仅用一张标注图实现高效视网膜血管分割，媲美全监督模型。
ESRVS: Extreme Semi-Supervised Retinal Vessel Segmentation with a Single Annotated Image
- 用DINOv3特征选参考图，跨域传递血管线索。
- 多粒度原型+物理先验生成初始伪标签，提升准确性。
- 适合标注资源极稀缺的医疗图像分割任务。
在医学图像分析中，密集专家标注成本高昂，如何在极少人工监督下学习是长期目标。本文研究仅需一张标注图像和大量未标注图像的极端半监督视网膜血管分割问题。提出ESRVS方法：选择代表性参考图进行标注，利用面向目标域的DINOv3特征传递血管线索；构建多粒度血管原型，结合原型相似性图与物理启发先验生成初始伪标签；通过加权伪标签训练与对抗性精炼优化转移监督。在八个公开数据集上，ESRVS在六项指标中优于对比的半监督方法（后者使用10%-20%标注数据），且全部八组数据上达到最优HD95。使用Mask2Former时，其平均保留了全监督模型93.7%的Dice与95.1%的clDice。结果表明，基于基础模型的标签传播在高度标签效率的视网膜血管分割中具有巨大潜力。代码已开源：https://github.com/IAANNH/ESRVS。
原文摘要 · Abstract (English)
Learning from minimal human supervision is a long-standing goal in medical image analysis, where dense expert annotations are costly. We study retinal vessel segmentation in an extreme semi-supervised setting with one annotated image and a pool of unlabeled images. We propose ESRVS, which selects a representative reference image for manual annotation and transfers vessel cues using target-domain-adapted DINOv3 features. ESRVS constructs a multi granular vessel prototype, combines prototype-similarity maps with a physics-inspired prior to generate initial pseudo-labels, and refines the transferred supervision through weighted pseudo-label training and adversarial refinement. Across eight public datasets, ESRVS achieves the best Dice and clDice on six datasets, and the best HD95 on all eight datasets among the compared semi-supervised methods, although those methods use 10 to 20% labeled data. With Mask2Former, ESRVS retains on average 93.7% of fully supervised Dice and 95.1% of fully supervised clDice. These results demonstrate the potential of foundation-model label propagation for highly label-efficient retinal vessel segmentation. Code is available at https://github.com/IAANNH/ESRVS.
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。