image is respectively c1, c2, c3 and c4, now by c1, c2, c3 and c4 sequentially
Connection, can obtain contour line of the tooth on the 13rd tooth slice image.
B2, the contour line of determination is added in the contour line set of corresponding tooth, obtains the corresponding renewal of every tooth
Contour line set afterwards.
B3, according to region-filling algorithm, each contour line in the contour line set after the corresponding renewal of every tooth is entered
Row area filling, obtains the pixel space model of every tooth.
To the corresponding tooth slice image of all maxillary teeths or the corresponding tooth slice image of all mandibular teeths
After being split, it is possible to obtain the set of the corresponding all contour lines of every tooth, now to each contour line set in it is every
Individual contour line carries out area filling, it is possible to obtain the corresponding pixel space model of every tooth, so as to subsequently using MC algorithms
Obtain the three-dimensional grid model of a whole set of tooth.
Further, according to said method embodiment, an alternative embodiment of the invention additionally provides a kind of dental imaging
Segmenting device, as shown in Fig. 2 the device mainly includes：Acquiring unit 21, adjustment unit 22, cutting unit 23, cluster cell
24 and fills unit 25.Wherein,
Acquiring unit 21, for obtaining on initial tooth slice image the corresponding initial profile line of every tooth, initial tooth
Tooth sectioning image is the image comprising maxillary teeth or mandibular teeth that user selects from all tooth slice images；
Adjustment unit 22, it is single to obtaining for according to the tooth on active contour model and initial tooth slice image
The corresponding initial profile line that unit 21 obtains is adjusted, the contour line after being adjusted；
Cutting unit 23, for the profile after the adjustment on the initial tooth slice image based on the acquisition of adjustment unit 22
Other tooth slice images, according to default segmentation rule, are split by line, obtain every tooth on other tooth slice images
Corresponding contour line；
Cluster cell 24, for according to default contour line clustering algorithm, institute's contour line dentulous being clustered, obtains
The corresponding contour line set of every tooth；
Fills unit 25, for according to region-filling algorithm, the corresponding profile of every tooth obtained to cluster cell 24
Each contour line in line set carries out area filling, obtains the pixel space model of every tooth, to obtain on all
After the pixel space model of jaw tooth and all mandibular teeths, the pixel space model of every tooth is carried out by MC algorithms
Calculate, obtain the three-dimensional grid model of every tooth.
The segmenting device of dental imaging provided in an embodiment of the present invention, can first obtain per on initial tooth slice image
The corresponding initial profile line of tooth；Secondly, according to active contour model, while initial to each on initial tooth slice image
Contour line is adjusted, and based on the contour line after the adjustment on the initial tooth slice image, it is right according to default segmentation rule
Other tooth slice images are split, and obtain on other tooth slice images the corresponding contour line of every tooth；Again, according to
Default contour line clustering algorithm, to institute's contour line dentulous clustering processing is carried out, while the corresponding profile of every tooth of acquisition
Line set；Finally, according to region-filling algorithm, while carrying out to each contour line in the corresponding contour line set of each tooth
Area filling, obtains the pixel space model of each tooth.It follows that the present invention can be on same tooth slice image
Different initial profile lines are adjusted, and after all contour lines are obtained, contour line are clustered, while obtaining each tooth
Contour line set, it is last simultaneously area filling to be carried out to each contour line, so as to realize to segmentation while multiple teeth (i.e.
The pixel space model of multiple teeth is obtained simultaneously), the efficiency of segmentation dental imaging is improve, and then improve based on CBCT teeth
The efficiency of tooth image reconstruction tooth three-dimensional grid model.
Further, as shown in figure 3, cutting unit 23, including：
Setup module 231, for from the tooth slice image adjacent with initial tooth slice image, will be with current dental
Sectioning image is adjacent, contour line on the tooth slice image containing contour line is used as correspondence on current dental sectioning image
The initial profile line of tooth；
Adjusting module 232, for according to the tooth on active contour model and current dental sectioning image, to corresponding
Initial profile line is adjusted, the contour line after being adjusted.
Further, as shown in figure 3, adjustment unit 22, is additionally operable to be based on initial tooth slice image in cutting unit 23
On adjustment after contour line, according to it is default segmentation rule, other tooth slice images are split, obtain other teeth and cut
On picture before the corresponding contour line of every tooth, based on pre-set user reciprocal force, to the tune on initial tooth slice image
Contour line after whole carries out secondary adjustment, obtains the contour line after secondary adjustment；
Cutting unit 23, for based on the contour line after the secondary adjustment on initial tooth slice image, according to default point
Rule is cut, other tooth slice images are split, obtain on other tooth slice images the corresponding contour line of every tooth.
Further, as shown in figure 3, adjustment unit 22, is additionally operable to be based on initial tooth slice image in cutting unit 23
On adjustment after contour line, according to it is default segmentation rule, other tooth slice images are split, obtain other teeth and cut
On picture after the corresponding contour line of every tooth, based on pre-set user reciprocal force, to other tooth slice images for obtaining
The corresponding contour line of upper every tooth is adjusted.
Further, as shown in figure 3, cluster cell 24, including：
Numbering module 241, for being numbered to each tooth on initial tooth slice image；
Cluster module 242, for the numbering teeth obtained based on numbering module 241, with initial tooth slice image
Contour line is starting point, is clustered to the contour line on the tooth slice image of two ends, the corresponding contour line collection of every tooth of acquisition
Close；
Cluster module 242, including：
Projection submodule 2421, for by tooth that is adjacent with current tooth slice image, having carried out clustering processing
Contour line upright projection on sectioning image is on current tooth slice image；
Determination sub-module 2422, intersect area most with each contour line on current tooth slice image for determining respectively
Big projection, and the corresponding tooth volume of the maximum projection of area will be intersected with the current outline line on current tooth slice image
Number it is defined as the corresponding numbering teeth of current outline line.
Further, as shown in figure 3, the device also includes：
Select unit 26, for the contour line after the adjustment that cutting unit 23 is based on initial tooth slice image, root
According to default segmentation rule, other tooth slice images are split, obtain every tooth correspondence on other tooth slice images
Contour line before, according to it is default select rule, tooth slice figure to be split is selected from remaining tooth slice image
Picture；
Cutting unit 23, for based on the contour line after the adjustment on initial tooth slice image, according to default segmentation rule
Then, tooth slice image to be split is split, obtains on tooth slice image to be split the corresponding wheel of every tooth
Profile.
Further, as shown in figure 3, fills unit 25, including：
Determining module 251, for according to default interpolation algorithm, it is determined that every tooth on not divided tooth slice image
Corresponding contour line；
Add module 252, for the contour line that determining module 251 determines to be added to the contour line set of corresponding tooth
In, the contour line set after the corresponding renewal of every tooth of acquisition；
Filling module 253, for according to region-filling algorithm, in the contour line set after the corresponding renewal of every tooth
Each contour line carries out area filling, obtains the pixel space model of every tooth.
Further, as shown in figure 3, determining module 251, including：
First determination sub-module 2511, for determining adjacent with not divided tooth slice image and having contained profile
Two tooth slice images of line, wherein, not divided tooth slice image is located in the two tooth slice images for determining
Between；
Calculating sub module 2512, for every on two tooth slice images for calculating the determination of the first determination sub-module 2511
The central point of individual contour line；
Second determination sub-module 2513, for the central point of each contour line that obtained with calculating sub module 2512 to rise
Point, determines the intersection point of the ray on preset direction and correspondence profile line；
Connection submodule 2514, for by the corresponding intersection point of same preset direction on corresponding two contour lines of identical tooth
It is connected, obtains the intersection point of line and not divided tooth slice image, and the corresponding intersection point of each preset direction is connected, obtains
Obtain the contour line of correspondence tooth on not divided tooth slice image.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, without the portion described in detail in certain embodiment
Point, may refer to the associated description of other embodiment.
It is understood that said method and the correlated characteristic in device can be referred to mutually.In addition, in above-described embodiment
" first ", " second " etc. be, for distinguishing each embodiment, and not represent the quality of each embodiment.
Those skilled in the art can be understood that, for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, may be referred to the corresponding process in preceding method embodiment, will not be described here.
Provided herein algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment.
Various general-purpose systems can also be used together based on teaching in this.As described above, construct required by this kind of system
Structure be obvious.Additionally, the present invention is also not for any certain programmed language.It is understood that, it is possible to use it is various
Programming language realizes the content of invention described herein, and the description done to language-specific above is to disclose this
Bright preferred forms.
In description mentioned herein, a large amount of details are illustrated.It is to be appreciated, however, that the enforcement of the present invention
Example can be put into practice in the case of without these details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help understand one or more in each inventive aspect, exist
Above in the description of the exemplary embodiment of the present invention, each feature of the present invention is grouped together into single enforcement sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
The more features of feature that the application claims ratio of shield is expressly recited in each claim.More precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific embodiment are expressly incorporated in the specific embodiment, wherein each claim itself
All as the separate embodiments of the present invention.
Those skilled in the art are appreciated that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Unit or component are combined into a module or unit or component, and can be divided in addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit is excluded each other, can adopt any
Combine to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so disclosed
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Profit is required, summary and accompanying drawing) disclosed in each feature can it is identical by offers, be equal to or the alternative features of similar purpose carry out generation
Replace.
Although additionally, it will be appreciated by those of skill in the art that some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment required for protection appoint
One of meaning can in any combination mode using.
The present invention all parts embodiment can be realized with hardware, or with one or more processor operation
Software module realize, or with combinations thereof realization.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) are realizing the state of accompanied electronic anti-theft device according to embodiments of the present invention
The some or all functions of some or all parts in detection method, equipment, server and system equipment.The present invention is also
Can be implemented as some or all equipment or program of device for performing method as described herein (for example, to count
Calculation machine program and computer program).Such program for realizing the present invention can be stored on a computer-readable medium, or
Person can have the form of one or more signal.Such signal can be downloaded from internet website and obtained, Huo Zhe
There is provided on carrier signal, or provide in any other form.
It should be noted that above-described embodiment the present invention will be described rather than limits the invention, and ability
Field technique personnel can design without departing from the scope of the appended claims alternative embodiment.In the claims,
Any reference markss between bracket should not be configured to limitations on claims.Word "comprising" is not excluded the presence of not
Element listed in the claims or step.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can come real by means of the hardware for including some different elements and by means of properly programmed computer
It is existing.If in the unit claim for listing equipment for drying, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and be run after fame
Claim.
Claims (9)
1. a kind of dividing method of dental imaging, methods described includes：
The corresponding initial profile line of every tooth is obtained on initial tooth slice image, the initial tooth slice image is user
Image of selected from all tooth slice images comprising maxillary teeth or mandibular teeth；
According to the tooth on active contour model and the initial tooth slice image, corresponding initial profile line is adjusted
Whole, after being adjusted contour line；
Based on the contour line after the adjustment on the initial tooth slice image, according to default segmentation rule, other teeth are cut
Picture is split, and obtains on other tooth slice images the corresponding contour line of every tooth；
According to default contour line clustering algorithm, institute's contour line dentulous is clustered, the corresponding profile of every tooth of acquisition
Line set；
According to region-filling algorithm, area filling is carried out to each contour line in the corresponding contour line set of every tooth, obtained
The pixel space model of every tooth is obtained, so as in the pixel space model for obtaining all maxillary teeths and all mandibular teeths
Afterwards, the pixel space model of every tooth is calculated by MC algorithms, obtains the three-dimensional grid model of every tooth；
Characterized in that, based on the contour line after the adjustment on the initial tooth slice image, it is right according to default segmentation rule
Other tooth slice images are split, and obtain on other tooth slice images the corresponding contour line of every tooth, including：
From the tooth slice image adjacent with the initial tooth slice image, by it is adjacent with current dental sectioning image,
The contour line on the tooth slice image containing contour line as on the current dental sectioning image correspondence tooth it is initial
Contour line；
According to the tooth on active contour model and the current dental sectioning image, corresponding initial profile line is adjusted
Whole, after being adjusted contour line；
Contour line after based on the adjustment on the initial tooth slice image, according to default segmentation rule, to other teeth
Sectioning image is split, and before obtaining on other tooth slice images the corresponding contour line of every tooth, methods described is also wrapped
Include：
Based on pre-set user reciprocal force, secondary adjustment is carried out to the contour line after the adjustment on the initial tooth slice image,
Obtain the contour line after secondary adjustment；
Contour line after based on the adjustment on the initial tooth slice image, according to default segmentation rule, to other teeth
Sectioning image is split, and after obtaining on other tooth slice images the corresponding contour line of every tooth, methods described is also wrapped
Include：
Based on pre-set user reciprocal force, the corresponding contour line of every tooth on other tooth slice images for obtaining is adjusted
It is whole.
2. method according to claim 1, it is characterised in that according to default contour line clustering algorithm, institute is dentulous
Contour line is clustered, the corresponding contour line set of every tooth of acquisition, including：
Each tooth on the initial tooth slice image is numbered；
Based on the numbering teeth for obtaining, with the contour line on the initial tooth slice image as starting point, to two ends tooth slice
Contour line on image is clustered, the corresponding contour line set of every tooth of acquisition；
Based on the numbering teeth for obtaining, with the contour line on the initial tooth slice image as starting point, to two ends tooth slice
Contour line on image is clustered, including：
Throw the contour line on tooth slice image that is adjacent with current tooth slice image, having carried out clustering processing is vertical
Shadow is on the current tooth slice image；
Determine respectively and intersect the maximum projection of area with each contour line on the current tooth slice image, and will with it is described
The corresponding numbering teeth of projection of the intersecting area maximum of current outline line on current tooth slice image is defined as described working as
The corresponding numbering teeth of front-wheel profile.
3. method according to claim 1, it is characterised in that after based on the adjustment on the initial tooth slice image
Contour line, according to default segmentation rule, other tooth slice images are split, obtain on other tooth slice images every
Before the corresponding contour line of tooth, methods described also includes：
Rule is selected according to default, tooth slice image to be split is selected from remaining tooth slice image；
Based on the contour line after the adjustment on the initial tooth slice image, according to default segmentation rule, to described to be split
Tooth slice image split, obtain on the tooth slice image to be split the corresponding contour line of every tooth.
4. method according to claim 3, it is characterised in that according to region-filling algorithm, to the corresponding wheel of every tooth
Each contour line in profile set carries out area filling, obtains the pixel space model of every tooth, including：
According to default interpolation algorithm, it is determined that the corresponding contour line of every tooth on not divided tooth slice image；
The contour line of determination is added in the contour line set of corresponding tooth, the profile after the corresponding renewal of every tooth of acquisition
Line set；
According to the region-filling algorithm, area is carried out to each contour line in the contour line set after the corresponding renewal of every tooth
Domain is filled, and obtains the pixel space model of every tooth.
5. the method according to right wants 4, it is characterised in that according to default interpolation algorithm, it is determined that not divided tooth is cut
The corresponding contour line of every tooth on picture, including：
It is determined that and containing contour line two tooth slice image adjacent with not divided tooth slice image, wherein,
The not divided tooth slice image is located in the middle of the two tooth slice images for determining；
Calculate the central point of each contour line on two tooth slice images of determination；
Central point with each contour line determines the intersection point of the ray on preset direction and correspondence profile line as starting point；
The corresponding intersection point of same preset direction on corresponding two contour lines of identical tooth is connected, obtain line with it is described not by
The intersection point of the tooth slice image of segmentation, and the corresponding intersection point of each preset direction is connected, not divided tooth described in acquisition
The contour line of correspondence tooth on tooth sectioning image.
6. a kind of segmenting device of dental imaging, described device includes：
Acquiring unit, for obtaining on initial tooth slice image the corresponding initial profile line of every tooth, the initial tooth
Sectioning image is the image comprising maxillary teeth or mandibular teeth that user selects from all tooth slice images；
Adjustment unit, for according to the tooth on active contour model and the initial tooth slice image, to the acquisition
The corresponding initial profile line that unit is obtained is adjusted, the contour line after being adjusted；
Cutting unit, for the profile after the adjustment on the described initial tooth slice image based on adjustment unit acquisition
Other tooth slice images, according to default segmentation rule, are split by line, obtain every tooth on other tooth slice images
Corresponding contour line；
Cluster cell, for according to default contour line clustering algorithm, institute's contour line dentulous being clustered, obtains every tooth
The corresponding contour line set of tooth；
Fills unit, for according to region-filling algorithm, the corresponding contour line collection of every tooth obtained to the cluster cell
Each contour line in conjunction carries out area filling, obtains the pixel space model of every tooth, to obtain all maxillary teeths
After the pixel space model of tooth and all mandibular teeths, the pixel space model of every tooth is counted by MC algorithms
Calculate, obtain the three-dimensional grid model of every tooth；
Characterized in that, the cutting unit, including：
Setup module, for from the tooth slice image adjacent with the initial tooth slice image, cutting with current dental
Picture is adjacent, contour line on the tooth slice image containing contour line is used as right on the current dental sectioning image
Answer the initial profile line of tooth；
Adjusting module, for according to the tooth on active contour model and the current dental sectioning image, to corresponding first
Beginning contour line is adjusted, the contour line after being adjusted；
The adjustment unit, is additionally operable in the cutting unit based on the profile after the adjustment on the initial tooth slice image
Other tooth slice images, according to default segmentation rule, are split by line, obtain every tooth on other tooth slice images
Before corresponding contour line, based on pre-set user reciprocal force, to the contour line after the adjustment on the initial tooth slice image
Secondary adjustment is carried out, the contour line after secondary adjustment is obtained；
The adjustment unit, is additionally operable in the cutting unit based on the profile after the adjustment on the initial tooth slice image
Other tooth slice images, according to default segmentation rule, are split by line, obtain every tooth on other tooth slice images
It is corresponding to every tooth on other tooth slice images of acquisition based on pre-set user reciprocal force after corresponding contour line
Contour line is adjusted；
The cluster cell, including：
Numbering module, for being numbered to each tooth on the initial tooth slice image；
Cluster module, for the numbering teeth obtained based on the numbering module, with the wheel on the initial tooth slice image
Profile is starting point, is clustered to the contour line on the tooth slice image of two ends, the corresponding contour line set of every tooth of acquisition；
The cluster module, including：
Projection submodule, for by tooth slice image that is adjacent with current tooth slice image, having carried out clustering processing
On contour line upright projection on the current tooth slice image；
Determination sub-module, for determining respectively area maximum is intersected with each contour line on the current tooth slice image
Projection, and the corresponding tooth volume of the maximum projection of area will be intersected with the current outline line on the current tooth slice image
Number it is defined as the corresponding numbering teeth of the current outline line.
7. device according to claim 6, it is characterised in that described device also includes：
Select unit, for the contour line after the adjustment that the cutting unit is based on the initial tooth slice image, root
According to default segmentation rule, other tooth slice images are split, obtain every tooth correspondence on other tooth slice images
Contour line before, according to it is default select rule, tooth slice figure to be split is selected from remaining tooth slice image
Picture；
The cutting unit, for based on the contour line after the adjustment on the initial tooth slice image, according to default segmentation
Rule, splits to the tooth slice image to be split, obtains every tooth on the tooth slice image to be split
The corresponding contour line of tooth.
8. device according to claim 7, it is characterised in that the fills unit, including：
Determining module, for according to default interpolation algorithm, it is determined that every tooth is corresponding on not divided tooth slice image
Contour line；
Add module, for the contour line that the determining module determines to be added in the contour line set of corresponding tooth, obtains
Contour line set after the corresponding renewal of every tooth；
Filling module, for according to the region-filling algorithm, to every in the contour line set after the corresponding renewal of every tooth
Individual contour line carries out area filling, obtains the pixel space model of every tooth.
9. device according to claim 8, it is characterised in that the determining module, including：
First determination sub-module is adjacent with not divided tooth slice image and containing contour line two for determining
Tooth slice image, wherein, the not divided tooth slice image is located in the middle of the two tooth slice images for determining；
Calculating sub module, for calculating each contour line on two tooth slice images that first determination sub-module determines
Central point；
Second determination sub-module, for the central point of each contour line that obtained with the calculating sub module as starting point, it is determined that in advance
The intersection point of ray and correspondence profile line on set direction；
Connection submodule, for the corresponding intersection point of same preset direction on corresponding two contour lines of identical tooth to be connected, obtains
The intersection point of line and the not divided tooth slice image is obtained, and the corresponding intersection point of each preset direction is connected, obtained
The contour line of correspondence tooth on the not divided tooth slice image.
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 | |
| CN106709917B (en) | Neural network model training method, device and system | |
| CN103544711B (en) | The autoegistration method of remote sensing image | |
| US8059873B2 (en) | Volume of interest selection | |
| US20150036790A1 (en) | Method and apparatus to generate a panoramic radiography | |
| JP4889182B2 (en) | Depth map generation by hypothesis mixing in Bayesian framework | |
| US7280106B2 (en) | Apparatus and method for generating texture maps for use in 3D computer graphics | |
| CN106779775A (en) | Region client division methods, divide device and client's distribution system | |
| US9652673B2 (en) | Method for identifying calcification portions in dual energy CT contrast agent enhanced scanning image | |
| CN103460254B (en) | Method and device for automatically detecting brightness based on image content | |
| Schunke et al. | TINA manual landmarking tool: software for the precise digitization of 3D landmarks | |
| KR102132369B1 (en) | Tooth segmentation system and method | |
| CN109377500A (en) | Image partition method and terminal device neural network based | |
| CN108961398A (en) | A kind of automatic filling algorithm of tooth undercut grid model based on normal vector angle | |
| CN102096939B (en) | Medical mass data-oriented multi-resolution volume rendering method | |
| CN106652008A (en) | Method automatically forming grid and shader multi-layer detail | |
| GB2406252A (en) | Generation of texture maps for use in 3D computer graphics | |
| 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 | |
| CN101248459A (en) | A method of generating a 2D image of a 3D object | |
| CN108022216A (en) | A kind of system and method for reduction MPR artifacts | |
| CN107025684A (en) | Large scale scene based on model component feature is fixed frame per second and drawn and device | |
| KR20210018661A (en) | Method for recommending crown model and prosthetic CAD apparatus therefor | |
| Schmitz et al. | Efficient and quality contouring algorithms on the GPU | |
| Manssour et al. | Visualizing inner structures in multimodal volume data |
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 |