用SAM提升医学图像分割伪标签质量，少样本下效果更优
A SAM-guided and Match-based Semi-Supervised Segmentation Framework for Medical Imaging
- 借助预训练SAM生成高置信度提示，优化伪标签
- 在心脏、乳腺、肝脏数据集上分别达89.36%、77.76%、80.04%的Dice分数
- 适合标注数据稀缺的医学图像分割任务
本文提出SAMatch，一种基于SAM引导的匹配式半监督医学图像分割框架，旨在改善数据稀缺场景下的伪标签质量。尽管匹配类方法有效，但缺乏真实标签时伪标签质量较差。SAM在大规模数据上预训练，具备强泛化能力，可生成高置信度提示，用于微调后进一步优化伪标签。SAMatch采用端到端训练，实现模型间动态交互。在ACDC心脏MRI、BUSI乳腺超声和MRLiver数据集上的实验表明，仅使用极少标注数据即取得领先性能，对应Dice分数分别为89.36%、77.76%和80.04%。该方法有效缓解了半监督分割中的挑战，为数据受限环境下的分割提供了有力工具。代码与数据已公开于https://github.com/apple1986/SAMatch。
原文摘要 · Abstract (English)
This study introduces SAMatch, a SAM-guided Match-based framework for semi-supervised medical image segmentation, aimed at improving pseudo label quality in data-scarce scenarios. While Match-based frameworks are effective, they struggle with low-quality pseudo labels due to the absence of ground truth. SAM, pre-trained on a large dataset, generalizes well across diverse tasks and assists in generating high-confidence prompts, which are then used to refine pseudo labels via fine-tuned SAM. SAMatch is trained end-to-end, allowing for dynamic interaction between the models. Experiments on the ACDC cardiac MRI, BUSI breast ultrasound, and MRLiver datasets show SAMatch achieving state-of-the-art results, with Dice scores of 89.36%, 77.76%, and 80.04%, respectively, using minimal labeled data. SAMatch effectively addresses challenges in semi-supervised segmentation, offering a powerful tool for segmentation in data-limited environments. Code and data are available at https://github.com/apple1986/SAMatch.
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。