发表机构
Duke University; Carnegie Mellon University; University of Pittsburgh Medical Center（杜克大学; 卡内基梅隆大学; 匹兹堡大学医学中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ConPro自监督预训练方法，利用DSA序列中造影剂流动的对比投影作为目标，在低标注比例下提升血管分割性能，并可与半监督方法结合获得显著增益。
AI 中文摘要
在数字减影血管造影（DSA）中对血管进行密集标注是劳动密集型的，然而每个未标注序列都记录了造影剂如何流经血管。半监督方法从当前模型获取目标，而通用的自监督预训练任务重建静态外观，因此这一信号未被利用。我们提出ConPro，一种自监督预训练方案，其目标是对比投影，即序列中每个像素相对于其时间中位数的归一化下降量。在DIAS和DSCA数据集上，当10%、20%和50%的训练病例被标注时，ConPro在每个标注比例下均优于从零开始训练，并且在DSCA上以20%和50%的标注比例成为比较方法中的最优。受控比较表明，增益来自目标本身。使用相同输入、损失和预算的时间中位数目标保持在从零开始的水平，而直接使用投影而非学习它，作为输入通道或伪标签，帮助甚微甚至有害。ConPro在不改变分割架构的情况下提供预训练权重，因此可与半监督训练结合，最强的基线UniMatch在从ConPro权重初始化后，在每个标注比例下获得0.5至2.0的Dice和0.9至2.3的clDice提升，在DIAS上达到75.4的Dice，在DSCA上达到81.3。
英文摘要
Dense vessel annotation in digital subtraction angiography (DSA) is labor-intensive, yet every unlabeled sequence records how contrast passes through the vessels. Semi-supervised methods take their targets from the current model, and generic self-supervised pretexts reconstruct static appearance, so this signal goes unused. We propose ConPro, a self-supervised pretraining scheme whose target is a contrast projection, the normalized drop of every pixel below its temporal median over the sequence. On DIAS and DSCA, with 10%, 20% and 50% of the training cases labeled, ConPro improves on training from scratch at every label fraction and is the best of the compared methods on DSCA at 20% and 50% labels. Controlled comparisons show that the gain comes from the target. A temporal-median target with the same input, loss and budget stays at scratch level, and using the projection directly instead of learning it, as an input channel or a pseudo-label, helps little or hurts. ConPro provides pretrained weights without changing the segmentation architecture, so it combines with semi-supervised training, and UniMatch, the strongest baseline, gains 0.5 to 2.0 Dice and 0.9 to 2.3 clDice at every label fraction when started from ConPro weights, reaching 75.4 Dice on DIAS and 81.3 on DSCA.
Comments5 pages, 4 figures, 2 tables. Submitted to IEEE ICASSP 2027
