Anatomy Aware Cascade Network: Bridging Epistemic Uncertainty and Geometric Manifold for 3D Tooth Segmentation

TL;DR

This paper introduces AACNet, a novel 3D tooth segmentation framework that effectively handles boundary ambiguity and maintains structural integrity, significantly improving accuracy and robustness in CBCT scans.

Contribution

The paper proposes AACNet with two innovative mechanisms, AGBR and SDMAA, to enhance boundary refinement and geometric consistency in 3D tooth segmentation.

Findings

Achieves 90.17% Dice coefficient on internal dataset

Attains 3.63 mm Hausdorff Distance, outperforming existing methods

Demonstrates strong generalization on external dataset

Abstract

Accurate three-dimensional (3D) tooth segmentation from Cone-Beam Computed Tomography (CBCT) is a prerequisite for digital dental workflows. However, achieving high-fidelity segmentation remains challenging due to adhesion artifacts in naturally occluded scans, which are caused by low contrast and indistinct inter-arch boundaries. To address these limitations, we propose the Anatomy Aware Cascade Network (AACNet), a coarse-to-fine framework designed to resolve boundary ambiguity while maintaining global structural consistency. Specifically, we introduce two mechanisms: the Ambiguity Gated Boundary Refiner (AGBR) and the Signed Distance Map guided Anatomical Attention (SDMAA). The AGBR employs an entropy based gating mechanism to perform targeted feature rectification in high uncertainty transition zones. Meanwhile, the SDMAA integrates implicit geometric constraints via signed distance map to enforce topological consistency, preventing the loss of spatial details associated with standard pooling. Experimental results on a dataset of 125 CBCT volumes demonstrate that AACNet achieves a Dice Similarity Coefficient of 90.17 \% and a 95\% Hausdorff Distance of 3.63 mm, significantly outperforming state-of-the-art methods. Furthermore, the model exhibits strong generalization on an external dataset with an HD95 of 2.19 mm, validating its reliability for downstream clinical applications such as surgical planning. Code for AACNet is available at https://github.com/shiliu0114/AACNet.