BiM-GeoAttn-Net: Linear-Time Depth Modeling with Geometry-Aware Attention for 3D Aortic Dissection CTA Segmentation

TL;DR

This paper introduces BiM-GeoAttn-Net, a lightweight, geometry-aware deep learning framework that efficiently models depth and refines vessel structures for accurate 3D aortic dissection segmentation in CTA images.

Contribution

It presents a novel combination of linear-time depth-wise state-space modeling with geometry-aware vessel attention for improved 3D segmentation accuracy.

Findings

Achieves a Dice score of 93.35% on AD CTA dataset.

Outperforms CNN, Transformer, and SSM baselines in overlap metrics.

Maintains competitive boundary accuracy.

Abstract

Accurate segmentation of aortic dissection (AD) lumens in CT angiography (CTA) is essential for quantitative morphological assessment and clinical decision-making. However, reliable 3D delineation remains challenging due to limited long-range context modeling, which compromises inter-slice coherence, and insufficient structural discrimination under low-contrast conditions. To address these limitations, we propose BiM-GeoAttn-Net, a lightweight framework that integrates linear-time depth-wise state-space modeling with geometry-aware vessel refinement. Our approach is featured by Bidirectional Depth Mamba (BiM) to efficiently capture cross-slice dependencies and Geometry-Aware Vessel Attention (GeoAttn) module that employs orientation-sensitive anisotropic filtering to refine tubular structures and sharpen ambiguous boundaries. Extensive experiments on a multi-source AD CTA dataset demonstrate that BiM-GeoAttn-Net achieves a Dice score of 93.35% and an HD95 of 12.36 mm, outperforming representative CNN-, Transformer-, and SSM-based baselines in overlap metrics while maintaining competitive boundary accuracy. These results suggest that coupling linear-time depth modeling with geometry-aware refinement provides an effective, computationally efficient solution for robust 3D AD segmentation.