发表机构
University of California, Merced（加州大学默塞德分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出UI-VISA混合分割架构，结合U-Net与区域生长算法优势，在26幅DSA图像的5折交叉验证中，其clDice提升具统计学显著性，可更精准分割血管结构。
AI 中文摘要
数字减影血管造影（DSA）图像中血管结构的精准分割仍具挑战，因血管纤细、细长且分支众多。U-Net等逐像素深度学习方法具备出色的通用分割性能，但因未显式强制结构连通性，常于精细血管区域产生碎片化或不连续的预测结果。区域生长算法可保留空间上下文与拓扑连续性，但对种子点初始化高度敏感，且计算成本高昂。本文提出UI-VISA（U-Net初始化血管图像分割架构），一种结合两种方法互补优势的混合流程：UI-VISA将U-Net的前景预测作为经信息引导的种子点，输入由CNN引导的区域生长算法，该算法通过强制局部连通性迭代优化分割结果，修复仅用U-Net易遗漏或过度预测的精细血管细节。我们在26幅DSA图像上采用5折交叉验证，将UI-VISA与单独的U-Net及现有基于区域生长的方法VISA对比评估。UI-VISA在各折中均取得最高的平均Dice分数与clDice分数；配对Wilcoxon符号秩检验显示，clDice的提升具有统计学显著性（p=0.023），与该方法保留血管连通性的设计目标一致，而Dice的提升未达显著性（p=0.104）。
英文摘要
Accurate segmentation of vascular structures in digital subtraction angiography (DSA) images remains challenging due to the thin, elongated, and branching nature of blood vessels. Pixel-wise deep learning approaches such as U-Net achieve strong general-purpose segmentation performance but often produce fragmented or discontinuous predictions in fine vascular regions, since they do not explicitly enforce structural connectivity. Region growing algorithms preserve spatial context and topological continuity, but are highly sensitive to seed point initialization and can be computationally expensive. We propose UI-VISA (U-Net Initialized Vascular Image Segmentation Architecture), a hybrid pipeline that combines the complementary strengths of both approaches. UI-VISA uses U-Net's foreground predictions as informed seed points for a CNN-guided region growing algorithm, which then iteratively refines the segmentation by enforcing local connectivity and recovering fine vessel details that U-Net alone tends to miss or over-predict. We evaluate UI-VISA against standalone U-Net and a prior region-growing-based method (VISA) using 5-fold cross-validation on 26 DSA images. UI-VISA achieves the highest mean Dice and clDice scores across folds, and a paired Wilcoxon signed-rank test shows the improvement in clDice is statistically significant ($p=0.023$), consistent with the method's design goal of preserving vascular connectivity, while the improvement in Dice does not reach significance ($p=0.104$).
Comments9 pages, 6 figures
