Tooth automatic segmentation from CBCT images: a systematic review

Polizzi, Alessandro; Quinzi, Vincenzo; Venezia, Pietro; Santonocito, Simona; Ronsivalle, Vincenzo; Leonardi, Rosalia; Isola, Gaetano

doi:10.1007/s00784-023-05048-5

Cited by 24 publications

(7 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, it is worth mentioning that recent technology has made possible a more realistic view of the anatomical structures of interest to surgeons, especially using 3D image acquisition and image segmentation. Researchers have highlighted benefits that cover the correct identification of the third molar position [35], as well as studying dental lesions such as root resorption [36].…”

Section: Discussionmentioning

confidence: 99%

Panoramic Radiography vs. CBCT in the Evaluation of the Maxillary Third Molar Roots

Almeida-Marques,

Ingold,

da Silva-Junior

et al. 2023

Medicina

View full text Add to dashboard Cite

Background and Objectives: A comprehensive understanding of the position of third molar roots and adjacent structures, such as the maxillary sinus (MS), is essential for safe extractions. Diagnostic imaging plays a fundamental role in achieving accurate treatment planning. This study aimed to compare panoramic radiography (PR) and cone-beam computed tomography (CBCT) for the evaluation of maxillary third molar roots and their relationship with the MS. Materials and Methods: Two trained radiologists evaluated third molar images. The number of roots, morphology (fused/conical, divergent, dilacerated, or atypical), and their relationship with the MS in PR and CBCT were registered. Descriptive and inferential statistics were performed using the weighted Kappa test. Results: Regarding the number and morphology of the roots, Kappa values showed moderate (κ = 0.42) and fair agreement (κ = 0.38), respectively. Regarding the proximity with the MS, most of the roots showed close contact (30.6%), or 1/3 of root superimposition (35%), in PR evaluation, while in CBCT, the third molars were in contact with the MS floor (32%), and with alveolar domes (27.2%). Conclusions: PR is a moderately reliable image technique to identify the number of roots and root morphology of maxillary third molars. PR, however, does not provide any radiographic signs that clearly indicate the anatomical relationship between the maxillary third molar roots and the maxillary sinus detected in CBCT images.

show abstract

Section: Discussionmentioning

confidence: 99%

Panoramic Radiography vs. CBCT in the Evaluation of the Maxillary Third Molar Roots

Almeida-Marques,

Ingold,

da Silva-Junior

et al. 2023

Medicina

View full text Add to dashboard Cite

show abstract

“…Fully automated tooth segmentation is currently a challenging problem that suffers from the following difficulties: (1) The teeth are tightly connected to each other and arranged in a complex structure. (2) It is difficult to separate the teeth from their surrounding alveolar bone due to the highly similar densities. This paper focuses on segmenting complete 3D models of teeth from CBCT images, it can assist dentists in clinical diagnosis and treatment planning, including orthodontic planning; In addition, in forensic science, inferring the age of an individual by analyzing the development and state of the teeth is an important task, and segmenting the teeth models will help to improve the accuracy and efficiency of age identification.…”

Section: Introductionmentioning

confidence: 99%

A comparison of U-Net series for teeth segmentation in CBCT images

Zhang,

Zheng,

Lin

et al. 2024

Medical Imaging 2024: Image Processing

View full text Add to dashboard Cite

Accurately segmenting complete teeth from CBCT images is not only crucial in the field of orthodontics but also holds significant importance in forensic science. However, fully automated teeth segmentation is challenging due to the tight interconnection of teeth and the complexity of their arrangement, as well as the difficulty in distinguishing them from the surrounding alveolar bone due to similar densities. Currently, U-Net-based approaches have demonstrated remarkable success across a spectrum of medical image processing tasks, particularly in the task of segmentation. This work compares some U-Net-based segmentation methods (U-Net, U-Net++, U 2 -Net, nnU-Net, and TransUNet) on clinical teeth segmentation. We assess the enhancements introduced by these networks over the original U-Net and validate their performance on the identical dataset. Experimental results, both qualitative and quantitative, reveal that all methods perform well, with TransUNet demonstrating the best performance, achieving a Dice coefficient of 0.9364. Notably, U-Net, serving as the foundational model, outperforms U-Net++ and U 2 -Net, highlighting its robust generalization capability.

show abstract

“…Despite those promising results, a recent systematic review on automatic tooth segmentation approaches from CBCT scans revealed that most of the studies were at high risk of bias regarding data selection, leading to a potential overestimation of the accuracy of the methods (Polizzi et al 2023). Most of the published studies reported results from cross-validation approaches or small-sized hold-out test dataset (less than 50 CBCT scans), which could be insufficient to evaluate the robustness and generalizability of the methods in actual clinical settings (Schwendicke et al 2021).…”

Section: Introductionmentioning

confidence: 99%

DentalSegmentator: robust deep learning-based CBCT image segmentation

Dot,

Chaurasia,

Dubois

et al. 2024

Preprint

View full text Add to dashboard Cite

Delineation of anatomical structures on dento-maxillo-facial (DMF) computed tomography (CT) or cone beam computed tomography (CBCT) scans is greatly needed for an increasing number of digital dentistry tasks. Following this process, called segmentation, three-dimensional (3D) patient-specific models can be exported for visualization, treatment planning, intervention, and follow-up purposes. Although several methods based on deep learning (DL) have been proposed for automating this task, there is no thoroughly evaluated publicly available tool offering segmentation of the anatomical structures needed for digital dentistry workflows. In this work, we propose and evaluate DentalSegmentator, a tool based on the nnU-Net deep learning framework, for fully automatic segmentation of 5 anatomic structures on DMF CT and CBCT scans: maxilla and upper skull, mandible, upper teeth, lower teeth and mandibular canal. A retrospective sample of 470 CT and CBCT scans was used as a training/validation set. The performance and generalizability of the tool was evaluated by comparing segmentations provided by experts and automatic segmentations on 2 hold-out test datasets: an internal dataset of 133 CT and CBCT scans acquired before orthognathic surgery and an external dataset of 123 CBCT scans randomly sampled from routine examinations in 5 institutions. In our internal test dataset (n = 133), the mean overall results were a Dice similarity coefficient (DSC) of 92.2 ± 6.3% and a normalized surface distance (NSD) of 98.2 ± 2.2%. In our external test dataset (n = 123), the mean overall results were a DSC of 94.2 ± 7.4% and a NSD of 98.4 ± 3.6%. The results obtained on this highly diversified dataset demonstrate that our tool can provide fully automatic and robust multiclass segmentation for DMF (CB)CT scans. To encourage the clinical deployment of DentalSegmentator, our pretrained nnU-Net model is made publicly available along with an extension for the 3D Slicer software.

show abstract

Tooth automatic segmentation from CBCT images: a systematic review

Cited by 24 publications

References 48 publications

Panoramic Radiography vs. CBCT in the Evaluation of the Maxillary Third Molar Roots

Panoramic Radiography vs. CBCT in the Evaluation of the Maxillary Third Molar Roots

A comparison of U-Net series for teeth segmentation in CBCT images

DentalSegmentator: robust deep learning-based CBCT image segmentation

Contact Info

Product

Resources

About