CTooth+: A Large-scale Dental Cone Beam Computed Tomography Dataset and Benchmark for Tooth Volume Segmentation

TL;DR

This paper introduces CTooth+, a large-scale annotated dental CBCT dataset, and evaluates various segmentation methods, establishing a benchmark for future AI-driven dental imaging research and clinical applications.

Contribution

It provides a new extensive dataset and benchmark for tooth volume segmentation, enabling reproducibility and evaluation of deep learning methods in dental imaging.

Findings

State-of-the-art segmentation strategies evaluated

Benchmark established for future research

Baseline results provided for semi-supervised and active learning methods

Abstract

Accurate tooth volume segmentation is a prerequisite for computer-aided dental analysis. Deep learning-based tooth segmentation methods have achieved satisfying performances but require a large quantity of tooth data with ground truth. The dental data publicly available is limited meaning the existing methods can not be reproduced, evaluated and applied in clinical practice. In this paper, we establish a 3D dental CBCT dataset CTooth+, with 22 fully annotated volumes and 146 unlabeled volumes. We further evaluate several state-of-the-art tooth volume segmentation strategies based on fully-supervised learning, semi-supervised learning and active learning, and define the performance principles. This work provides a new benchmark for the tooth volume segmentation task, and the experiment can serve as the baseline for future AI-based dental imaging research and clinical application development.