用于增强左前降动脉三维分割的邻域注意力Transformer网络

中文摘要 AI 辅助

背景：在三维自由呼吸非对比CT中准确分割左前降动脉（LAD）对于胸部放疗中心脏的剂量 sparing 至关重要。LAD 极其细小、软组织对比度差且患者间差异极大；即使是人工轮廓也显示出有限的观察者间一致性，凸显了血管边界的模糊性。目的：开发一种基于Transformer的框架，通过局部-全局上下文建模和不确定性引导优化，提升低对比度、不平衡CT中LAD的勾画效果。方法：我们提出NA-UNETR，一种基于三维Transformer的分割模型，其邻域注意力（NA）和扩张邻域注意力（DiNA）模块共同捕捉精细结构细节和长程上下文。鉴于标注的LAD数据稀缺，该模型在1000例通用冠状动脉解剖的CTA volume上进行预训练，并在20例机构自由呼吸CT扫描上通过基于LoRA的参数高效适应进行微调。通过同方差不确定性动态平衡的组合Dice-Focal和Hausdorff损失，提升重叠度和边界精度。结果：NA-UNETR取得了45.64%的Dice、38.16 mm的HD95和10.01 mm的ASD，相比nnU-Net提升了3.10个百分点的Dice，相比Swin UNETR降低了2.96 mm的HD95，在所有模型中具有最强的边界精度和改进的中心线稳定性。在ImageCAS上，它取得了79.49%的Dice、8.89 mm的HD95和1.02 mm的ASD。 ablation 实验证实，残差模块、可变卷积核和不确定性加权损失各有贡献。结论：NA-UNETR为细小、低对比度的LAD结构平衡了局部精度和全局上下文，为放疗规划中的亚结构级心脏分割提供了计算高效的框架。

英文摘要

Background: Accurate segmentation of the Left Anterior Descending (LAD) artery in 3D free-breathing, non-contrast CT is critical for cardiac dose sparing in thoracic radiotherapy. The LAD is extremely small, has poor soft-tissue contrast, and varies substantially across patients; even manual contours show limited inter-observer agreement, underscoring the ambiguity of the vessel boundaries. Purpose: To develop a transformer-based framework that improves LAD delineation in low-contrast, imbalanced CT through local-global context modeling and uncertainty-guided optimization. Methods: We propose NA-UNETR, a 3D transformer-based segmentation model whose Neighborhood Attention (NA) and Dilated NA (DiNA) blocks jointly capture fine structural detail and long-range context. Given the scarcity of annotated LAD data, the model is pretrained on 1,000 CTA volumes of general coronary anatomy and fine-tuned with LoRA-based parameter-efficient adaptation on 20 free-breathing institutional CT scans. A composite Dice-Focal and Hausdorff loss, dynamically balanced via homoscedastic uncertainty, improves overlap and boundary accuracy. Results: NA-UNETR reached 45.64% Dice, 38.16 mm HD95, and 10.01 mm ASD, improving Dice by 3.10 percentage points over nnU-Net and reducing HD95 by 2.96 mm relative to Swin UNETR, with the strongest boundary accuracy among all models and improved centerline stability. On ImageCAS it achieved 79.49% Dice, 8.89 mm HD95, and 1.02 mm ASD. Ablations confirmed that residual blocks, variable kernels, and uncertainty-weighted loss each contributed. Conclusions: NA-UNETR balances local precision and global context for thin, low-contrast LAD structures, offering a computationally efficient framework for substructure-level cardiac segmentation in radiotherapy planning.

发表机构

• Wayne State University（韦恩州立大学）
• Henry Ford Health（亨利福特医疗集团）
• Alexandria University（亚历山大大学）
• Michigan State University（密歇根州立大学）
• Oakland University（奥克兰大学）
• Institute for AI and Data Science, Wayne State University（韦恩州立大学人工智能与数据科学学院）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

Acceteed by Medical Physics 2026