Robust Teeth Detection in 3D Dental Scans by Automated Multi-view Landmarking

Tibor Kubík, Michal Španěl, Michal Španěl

2022

Abstract

Landmark detection is frequently an intermediate step in medical data analysis. More and more often, these data are represented in the form of 3D models. An example is a 3D intraoral scan of dentition used in orthodontics, where landmarking is notably challenging due to malocclusion, teeth shift, and frequent teeth missing. What’s more, in terms of 3D data, the DNN processing comes with high memory and computational time requirements, which do not meet the needs of clinical applications. We present a robust method for tooth landmark detection based on a multi-view approach, which transforms the task into a 2D domain, where the suggested network detects landmarks by heatmap regression from several viewpoints. Additionally, we propose a post-processing based on Multi-view Confidence and Maximum Heatmap Activation Confidence, which can robustly determine whether a tooth is missing or not. Experiments have shown that the combination of Attention U-Net, 100 viewpoints, and RANSAC consensus method is able to detect landmarks with an error of 0:75  0:96 mm. In addition to the promising accuracy, our method is robust to missing teeth, as it can correctly detect the presence of teeth in 97.68% cases.

Download


Paper Citation


in Harvard Style

Kubík T. and Španěl M. (2022). Robust Teeth Detection in 3D Dental Scans by Automated Multi-view Landmarking. In Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING, ISBN 978-989-758-552-4, pages 24-34. DOI: 10.5220/0010770700003123


in Bibtex Style

@conference{bioimaging22,
author={Tibor Kubík and Michal Španěl},
title={Robust Teeth Detection in 3D Dental Scans by Automated Multi-view Landmarking},
booktitle={Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING,},
year={2022},
pages={24-34},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010770700003123},
isbn={978-989-758-552-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING,
TI - Robust Teeth Detection in 3D Dental Scans by Automated Multi-view Landmarking
SN - 978-989-758-552-4
AU - Kubík T.
AU - Španěl M.
PY - 2022
SP - 24
EP - 34
DO - 10.5220/0010770700003123