DArch: Dental Arch Prior-assisted 3D Tooth Instance Segmentation

TL;DR

DArch introduces a low-cost annotation approach for 3D tooth segmentation using dental arch priors, combining Bezier curve regression, GCN refinement, and patch-based segmentation to outperform existing methods.

Contribution

The paper presents a novel weakly supervised 3D tooth segmentation method leveraging dental arch priors, reducing annotation costs and improving accuracy.

Findings

Achieved superior segmentation accuracy over state-of-the-art methods.

Effectively utilized weak annotations for precise tooth instance segmentation.

Demonstrated robustness on a large dataset of 4,773 dental models.

Abstract

Automatic tooth instance segmentation on 3D dental models is a fundamental task for computer-aided orthodontic treatments. Existing learning-based methods rely heavily on expensive point-wise annotations. To alleviate this problem, we are the first to explore a low-cost annotation way for 3D tooth instance segmentation, i.e., labeling all tooth centroids and only a few teeth for each dental model. Regarding the challenge when only weak annotation is provided, we present a dental arch prior-assisted 3D tooth segmentation method, namely DArch. Our DArch consists of two stages, including tooth centroid detection and tooth instance segmentation. Accurately detecting the tooth centroids can help locate the individual tooth, thus benefiting the segmentation. Thus, our DArch proposes to leverage the dental arch prior to assist the detection. Specifically, we firstly propose a coarse-to-fine method to estimate the dental arch, in which the dental arch is initially generated by Bezier curve regression, and then a graph-based convolutional network (GCN) is trained to refine it. With the estimated dental arch, we then propose a novel Arch-aware Point Sampling (APS) method to assist the tooth centroid proposal generation. Meantime, a segmentor is independently trained using a patch-based training strategy, aiming to segment a tooth instance from a 3D patch centered at the tooth centroid. Experimental results on $4,773$ dental models have shown our DArch can accurately segment each tooth of a dental model, and its performance is superior to the state-of-the-art methods.