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

2026-01-12

AI Summary

This work proposes AACNet, a coarse-to-fine cascaded network designed to address the challenges of low contrast and blurred boundaries in cone-beam computed tomography (CBCT) images caused by natural dental occlusion. The method innovatively integrates an entropy-driven Ambiguity Gated Boundary Refiner (AGBR) with a signed distance map–guided anatomical attention module (SDMAA), introducing uncertainty-aware refinement and implicit geometric constraints within a cascaded architecture to jointly preserve global structural consistency and achieve precise local boundary delineation. Evaluated on 125 CBCT scans, the model achieves a Dice coefficient of 90.17% and a Hausdorff distance at the 95th percentile (HD95) of 3.63 mm; notably, on an external cohort, HD95 further improves to 2.19 mm, significantly outperforming existing approaches.

Technology Category

• Computer Vision: Segmentation
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Responsible Web: Measurement, analysis, and circumvention of Web censorship
• Search and Retrieval-Augmented AI: Agentic search

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.

Problem

• 3D tooth segmentation
• CBCT
• boundary ambiguity
• adhesion artifacts
• geometric manifold

Innovation

• Anatomy Aware Cascade Network
• Ambiguity Gated Boundary Refiner
• Signed Distance Map
• 3D Tooth Segmentation
• Epistemic Uncertainty