Boundary-Aware Vision Transformer for Angiography Vascular Network Segmentation

2025/06/15 by Nabil Hezil, Hezil, Nabil, Suraj Singh +9
Medicine · #Retinal Imaging and Analysis #Cerebrovascular and Carotid Artery Diseases

paper · pdf · doi:10.48550/arxiv.2506.12980

Abstract

Accurate segmentation of vascular structures in coronary angiography remains a core challenge in medical image analysis due to the complexity of elongated, thin, and low-contrast vessels. Classical convolutional neural networks (CNNs) often fail to preserve topological continuity, while recent Vision Transformer (ViT)-based models, although strong in global context modeling, lack precise boundary awareness. In this work, we introduce BAVT, a Boundary-Aware Vision Transformer, a ViT-based architecture enhanced with an edge-aware loss that explicitly guides the segmentation toward fine-grained vascular boundaries. Unlike hybrid transformer-CNN models, BAVT retains a minimal, scalable structure that is fully compatible with large-scale vision foundation model (VFM) pretraining. We validate our approach on the DCA-1 coronary angiography dataset, where BAVT achieves superior performance across medical image segmentation metrics outperforming both CNN and hybrid baselines. These results demonstrate the effectiveness of combining plain ViT encoders with boundary-aware supervision for clinical-grade vascular segmentation.

Citations

• M⁴oE: A Foundation Model for Medical Multimodal Image Segmentation with Mixture of Experts
• How to Benchmark Vision Foundation Models for Semantic Segmentation?
• FS-Net: Full Scale Network and Adaptive Threshold for Improving Extraction of Micro-Retinal Vessel Structures
• DINOv2: Learning Robust Visual Features without Supervision
• EVA-02: A visual representation for neon genesis
• Medical Image Captioning via Generative Pretrained Transformers
• GIT: A Generative Image-to-text Transformer for Vision and Language
• Vision Transformer Adapter for Dense Predictions
• A ConvNet for the 2020s
• A ConvNet for the 2020s
• You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
• SegFormer: Simple and Efficient Design for Semantic Segmentation with\n Transformers
• Emerging Properties in Self-Supervised Vision Transformers
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• UNet++: A Nested U-Net Architecture for Medical Image Segmentation
• Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation
• Attention U-Net: Learning Where to Look for the Pancreas
• Attention Is All You Need
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Related

• Rethinking Boundary Detection in Deep Learning-Based Medical Image Segmentation
• Rethinking Boundary Detection in Deep Learning Models for Medical Image Segmentation
• Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion
• BEFD: Boundary Enhancement and Feature Denoising for Vessel Segmentation
• Deep 3D Vessel Segmentation based on Cross Transformer Network