DilatedToothSegNet: Tooth Segmentation Network on 3D Dental Meshes Through Increasing Receptive Vision
Journal of Imaging Informatics in Medicine · 05.03.2024 · 37 (4) · 1846-1862
DOI: 10.1007/s10278-024-01061-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 05.03.2024. Verfasst von Lucas Krenmayr und 4 weiteren Autor:innen. Beteiligte Einrichtung: Cooperative Doctoral Program for Data Science and Analytics, Ulm University and University of Applied Sciences, Ulm, 89075, Germany. lucas.krenmayr@u…. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Tooth, Deep Learning. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universität Ulm.
Abstract (Originalsprache)
The utilization of advanced intraoral scanners to acquire 3D dental models has gained significant popularity in the fields of dentistry and orthodontics. Accurate segmentation and labeling of teeth on digitized 3D dental surface models are crucial for computer-aided treatment planning. At the same time, manual labeling of these models is a time-consuming task. Recent advances in geometric deep learning have demonstrated remarkable efficiency in surface segmentation when applied to raw 3D models. However, segmentation of the dental surface remains challenging due to the atypical and diverse appearance of the patients’ teeth. Numerous deep learning methods have been proposed to automate dental surface segmentation. Nevertheless, they still show limitations, particularly in cases where teeth are missing or severely misaligned. To overcome these challenges, we introduce a network operator called dilated edge convolution, which enhances the network’s ability to learn additional, more distant features by expanding its receptive field. This leads to improved segmentation results, particularly in complex and challenging cases. To validate the effectiveness of our proposed method, we performed extensive evaluations on the recently published benchmark data set for dental model segmentation Teeth3DS. We compared our approach with several other state-of-the-art methods using a quantitative and qualitative analysis. Through these evaluations, we demonstrate the superiority of our proposed method, showcasing its ability to outperform existing approaches in dental surface segmentation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cooperative Doctoral Program for Data Science and Analytics, Ulm University and University of Applied Sciences, Ulm, 89075, Germany. lucas.krenmayr@uni-ulm.de.
- Department of Computer Science, University of Applied Sciences, Prittwitzstr. 10, Ulm, 89075, Germany. lucas.krenmayr@uni-ulm.de.
- Department of Computer Science, University of Applied Sciences, Prittwitzstr. 10, Ulm, 89075, Germany.
ORCID-Profile: Lucas Krenmayr
Förderung
- Universität Ulm
Zitieren
APA
Krenmayr, L., von Schwerin, R., Schaudt, D., Riedel, P., & Hafner, A. (2024). DilatedToothSegNet: Tooth Segmentation Network on 3D Dental Meshes Through Increasing Receptive Vision. Journal of Imaging Informatics in Medicine, 37(4), 1846-1862. https://doi.org/10.1007/s10278-024-01061-6
Vancouver
Krenmayr L, von Schwerin R, Schaudt D, Riedel P, Hafner A. DilatedToothSegNet: Tooth Segmentation Network on 3D Dental Meshes Through Increasing Receptive Vision. Journal of Imaging Informatics in Medicine. 2024;37(4):1846-1862. doi:10.1007/s10278-024-01061-6
BibTeX
@article{Krenmayr2024,
author = {Krenmayr, Lucas and von Schwerin, Reinhold and Schaudt, Daniel and Riedel, Pascal and Hafner, Alexander},
title = {DilatedToothSegNet: Tooth Segmentation Network on 3D Dental Meshes Through Increasing Receptive Vision},
journal = {Journal of Imaging Informatics in Medicine},
year = {2024},
volume = {37},
number = {4},
pages = {1846--1862},
doi = {10.1007/s10278-024-01061-6}
}
EUVIMED