用边界感知损失提升ViT对血管细线的分割精度。
Boundary-Aware Vision Transformer for Angiography Vascular Network Segmentation
- 在ViT中引入边缘感知损失，显式优化血管边界
- 在DCA-1数据集上超越CNN与混合模型，达最优指标
- 结构简洁可扩展，适合大规模视觉预训练
冠状动脉造影中血管结构的精确分割仍是医学图像分析的核心挑战，因血管呈细长、低对比度且形态复杂。传统卷积神经网络（CNN）常无法保持拓扑连续性，而近期基于视觉变换器（ViT）的模型虽具备全局建模能力，却缺乏精细边界感知。本文提出BAVT——一种边界感知视觉变换器，通过引入边缘感知损失，显式引导分割结果贴合细微血管边界。与混合型变压器-CNN模型不同，BAVT保持极简可扩展架构，完全兼容大规模视觉基础模型（VFM）预训练。我们在DCA-1冠状动脉造影数据集上验证该方法，结果显示，BAVT在各项医学图像分割指标上均优于CNN及混合基线模型，证明了纯ViT编码器结合边界感知监督在临床级血管分割中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。