用U-Net和SAM互训，零标注下实现医疗图像分割新突破
From Specialist to Generalist: Unlocking SAM's Learning Potential on Unlabeled Medical Images
- U-Net生成提示点与伪标签，引导SAM适应医学图像
- 双向协作使模型在无标签数据上表现超越现有方法
- 适合关注少样本医疗分割的研究者与开发者
像分割一切模型（SAM）这样的基础模型虽具强泛化能力，但将其应用于医学图像仍受领域差异、标注稀缺及参数高效微调（PEFT）无法利用未标注数据的限制。传统模型如U-Net在半监督医学学习中表现优异，但其辅助PEFT-SAM的潜力尚未被发掘。本文提出SC-SAM框架：U-Net提供基于点的提示与伪标签以引导SAM适应，而SAM则作为强大通用监督者正则化U-Net。二者形成双向协同训练循环，有效利用未标注数据。在前列腺MRI与肠息肉分割基准测试中，该方法达到当前最优性能，优于其他半监督SAM变体甚至医学基础模型MedSAM，凸显了专家-通用模型协作在标签高效医学图像分割中的价值。代码已开源。
原文摘要 · Abstract (English)
Foundation models like the Segment Anything Model (SAM) show strong generalization, yet adapting them to medical images remains difficult due to domain shift, scarce labels, and the inability of Parameter-Efficient Fine-Tuning (PEFT) to exploit unlabeled data. While conventional models like U-Net excel in semi-supervised medical learning, their potential to assist a PEFT SAM has been largely overlooked. We introduce SC-SAM, a specialist-generalist framework where U-Net provides point-based prompts and pseudo-labels to guide SAM's adaptation, while SAM serves as a powerful generalist supervisor to regularize U-Net. This reciprocal guidance forms a bidirectional co-training loop that allows both models to effectively exploit the unlabeled data. Across prostate MRI and polyp segmentation benchmarks, our method achieves state-of-the-art results, outperforming other existing semi-supervised SAM variants and even medical foundation models like MedSAM, highlighting the value of specialist-generalist cooperation for label-efficient medical image segmentation. Our code is available at https://github.com/vnlvi2k3/SC-SAM.
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。