Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yuan Zhang, Lei Liu, Jialin Zhang, Ya-Nan Zhang, Ling Wang, Nan Mu

TL;DR

BiM-GeoAttn-Net, a lightweight framework that integrates linear-time depth-wise state-space modeling with geometry-aware vessel refinement provides an effective, computationally efficient solution for robust 3D AD segmentation.

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.

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

TL;DR

BiM-GeoAttn-Net, a lightweight framework that integrates linear-time depth-wise state-space modeling with geometry-aware vessel refinement provides an effective, computationally efficient solution for robust 3D AD segmentation.

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.
Paper Structure (12 sections, 14 equations, 4 figures, 2 tables)

This paper contains 12 sections, 14 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Motivation and Overview
  4. Bidirectional Depth Mamba
  5. Geometry-Aware Vessel Attention
  6. Loss Function
  7. Experiments
  8. Dataset
  9. Implementation Details and Evaluation Metrics
  10. Comparison with State-of-the-Art Methods
  11. Ablation Study
  12. Conclusions

Figures (4)

  • Figure 1: Challenges in AD CTA segmentation. Four consecutive axial slices exhibit strong cross-slice continuity, subtle boundary contrast, and morphological variation. Ground-truth masks are in red.
  • Figure 2: Overall architecture of the proposed BiM-GeoAttn-Net.
  • Figure 3: Qualitative comparison on representative AD test cases. Yellow indicates correct overlap, blue denotes false positives, and red denotes false negatives. Compared with CNN-, Transformer-, and SSM-based baselines, BiM-GeoAttn-Net achieves sharper boundaries and improved depth-wise continuity.
  • Figure 4: Qualitative ablation comparison. Yellow indicates correct overlap, blue false positives, and red false negatives. The combined model yields the most consistent continuity and boundary delineation.