医学图像分割新模型，解决噪声多、遗忘快难题
SAMed-2: Selective Memory Enhanced Medical Segment Anything Model
- 引入时序适配器和置信度记忆机制，提升特征稳定性
- 在10个外部数据集上超越现有最佳模型，多任务表现优异
- 适合医疗图像分割研究者，尤其关注持续学习与跨模态应用
近期的“任意分割”方法通过大规模数据学习展现潜力，但直接应用于医学图像仍面临数据复杂、标注噪声及跨模态持续学习等挑战。本文提出SAMed-2，基于SAM-2架构构建医学图像分割基础模型。具体地，我们在图像编码器中引入时序适配器以捕捉图像相关性，并设计置信度驱动的记忆机制，存储高置信度特征以供后续检索。该记忆策略有效缓解大规模医学数据集中的普遍噪声问题，并减轻面对新任务或模态时的灾难性遗忘。为训练与评估SAMed-2，我们构建了MedBank-100k数据集，涵盖七种成像模态和21项医学分割任务。实验在内部基准及10个外部数据集上均显示其在多任务场景下优于当前最先进基线。代码已开源：https://github.com/ZhilingYan/Medical-SAM-Bench。
原文摘要 · Abstract (English)
Recent "segment anything" efforts show promise by learning from large-scale data, but adapting such models directly to medical images remains challenging due to the complexity of medical data, noisy annotations, and continual learning requirements across diverse modalities and anatomical structures. In this work, we propose SAMed-2, a new foundation model for medical image segmentation built upon the SAM-2 architecture. Specifically, we introduce a temporal adapter into the image encoder to capture image correlations and a confidence-driven memory mechanism to store high-certainty features for later retrieval. This memory-based strategy counters the pervasive noise in large-scale medical datasets and mitigates catastrophic forgetting when encountering new tasks or modalities. To train and evaluate SAMed-2, we curate MedBank-100k, a comprehensive dataset spanning seven imaging modalities and 21 medical segmentation tasks. Our experiments on both internal benchmarks and 10 external datasets demonstrate superior performance over state-of-the-art baselines in multi-task scenarios. The code is available at: https://github.com/ZhilingYan/Medical-SAM-Bench.
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。