Figure - available from: BioMed Research International
This content is subject to copyright. Terms and conditions apply.
Assignment of constraint points on dental mesh for harmonic field computation. (a) Constraints assigned in our proposed method. (b) Resulting harmonic field with intersecting contour mesh points as constraints. (c) Resulting field without intersecting contour mesh points as constraints.
Source publication
An important preprocess in computer-aided orthodontics is to segment teeth from the dental models accurately, which should involve manual interactions as few as possible. But fully automatic partition of all teeth is not a trivial task, since teeth occur in different shapes and their arrangements vary substantially from one individual to another. T...
Similar publications
Orthodontists have seen their practices evolve from estimating distances on plaster models to estimating distances on non-immersive virtual models. However, if the estimation of distance using real models can generate errors (compared to the real distance measured using tools), which remains acceptable from a clinical point of view, is this also th...
Citations
... Especially in cases with many victims, manual removal of soft tissue from ante mortem dental scans would require a significant investment of human resources. A few studies have reported on automated soft tissue removal from 3D dental scans [15][16][17][18][19] . The methods of these studies aimed at determining the precise border between dentition and soft tissue but some of the methods suffer from poor performance on dentitions with missing teeth, malocclusion or dental scans not originating from plaster models 15,16 . ...
... A few studies have reported on automated soft tissue removal from 3D dental scans [15][16][17][18][19] . The methods of these studies aimed at determining the precise border between dentition and soft tissue but some of the methods suffer from poor performance on dentitions with missing teeth, malocclusion or dental scans not originating from plaster models 15,16 . The use of supervised deep learning for tooth segmentation has also been emerging 15,[17][18][19] . ...
... The aim of the present study was to develop a new robust method for automated soft tissue removal from dental scans that works with scans from both living and deceased humans with or without missing teeth and malocclusion. Unlike earlier methods focusing on defining the dentition/soft tissue border 15,16 , our method aims at limiting the amount of soft tissue in dental scans. Our study mimics real-life disaster victim identification scenarios since the goal is to automate data cleaning to support future automated forensic odontology identification. ...
The potential of intraoral 3D photo scans in forensic odontology identification remains largely unexplored, even though the high degree of detail could allow automated comparison of ante mortem and post mortem dentitions. Differences in soft tissue conditions between ante- and post mortem intraoral 3D photo scans may cause ambiguous variation, burdening the potential automation of the matching process and underlining the need for limiting inclusion of soft tissue in dental comparison. The soft tissue removal must be able to handle dental arches with missing teeth, and intraoral 3D photo scans not originating from plaster models. To address these challenges, we have developed the grid-cutting method. The method is customisable, allowing fine-grained analysis using a small grid size and adaptation of how much of the soft tissues are excluded from the cropped dental scan. When tested on 66 dental scans, the grid-cutting method was able to limit the amount of soft tissue without removing any teeth in 63/66 dental scans. The remaining 3 dental scans had partly erupted third molars (wisdom teeth) which were removed by the grid-cutting method. Overall, the grid-cutting method represents an important step towards automating the matching process in forensic odontology identification using intraoral 3D photo scans.
... The capability of deep learning for automatic feature extraction in medical imaging leads to the creation of robust, quantifiable models with strong adaptability and generalizability, significantly aiding doctors in formulating precise and effective medical plans [17][18][19]. The advent of automatic tooth segmentation technologies [20], leveraging and computer vision techniques, has the potential to autonomously identify and segment dental structures [21,22]. Current approaches predominantly utilize U-shaped convolutional neural network architectures, with methods like Faster R-CNN [23] and Mask R-CNN [24] being widely applied in tooth segmentation and caries detection [25,26]. ...
In this paper, we introduce a novel deep learning method for dental panoramic image segmentation, which is crucial in oral medicine and orthodontics for accurate diagnosis and treatment planning. Traditional methods often fail to effectively combine global and local context, and struggle with unlabeled data, limiting performance in varied clinical settings. We address these issues with an advanced TransUNet architecture, enhancing feature retention and utilization by connecting the input and output layers directly. Our architecture further employs spatial and channel attention mechanisms in the decoder segments for targeted region focus, and deep supervision techniques to overcome the vanishing gradient problem for more efficient training. Additionally, our network includes a self-learning algorithm using unlabeled data, boosting generalization capabilities. Named the Semi-supervised Tooth Segmentation Transformer U-Net (STS-TransUNet), our method demonstrated superior performance on the MICCAI STS-2D dataset, proving its effectiveness and robustness in tooth segmentation tasks.
... Contour line-based methods involve manual selection of tooth boundary landmarks, followed by contour line generation based on geodesic information, as demonstrated in studies such as Sinthanayothin et al. and Yaqi et al. [31,42]. Harmonic field methods require less user interaction, as they allow a limited number of surface points to be selected prior to the segmentation process, as seen in studies by Zou et al. [54] and Liao et al. [18]. ...
... Although the previous works of this paper [4], [5] have demonstrated superior performance compared to methods of the same period, the way of solving the Laplace harmonic field with manually specified constraints has become its main bottleneck, especially in the current season that most of the successful methods rely on deep learning to extract pattern features from big data. Unlike regular data such as digital images, the structure of mesh is far more complex, and traditional convolution cannot be directly applied. ...
Dental triangular mesh is widely used in computer-aided oral medicine. Different from regular data such as digital images, the structure of triangular mesh is more complex, and traditional operations such as convolution cannot be directly applied. Therefore, the segmentation of patients’ personalized teeth from mesh through deep learning is a hot topic in the current research field. Recently, a method named TSGCN presented the idea of learning coordinate features and normal features through a two-stream architecture based on Graph Convolutional Networks (GCN), which further improved the performance compared with other methods. However, its ability to extract and process global features still can be strengthened. To this end, a method named TSGCN-SA is proposed, whose core idea is to introduce the self-attention (SA) mechanism into TSGCN. Specifically, two SA modules are introduced, the first one is used to improve the global feature extraction ability in the coordinate stream. The second one plays an important role in the adaptive contribution adjustment of each stream during the feature fusion. Experiments based on the public dataset named 3DTeethSeg show that TSGCN-SA is superior to SOTAs in terms of segmentation performance due to the proposed SA modules, and the proposed method is competent in the task of individual tooth mesh segmentation.
... We can also mention the harmonic-field method which is more user-friendly for teeth segmentation than the previous approaches. In comparison to previous techniques, this method requires less user interaction by allowing them to select a limited number of surface points prior to the segmentation process Liao et al., 2015). ...
Teeth localization, segmentation, and labeling from intra-oral 3D scans are essential tasks in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health. However, developing automated algorithms for teeth analysis presents significant challenges due to variations in dental anatomy, imaging protocols, and limited availability of publicly accessible data. To address these challenges, the 3DTeethSeg'22 challenge was organized in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2022, with a call for algorithms tackling teeth localization, segmentation, and labeling from intraoral 3D scans. A dataset comprising a total of 1800 scans from 900 patients was prepared, and each tooth was individually annotated by a human-machine hybrid algorithm. A total of 6 algorithms were evaluated on this dataset. In this study, we present the evaluation results of the 3DTeethSeg'22 challenge. The 3DTeethSeg'22 challenge code can be accessed at: https://github.com/abenhamadou/3DTeethSeg22_challenge
... The user indicates points of correction and the boundary is redefined by the shortest geodesical path. [6] applied an harmonic field weight to each Laplacian value to improve the boundary extraction. ...
The teeth segmentation plays a key role in the orthodontics analysis, but, due to their irregularity, it is a complex task. Irregular surfaces segmentation is still an open issue. Whereas some state-of-art algorithms are either very time consuming or not very precise, the region growth algorithm performs well in both aspects. In this project, the region growth algorithm was adapted to reduce noise and improve the performance with a pre-processing step. In this step, the curvature was analysed in order to obtain the boundaries and apply the region growth. Two method were developed: a manual algorithm and an automatic application. The manual algorithm was capable of segmenting all teeth correctly in the experiments. However, the automatic variant did not achieve the same results. Moreover, some holes must be removed in order to perform simulation on the results.
... Researchers have developed and implemented wide range of image processing techniques to segment and classify teeth in dental X-ray images. These studies include teeth segmentation based on harmonic fields [1,2], adaptive thresholding [3,4], local singularity analysis [5], level-set method [6] and mathematical morphology [7], while feature extraction from teeth based on textures [6], radius vector function [8], multiple criteria [9], contents [10], roots [11], force field energy function and Fourier descriptor [12]. Finally, teeth classification based on Bayesian techniques [12], vertical projection profile [11], linear models [13], orthogonal locality preserving projection (OLPP) [14] and binary support vector machines [15]. ...
... Recall-precision graphs precision (AP), precision and recall are calculated using the equations as follows(2) ...
Computer aided diagnosis in dental treatment is highly desirable as it brings efficiency and accuracy in dental treatment. In this paper, an automatic teeth recognition method is proposed involving faster R-CNN method. The proposed method is implemented using a pre-trained ResNet-50 to automatically recognize tooth by its number. This paper follows the universal tooth numbering system to number the teeth. Obtained result is evaluated using mean average precision (mAP). The system achieved 0.942 mAP and thus can be considered as a reliable tool to aid dental care system professionals in automatic recognition of tooth.
... However, in real life, the teeth anatomy may be different from patient to patient due to the chewing habit, teeth grinding, or developmental variations. There are also studies that developed an interactive tooth partition method based on harmonic field and prior knowledge of teeth landmarks [17,18]. However, braces will also change the shape and features of the teeth. ...
PurposeOne critical step in routine orthognathic surgery is to reestablish a desired final dental occlusion. Traditionally, the final occlusion is established by hand articulating stone dental models. To date, there are still no effective solutions to establish the final occlusion in computer-aided surgical simulation. In this study, we consider the most common one-piece maxillary orthognathic surgery and propose a three-stage approach to digitally and automatically establish the desired final dental occlusion.Methods
The process includes three stages: (1) extraction of points of interest and teeth landmarks from a pair of upper and lower dental models; (2) establishment of Midline-Canine-Molar (M-C-M) relationship following the clinical criteria on these three regions; and (3) fine alignment of upper and lower teeth with maximum contacts without breaking the established M-C-M relationship. Our method has been quantitatively and qualitatively validated using 18 pairs of dental models.ResultsQualitatively, experienced orthodontists assess the algorithm-articulated and hand-articulated occlusions while being blind to the methods used. They agreed that occlusion results of the two methods are equally good. Quantitatively, we measure and compare the distances between selected landmarks on upper and lower teeth for both algorithm-articulated and hand-articulated occlusions. The results showed that there was no statistically significant difference between the algorithm-articulated and hand-articulated occlusions.Conclusion
The proposed three-stage automatic dental articulation method is able to articulate the digital dental model to the clinically desired final occlusion accurately and efficiently. It allows doctors to completely eliminate the use of stone dental models in the future.
... ere are some specific approaches [3][4][5][6][7] that fully exploit the dental characteristics. ese methods are either interaction-intensive or resultinaccurate. ...
... In the main loop, the distance between two adjacent vertices-based anisotropic metric is calculated. e (2) source Q, Q is a priority queue ordered by dist; (3) while not Q empty do (4) υ Q; (5) υ.final = true; (6) for w adjancen υ and w.final ≠ true do (7) if w.dist > υ.dist + l g (υ, w) then (8) w.dist = υ.dist + l g (υ, w); (9) w.pred = υ; (10) if not w in Q then (11) w Q; ...
... e tracking back time is slightly longer than that of Zhuang's method, but a few milliseconds of tracking time does not affect the real-time interaction. So (4) for m = 1 : s do (5) initialize pts as a point array; (6) foreach pt i 2D in C 2D do (7) (8) update C 2D using temp_pt; ...
Teeth segmentation is a crucial technologic component of the digital dentistry system. The limitations of the live-wire segmentation include two aspects: (1) computing the wire as the segmentation boundary is time-consuming and (2) a great deal of interactions for dental mesh is inevitable. For overcoming these disadvantages, 3D intelligent scissors for dental mesh segmentation based on live-wire is presented. Two tensor-based anisotropic metrics for making wire lie at valleys and ridges are defined, and a timesaving anisotropic Dijkstra is adopted. Besides, to improve with the smoothness of the path tracking back by the traditional Dijkstra, a 3D midpoint smoothing algorithm is proposed. Experiments show that the method is effective for dental mesh segmentation and the proposed tool outperforms in time complexity and interactivity.
... This meth gives a better accuracy.95.63% for the upper jaw separation and 98.71% accuracy for Lower jaw separation. In [5], Enny Itje Sela et al. suggested a method named as Segmentation on the Dental Periapical X Osteoporosis Screening.The training results were found accuracy rate to be 99,96%and the testing results were found to around 65%. Liao et al. [6], proposed the dental segmentation using Harmonic Field based approach. The author uses 60 laser scanned Dental mesh models. ...
Dental biometrics is another authentication technique where the dental features are used from dental images for identify a person. Segmentation of teeth from dental radiograph images is a crucial step for achieving automated forensic identification. Segmentation of teeth helps a dentist to diagnose the teeth problems and understand the structure of the teeth. The dental segmentation work we discuss in the paper is based on Otsu's thresholding and connected component analysis. Initially we input a radiograph image of teeth. Preprocessing is done using the smoothening filter to remove the noise or the corrupted pixels in the dental image. We perform dental segmentation in periapical dental images. We preprocess the image for noise removal and enhancement is done using CLAHE. Finally, Segmentation is done by Otsu's thresholding and the connected component are identified to extract the ROI of the teeth is segmented.
