CTooth+: A Large-scale Dental Cone Beam Computed Tomography Dataset and Benchmark for Tooth Volume Segmentation
This work addresses a critical data bottleneck for researchers and clinicians in dental imaging, enabling reproducible and applicable AI-based methods, though it is incremental as it builds on existing segmentation techniques.
The authors tackled the lack of publicly available dental data for tooth volume segmentation by creating CTooth+, a large-scale 3D CBCT dataset with 22 fully annotated and 146 unlabeled volumes, and established a benchmark by evaluating state-of-the-art segmentation methods to serve as a baseline for future research and clinical applications.
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.