CN117495801A - Implant planting parameter determining method based on image segmentation network - Google Patents

Implant planting parameter determining method based on image segmentation network Download PDF

Info

Publication number
CN117495801A
CN117495801A CN202311450735.XA CN202311450735A CN117495801A CN 117495801 A CN117495801 A CN 117495801A CN 202311450735 A CN202311450735 A CN 202311450735A CN 117495801 A CN117495801 A CN 117495801A
Authority
CN
China
Prior art keywords
implant
implantation
tooth
implanted
radius
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.)
Pending
Application number
CN202311450735.XA
Other languages
Chinese (zh)
Inventor
王全玉
欧立炜
韦少江
易纯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Peking University School of Stomatology
Original Assignee
Beijing Institute of Technology BIT
Peking University School of Stomatology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Technology BIT, Peking University School of Stomatology filed Critical Beijing Institute of Technology BIT
Priority to CN202311450735.XA priority Critical patent/CN117495801A/en
Publication of CN117495801A publication Critical patent/CN117495801A/en
Pending legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
    • A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
    • A61C8/00—Means to be fixed to the jaw-bone for consolidating natural teeth or for fixing dental prostheses thereon; Dental implants; Implanting tools
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06T2207/10004—Still image; Photographic image
    • 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
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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 an implant planting parameter determining method based on an image segmentation network, which is used for realizing the identification and segmentation of teeth in an oral cavity area through the image segmentation network and calculating the tooth position, the implantation point, the implantation depth, the implantation axial direction and the implantation radius of an implant to be implanted by utilizing an image processing technology. The invention comprises an image segmentation network model based on deep learning, a dental position and implantation point calculation method, an implantation depth calculation method, an implantation axial calculation method and an implantation radius calculation method. Aiming at the limitations that the prior art needs to consume a great deal of time and energy cost, relies on clinical experience of medical staff, has unavoidable personal errors and the like, the invention combines an image segmentation network model based on a deep learning technology with an oral implant planting parameter determining method based on an image processing technology, and ensures accurate positioning precision while realizing intelligent positioning of the oral implant automatically.

Description

Implant planting parameter determining method based on image segmentation network
Technical field:
the invention relates to the technical field of artificial intelligence and image processing, in particular to an image segmentation method of an oral cavity tooth area and a planting parameter determination method of a quasi-implanted implant.
The background technology is as follows:
dental implant restoration has become one of the most important ways to restore missing teeth, and the surgical implantation of an implant into an ideal position is key to the success of the implant. According to the medical planting requirements, the planting parameters of the implant are divided into the following parts: dental site and implantation point, implantation depth, implantation axis, implantation radius.
The positioning mode of the implant can be divided into a traditional mode and a digital mode. The traditional mode, commonly called "free hand" planting, relies on preoperative analysis and intra-operative judgment of doctors, is greatly influenced by personal subjective factors such as clinical experience and working state of doctors, requires more time and energy, and is easy to cause human errors. To reduce the effects of these adverse factors, digitization techniques of three-dimensional reconstruction, static guides, dynamic navigation are introduced into the implantation procedure. These techniques allow the clinician to perform the virtual implantation of the implant in software in advance, finding the ideal location of the implant. However, in the case of virtual implant, the physician still needs to manually design the implant implantation position, which is time-consuming and labor-consuming, and depends largely on the clinical experience of the physician, and is essentially a non-intelligent implant positioning technique which depends entirely on manpower.
The invention comprises the following steps:
the invention aims to overcome the limitations of the prior art, and provides an implant planting parameter determining method based on an image segmentation network, which is used for realizing the identification and segmentation of teeth in an oral cavity area through the image segmentation network and calculating the tooth position, the implantation point, the implantation depth, the implantation axial direction and the implantation radius of an implant to be implanted by utilizing an image processing technology.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
the invention provides an implant planting parameter determining method based on an image segmentation network, which comprises the following steps of:
step 1: for three-dimensional oral Cone Beam CT (CBCT) medical image data, slicing from transverse positions according to fixed intervals to construct oral two-dimensional slice data for segmentation;
step 2: labeling the two-dimensional slice data of the oral cavity, distinguishing a tooth area and a background area by adopting different colors, and performing binarization processing on the labeled two-dimensional image to obtain an oral cavity two-dimensional slice label;
step 3: dividing the two-dimensional slice data and the labels of the oral cavity into a training set and a testing set, training an image segmentation network based on a deep learning technology by using the training set, performing layer-by-layer training by adopting supervised learning until the error is reduced to be within an expected range, and evaluating the performance of the model on the testing set to obtain a trained image segmentation network model;
step 4: inputting the two-dimensional slice data to be segmented into the trained image segmentation network model to obtain a segmentation result of the oral cavity transverse teeth;
step 5: determining the tooth position and the implantation point of the implant to be implanted according to the segmentation result by a tooth position and implantation point calculation method;
step 6: determining the implantation depth of the implant to be implanted according to the segmentation result by an implantation depth calculation method;
step 7: determining the implantation axial direction of the implant to be implanted according to the segmentation result by an implantation axial direction calculation method;
step 8: and determining the implantation radius of the implant to be implanted according to the segmentation result by an implantation radius calculation method.
Furthermore, the data set is divided into a training set and a test set according to a certain proportion in the step 3, and the data of the training set is enhanced by adopting methods of random cutting, rotation, mirror image application, translation shake and the like so as to make up for the defect of the training sample size.
Further, the image segmentation network in step 3 includes a feature extraction module and a resolution restoration module, and each decoder layer is connected to the feature map correspondingly clipped from the same layer of the encoder during decoding.
Further, the dental position and implantation point calculating method in step 5 includes the following steps:
step (1), screening out sections of the dental neck region based on the segmentation result of the oral cavity transverse teeth obtained in the step (4);
step (2), denoising the slice;
step (3), determining the radius and the circle center of the maximum inscribed circle of the cross section of each tooth;
and (4) judging whether tooth missing exists between adjacent teeth one by one, and further calculating the implantation point of the implant under the condition of tooth missing.
Further, the implantation depth calculating method in step 6 includes the following steps:
step (1), determining the tooth position and the implantation point of an implant to be implanted based on a tooth position and implantation point calculation method;
step (2), calculating the depth of two teeth adjacent to the implant tooth to be implanted according to a tooth depth expression based on the segmentation result of the oral cavity transverse tooth obtained in the step 4;
and (3) calculating the implantation depth of the implant to be implanted based on the depths of the two adjacent teeth, and further determining the optimal length model of the implant to be implanted.
Further, in the implantation depth calculating method, the tooth depth expression in step (2) is calculated according to the number of slices from the neck to the root and the slice spacing, and the specific expression is:
Deep＝n×d
where n represents the number of slices from the neck to the root, and d represents the slice pitch of adjacent slices.
Further, the method for calculating the implantation axis of step 7, a technical scheme thereof includes the following steps:
step (1), determining the tooth position and the implantation point of an implant to be implanted based on a tooth position and implantation point calculation method;
step (2), calculating the maximum inscribed circle center of the cross section of two teeth adjacent to the implant tooth position to be implanted in each slice based on the segmentation result of the oral cavity transverse tooth obtained in the step 4, and marking the maximum inscribed circle center as a left adjacent tooth center point set L and a right adjacent tooth center point set R;
step (3), for the point set L and the point set R, respectively establishing a space coordinate system by taking the circle center coordinate of the innermost inscribed circle as an original point, the sagittal axis as an x axis, the coronal axis as a y axis and the vertical axis as a z axis;
fitting a space axial equation of the left and right adjacent teeth based on the point sets L and R;
and (5) calculating the angles of the two adjacent tooth axial equations deviating from three coordinate axes of X, Y and Z, and further determining the implantation axial direction of the implant to be implanted.
Further, the method for calculating the implantation axis of step 7, another technical scheme thereof includes the following steps:
step (1), determining the tooth position and the implantation point of an implant to be implanted based on a tooth position and implantation point calculation method;
step (2), repeating the step (1) on each slice based on the segmentation result of the oral cavity transverse teeth obtained in the step (4) to obtain a circle center set C of the maximum inscribed circle at the implant tooth position to be implanted;
step (3), for the circle center set C, establishing a space coordinate system by taking the circle center coordinate of the inscribed circle closest to the tooth root as an original point, the sagittal axis as an x axis, the coronal axis as a y axis and the vertical axis as a z axis;
fitting a space axial equation of the implant to be implanted based on the circle center set C;
and (5) calculating the angles of the axial equation deviating from three coordinate axes X, Y and Z, and further determining the implantation axial direction of the implant to be implanted.
Further, the implantation radius calculation method in step 8, a technical scheme thereof includes the following steps:
step (1), determining the tooth position of the implant to be implanted and the maximum inscribed circle radius and circle center of two adjacent tooth cross sections based on the tooth position and the implantation point calculation method;
step (2), calculating the implantation radius of the implant to be implanted according to the radius expression;
and (3) determining the optimal radius model of the implant to be implanted based on the calculated implantation radius.
Furthermore, according to the "safe distance principle", the implant needs to have a safe distance d from the adjacent teeth on both sides, so the radius expression in the step (2) in the implantation radius calculation method is specifically expressed as:
wherein R represents the implantation radius of the implant to be implanted, R i And R is j Respectively representing the radius of the maximum inscribed circle of the cross sections of the two adjacent teeth, and D represents the Euler distance of the circle center of the maximum inscribed circle of the cross sections of the two adjacent teeth.
Further, the implantation radius calculation method in step 8, another technical scheme thereof includes the following steps:
step (1), determining the tooth position of the implant to be implanted and the radius of the maximum inscription circle at the tooth position based on the tooth position and the implantation point calculation method;
step (2), repeating the step (1) on each slice to obtain a radius set S of the maximum inscribed circle at the tooth position of the implant to be implanted;
and (3) selecting the minimum value in the radius set S as the implantation radius of the implant to be implanted, and determining the optimal radius model of the implant to be implanted.
Aiming at the limitations that a great deal of time and energy cost are required to be consumed, the clinical experience of medical staff is relied on, unavoidable human errors exist and the like in the prior art, the image segmentation network model based on deep learning and the oral implant implantation parameter determination method based on the image processing technology are fused, intelligent positioning of the oral implant is automatically realized, and meanwhile, accurate positioning precision is ensured.
Description of the drawings:
FIG. 1 is a flow chart of a method provided by the invention.
Fig. 2 is a schematic diagram of an image segmentation network based on U-Net according to an embodiment of the present invention.
Fig. 3 is a flowchart of a method for calculating a dental implant position and an implant point according to embodiment 1 of the present invention.
Fig. 4 is a flowchart of a method for calculating a dental implant site according to embodiment 2 of the present invention.
Fig. 5 is a flowchart of an implantation depth calculating method according to embodiment 1/2 of the present invention.
Fig. 6 is a flowchart of an implantation axial calculation method according to embodiment 1 of the present invention.
Fig. 7 is a flowchart of an implantation axial calculation method according to embodiment 2 of the present invention.
Fig. 8 is a flowchart of an implantation radius calculation method according to embodiment 1 of the present invention.
Fig. 9 is a flowchart of an implantation radius calculation method according to embodiment 2 of the present invention.
The specific implementation method comprises the following steps:
in order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, the invention provides an implant planting parameter determining method based on an image segmentation network, which comprises the following steps:
step 1: three-dimensional oral cavity CBCT image data are obtained, and the existing medical image software RadiAnt DICOM Viewer (64-bit, professional edition) is used for slicing the three-dimensional image from a transverse position at intervals of 0.2mm to obtain oral cavity two-dimensional slice data.
Step 2: labeling the two-dimensional slice data of the oral cavity by using labelme software, distinguishing a tooth area and a background area by adopting two colors of white and black, and performing binarization processing on the labeled two-dimensional image to obtain the two-dimensional slice label of the oral cavity.
Step 3: dividing the two-dimensional slice data of the oral cavity and the label into a training set and a testing set according to the ratio of 7:3, training an image segmentation network based on U-Net by using the training set, training layer by adopting supervised learning until the error is reduced to be within an expected range, and evaluating the performance of the model on the testing set to obtain a trained image segmentation network model.
Fig. 2 shows a basic structure of the U-Net based image segmentation network, which includes a feature extraction module and a resolution recovery module. The overall architecture employs a 5-layer symmetric encoder-decoder architecture. Wherein the encoder has four sub-modules, each comprising two convolutional layers, after which the downsampling is achieved by one max pooling layer. In consideration of the presence of speckle noise in actual data, the present embodiment uses an average pooling layer to replace the original maximum pooling layer for noise reduction processing. The resolution of the input image is 572x572 and the resolutions of the 1 st to 5 th blocks are 572x572,284x284,140x140,68x68 and 32x32, respectively. The decoder also contains four sub-modules, the resolution is sequentially increased by an up-sampling operation until it coincides with the resolution of the input image. The network also uses a jump connection to connect the up-sampling result to the output of a sub-module in the encoder with the same resolution as the input of the next sub-module in the decoder.
In terms of optimizer selection, this embodiment employs an Adam optimizer. The loss function selects a binary cross entropy loss function considering that the U-Net adopts binary segmentation in the segmentation process. In the aspect of network training, the embodiment adopts a grid search algorithm to search parameters, continuously feeds the training set until the training times or loss reaches a set threshold value, stores network model parameters, shifts into a test set, and finishes training if no over-fitting or under-fitting problem is determined.
Step 4: inputting the two-dimensional slice data to be segmented into the trained image segmentation network model to obtain the segmentation result of the oral cavity transverse teeth.
Step 5: and (3) determining the tooth position and the implantation point of the implant to be implanted by a tooth position and implantation point calculation method based on the image processing technology according to the segmentation result in the step (4).
Fig. 3 is a flowchart of a dental position and implantation point calculating method based on the image processing technology in embodiment 1, which specifically includes the following steps:
step (1), screening a slice set between the upper and lower 2mm positions of the dental neck based on the segmentation result of the oral cavity transverse teeth obtained in the step (4);
step (2), for the slice set, image denoising is realized through Gaussian filtering;
step (3), extracting the rough outline of each tooth through an edge detection operator for the denoised slice set, and further determining the maximum inscribed circle radius and circle center of each tooth cross section;
step (4), fitting the maximum inscribed circle center of each tooth cross section by adopting a curve equation to obtain a curve equation about the maximum inscribed circle center of the tooth cross section;
step (5), for two adjacent teeth i and j, if they satisfy the missing tooth expression(wherein R is i And R is j Respectively representing the maximum inscribed circle radius of the cross sections of the two teeth, wherein D represents the Euler distance of the circle centers of the maximum inscribed circles of the cross sections of the two teeth, k is an adjustable parameter, k=3 is taken in the embodiment), and the fact that the teeth are missing between i and j is judged, and implant implantation can be carried out;
and (6) under the condition of tooth deficiency, calculating the middle point of the maximum inscribed circle center of the cross section of the two teeth i and j based on the curve equation, and taking the middle point as an implantation point of the implant to be implanted.
Fig. 4 is a flowchart of a dental position and implantation point calculating method based on the image processing technology in embodiment 2, which specifically includes the following steps:
step (1), screening a slice set between the upper and lower 2mm positions of the dental neck based on the segmentation result of the oral cavity transverse teeth obtained in the step (4);
step (2), for the slice set, image denoising is realized through Gaussian filtering;
step (3), extracting the rough outline of each tooth from the denoised slice set through an edge detection operator;
step (4), based on the rough outline of each tooth, two tangent lines are fitted on the inner side edge and the outer side edge of the tooth area (wherein the inner side edge refers to the side close to the tongue part, and the outer side edge refers to the side close to the lip part), so as to form the rough outline of the tooth area;
step (5), based on the rough outline of the tooth area, for any two adjacent teeth, making a maximum inscribed circle along the outline of the tooth area and the outline of the adjacent teeth: if the radius of the largest inscribed circle is larger than the minimum implant radius model (1.65 mm), judging that the teeth between the two adjacent teeth are missing, and implanting the implant;
and (6) taking the center of the maximum inscribed circle as an implantation point of the implant under the condition of tooth deficiency.
Step 6: and (3) determining the implantation depth of the implant to be implanted by an implantation depth calculation method based on an image processing technology according to the segmentation result in the step (4).
Fig. 5 is a flowchart of the implantation depth calculation method based on the image processing technology in embodiment 1 and embodiment 2, specifically including the following steps:
step (1), determining the tooth position and the implantation point of the implant to be implanted based on the tooth position and the implantation point calculation method in the embodiment 1 or the embodiment 2;
step (2), based on the segmentation result of the oral cavity transverse teeth obtained in the step (4), calculating the depth of two teeth adjacent to the implant tooth to be implanted according to a tooth depth expression deep=n×d (wherein n represents the number of slices from the tooth neck to the tooth root, and d represents the slice spacing between adjacent slices);
and (3) taking the average depth of the two adjacent teeth as the implantation depth of the implant to be implanted, and selecting the maximum implant length model with the length smaller than the implantation depth of the implant to be implanted.
The implant model used in this example was CAMLOG TM SCREW-LINE, thus the implant length model in step (3) in the implantation depth calculation method is four, namely 9mm, 11mm, 13mm and 16mm respectively.
Step 7: and (3) determining the implantation axial direction of the implant to be implanted by an implantation axial direction calculation method based on an image processing technology according to the segmentation result in the step (4).
Fig. 6 is a flowchart of an implantation axial calculation method based on the image processing technology in embodiment 1, specifically including the following steps:
step (1), determining the tooth position of the implant to be implanted based on the tooth position and the implantation point calculation method in the embodiment 1;
step (2), calculating the maximum inscribed circle center of the cross section of two teeth adjacent to the implant tooth position to be implanted in each slice based on the segmentation result of the oral cavity transverse tooth obtained in the step 4, and marking the maximum inscribed circle center as a left adjacent tooth center point set L and a right adjacent tooth center point set R;
step (3), for the point set L and the point set R, respectively establishing a space coordinate system by taking the center coordinates of an inscribed circle closest to the tooth root as an origin, the sagittal axis as an x axis, the coronal axis as a y axis and the vertical axis as a z axis;
step (4), fitting the point sets L and R based on a least square method, and taking the fitted space linear equation as an axial equation of the left adjacent tooth and the right adjacent tooth respectively;
and (5) calculating the angles of the two adjacent tooth axial equations deviating from three coordinate axes of X, Y and Z, and taking the average value of the angles deviating from the three coordinate axes as the implantation axial direction of the implant (adopting angle preparation, wherein the value interval is [0,90 ]).
Fig. 7 is a flowchart of an implantation axial calculation method based on the image processing technology in embodiment 2, specifically including the following steps:
step (1), determining the tooth position and the implantation point (namely the center of the maximum inscription circle) of the implant to be implanted based on the tooth position and the implantation point calculation method in the embodiment 2;
step (2), repeating the step (1) on each slice based on the segmentation result of the oral cavity transverse teeth obtained in the step (4) to obtain a circle center set C of the maximum inscribed circle at the implant tooth position to be implanted;
step (3), for the circle center set C, establishing a space coordinate system by taking the circle center coordinate of the inscribed circle closest to the tooth root as an original point, the sagittal axis as an x axis, the coronal axis as a y axis and the vertical axis as a z axis;
step (4), fitting a circle center set C based on a least square method, and taking the fitted space linear equation as an axial equation of the implant;
and (5) calculating the angles of the axial equation deviating from three coordinate axes of X, Y and Z, and taking the angles deviating from the three coordinate axes as the implantation axial of the implant to be implanted (adopting angle preparation, wherein the value interval is [0,90 ]).
Step 8: and (3) determining the implantation radius of the implant to be implanted by an implantation radius calculation method based on an image processing technology according to the segmentation result in the step (4).
Fig. 8 is a flowchart of an implantation radius calculation method based on the image processing technology in embodiment 1, specifically including the following steps:
step (1), determining the tooth position of the implant to be implanted and the maximum inscribed circle radius and circle center of the cross sections of two adjacent teeth based on the tooth position and implantation point calculation method in the embodiment 1;
step (2), according to the safety distance principle, the implant needs to have a safety distance of 1.5mm from the bilateral adjacent teeth, so that the implant is expressed according to the radius(wherein R represents the implantation radius of the implant to be implanted, R i And R is j Respectively representing the maximum inscribed circle radius of the cross sections of two teeth, D representing the Euler distance of the centers of the maximum inscribed circles of the cross sections of two teeth), and calculating the implant to be implantedAn implantation radius;
and (3) selecting the maximum model with the radius smaller than the implantation radius from the implant radius models.
Fig. 9 shows a flowchart of the implantation radius calculation method based on the image processing technology in embodiment 2, specifically including the following steps:
step (1), determining the tooth position of the implant to be implanted and the radius of the maximum inscription circle at the tooth position based on the tooth position and the implantation point calculation method in the embodiment 2;
step (2), repeating the step (1) on each slice to obtain a radius set S of the maximum inscribed circle at the tooth position of the implant to be implanted;
and (3) selecting the minimum value in the radius set S as the implantation radius of the implant to be implanted, and selecting the maximum model with the radius smaller than the implantation radius from the implant radius models.
The implant model used in this example was CAMLOG TM SCREW-LINE, thus, five types of implant radius were used in the implant radius calculation method of example 1 and example 2 in step (3), 1.65mm, 1.9mm, 2.15mm, 2.5mm and 3mm, respectively.
Finally, it should be noted that the above embodiments are only for illustrating the technical scheme of the present invention, and are not limiting; while the invention has been described in detail with reference to the foregoing embodiments, it will be appreciated by those skilled in the art that variations may be made in the techniques described in the foregoing embodiments, or equivalents may be substituted for elements thereof; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (8)

1. The implant planting parameter determining method based on the image segmentation network is characterized by comprising the following steps of:
step 1, acquiring oral cavity CBCT data, slicing from a transverse position according to a fixed interval, and constructing oral cavity two-dimensional slice data;
step 2, labeling the two-dimensional slice data of the oral cavity to obtain an oral cavity two-dimensional slice label;
step 3, dividing the two-dimensional slice data and the labels of the oral cavity into a training set and a testing set, training the image segmentation network model in the training set, and evaluating the performance of the model on the testing set;
step 4, inputting the two-dimensional slice data to be segmented into the trained image segmentation network model to obtain a segmentation result of the oral cavity transverse teeth;
step 5, determining the tooth position and the implantation point of the implant to be implanted according to the segmentation result by a tooth position and implantation point calculation method;
step 6, determining the implantation depth of the implant to be implanted according to the segmentation result by an implantation depth calculation method;
step 7, determining the implantation axial direction of the implant to be implanted according to the segmentation result by an implantation axial direction calculation method;
and 8, determining the implantation radius of the implant to be implanted by an implantation radius calculation method according to the segmentation result.
2. The method according to claim 1, wherein in the step 5, a dental implant and implant point calculation method is implemented based on a missing tooth expression, and the method comprises the following steps:
step (1), screening out sections of the dental neck region based on the segmentation result of the oral cavity transverse teeth;
step (2), denoising the slice;
step (3), determining the approximate outline of each tooth, and further determining the maximum inscribed circle radius and the circle center of the cross section of each tooth;
step (4), fitting a curve equation about the maximum inscribed circle center of the tooth cross section aiming at the maximum inscribed circle center of each tooth cross section;
step (5), based on the lack of tooth expression(wherein i and j are the numbers of two adjacent teeth, R i And R is j Respectively representing the maximum inscribed circle radius of the cross sections of two teeth, D representing the Euler distance of the circle centers of the maximum inscribed circles of the cross sections of two teeth, k being an adjustable parameter), and judging whether teeth lack exist between adjacent teeth one by one;
and (6) calculating the implantation point of the implant to be implanted based on a curve equation under the condition of tooth deficiency.
3. The method according to claim 1, wherein in the step 5, the other dental position and implantation point calculation method is implemented based on a maximum inscribed circle, and comprises the steps of:
step (1), screening out sections of the dental neck region based on the segmentation result of the oral cavity transverse teeth;
step (2), denoising the slice;
a step (3) of determining the general contour of each tooth;
step (4), based on the approximate contour of each tooth, two tangent lines are fitted on the inner side edge and the outer side edge of the tooth area (wherein the inner side edge refers to the side close to the tongue part and the outer side edge refers to the side close to the lip part), so as to form the approximate contour of the tooth area;
step (5), based on the rough outline of the tooth area, for any two adjacent teeth, making a maximum inscribed circle along the outline of the tooth area and the outline of the adjacent teeth: if the radius of the largest inscribed circle is larger than the minimum implant radius model, judging that the teeth between the two adjacent teeth are missing, and implanting the implant;
and (6) taking the center of the maximum inscribed circle as the implantation point of the implant under the condition of tooth deficiency.
4. The method for determining implant parameters based on image segmentation network according to claim 1, wherein in the step 6, the method for calculating the implantation depth comprises the following steps:
step (1), determining the tooth position and the implantation point of an implant to be implanted based on a tooth position and implantation point calculation method;
step (2), calculating the depth of two teeth adjacent to the implant tooth to be implanted according to a tooth depth expression deep=n×d (wherein n represents the number of slices from the tooth neck to the tooth root, and d represents the slice spacing between adjacent slices) based on the segmentation result of the tooth of the oral cavity transection position;
and (3) calculating the implantation depth of the implant to be implanted based on the depths of the two adjacent teeth, and further determining the optimal length model of the implant to be implanted.
5. The method for determining implant parameters based on image segmentation network according to claim 1, wherein in step 7, an implant axial calculation method is calculated based on the adjacent tooth axial information, and comprises the following steps:
step (1), determining the tooth position of an implant to be implanted based on a tooth position and an implantation point calculation method;
calculating the maximum inscribed circle center of the cross section of two teeth adjacent to the implant tooth position to be implanted in each slice based on the segmentation result of the teeth at the oral cavity transverse position, and marking the maximum inscribed circle center as a left adjacent tooth center point set L and a right adjacent tooth center point set R;
step (3), for the point set L and the point set R, respectively establishing a space coordinate system by taking the center coordinates of an inscribed circle closest to the tooth root as an origin, the sagittal axis as an x axis, the coronal axis as a y axis and the vertical axis as a z axis;
step (4), fitting the point sets L and R based on a least square method, and taking the fitted space linear equation as an axial equation of the left adjacent tooth and the right adjacent tooth respectively;
and (5) calculating the angles of the two adjacent tooth axial equations deviating from three coordinate axes of X, Y and Z, and further determining the implantation axial direction of the implant to be implanted.
6. The method according to claim 1, wherein in the step 7, another method for calculating the implantation axis is calculated based on the maximum inscribed circle center information at the point of the planned implantation, and comprises the steps of:
step (1), determining the tooth position and the implantation point (namely the center of the maximum inscription circle) of the implant to be implanted based on a tooth position and implantation point calculation method;
step (2), repeating the step (1) on each slice based on the segmentation result of the oral cavity transverse teeth obtained in the step (4) to obtain a circle center set C of the maximum inscribed circle at the implant tooth position to be implanted;
step (3), for the circle center set C, establishing a space coordinate system by taking the circle center coordinate of the inscribed circle closest to the tooth root as an original point, the sagittal axis as an x axis, the coronal axis as a y axis and the vertical axis as a z axis;
step (4), fitting a circle center set C based on a least square method, and taking the fitted space linear equation as an axial equation of the implant;
and (5) calculating the angles of the axial equation deviating from three coordinate axes X, Y and Z, and further determining the implantation axial direction of the implant to be implanted.
7. The method for determining implant parameters based on image segmentation network according to claim 1, wherein in the step 8, an implant radius calculation method is calculated based on maximum inscribed circle radius information of the adjacent tooth cross section, and comprises the following steps:
step (1), determining the tooth position of the implant to be implanted and the maximum inscribed circle radius and circle center of two adjacent tooth cross sections based on the tooth position and the implantation point calculation method;
step (2), according to the radius expression(wherein R represents the implantation radius of the implant to be implanted, i and j are the numbers of two adjacent teeth, R i And R is j Respectively representing the maximum inscribed circle radius of the cross sections of two teeth, D representing the Euler distance of the centers of the maximum inscribed circles of the cross sections of two adjacent teeth, D representing the safe distance between the implant and the adjacent teeth on two sides), and calculating the implant to be implantedAn implantation radius;
and (3) determining the optimal radius model of the implant to be implanted based on the calculated implantation radius.
8. The method according to claim 1, wherein in the step 8, another implantation radius calculation method is calculated based on the maximum inscribed circle radius information at the point of intended implantation, and comprises the steps of:
step (1), determining the tooth position of the implant to be implanted and the radius of the maximum inscription circle at the tooth position based on the tooth position and the implantation point calculation method;
step (2), repeating the step (1) on each slice to obtain a radius set S of the maximum inscribed circle at the tooth position of the implant to be implanted;
and (3) selecting the minimum value in the radius set S as the implantation radius of the implant to be implanted, and determining the optimal radius model of the implant to be implanted.
CN202311450735.XA 2023-11-02 2023-11-02 Implant planting parameter determining method based on image segmentation network Pending CN117495801A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311450735.XA CN117495801A (en) 2023-11-02 2023-11-02 Implant planting parameter determining method based on image segmentation network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311450735.XA CN117495801A (en) 2023-11-02 2023-11-02 Implant planting parameter determining method based on image segmentation network

Publications (1)

Publication Number Publication Date
CN117495801A true CN117495801A (en) 2024-02-02

Family

ID=89666977

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311450735.XA Pending CN117495801A (en) 2023-11-02 2023-11-02 Implant planting parameter determining method based on image segmentation network

Country Status (1)

Country Link
CN (1) CN117495801A (en)

Similar Documents

Publication Publication Date Title
US20200305808A1 (en) Automated Tooth Localization, Enumeration, and Diagnostic System and Method
CN110738681A (en) automatic pedicle screw operation path planning method based on deep learning network
Barone et al. CT segmentation of dental shapes by anatomy‐driven reformation imaging and B‐spline modelling
CN110796670B (en) Dissection method and device for dissecting interbed artery
CN114757960B (en) Tooth segmentation and reconstruction method based on CBCT image and storage medium
US20130121548A1 (en) Adaptive visualization for direct physician use
CN113223010B (en) Method and system for multi-tissue full-automatic segmentation of oral cavity image
US20220084267A1 (en) Systems and Methods for Generating Quick-Glance Interactive Diagnostic Reports
CN112515787B (en) Three-dimensional dental data analysis method
CN112785609B (en) CBCT tooth segmentation method based on deep learning
CN111493918B (en) Automatic positioning method, application method and equipment for observation plane of lumbar vertebra CT image
CN102576465A (en) Method for digitizing dento-maxillofacial objects
CN112989954B (en) Three-dimensional tooth point cloud model data classification method and system based on deep learning
CN110610198A (en) Mask RCNN-based automatic oral CBCT image mandibular neural tube identification method
CN113628223A (en) Dental CBCT three-dimensional tooth segmentation method based on deep learning
CN116152500A (en) Full-automatic tooth CBCT image segmentation method based on deep learning
Bräuer et al. Virtual study of the endocranial morphology of the matrix‐filled cranium from Eliye Springs, Kenya
Ben-Hamadou et al. Teeth3ds: a benchmark for teeth segmentation and labeling from intra-oral 3d scans
CN112700447B (en) Automatic gum line extraction method based on digital tooth model
Moris et al. Automated tracking of the mandibular canal in CBCT images using matching and multiple hypotheses methods
KR20220069655A (en) Tooth segmentation system and method
CN117495801A (en) Implant planting parameter determining method based on image segmentation network
CN116823729A (en) Alveolar bone absorption judging method based on SegFormer and oral cavity curved surface broken sheet
CN112201349A (en) Orthodontic operation scheme generation system based on artificial intelligence
US20220358740A1 (en) System and Method for Alignment of Volumetric and Surface Scan Images

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination