动态选择辅助数据提升医学影像分割的少样本适应能力
Adapting Foundation Models for Few-Shot Medical Image Segmentation: Actively and Sequentially
- 将少样本域适应建模为多臂老虎机问题，智能筛选最匹配目标任务的辅助数据
- 在MRI和CT数据上分别提升27.75%和7.52%的Dice分数，显著优于现有方法
- 适合资源有限、标注少但需高精度分割的医疗图像分析场景
基础模型在计算机视觉领域取得进展，尤其在医学图像分割中表现优异。然而，在目标任务存在大领域差异且标注样本极少的情况下，如何可靠地适应基础模型仍是挑战。以往的少样本域适应（FSDA）方法依赖辅助数据弥合源域与目标域分布差异，但辅助数据的选择与调度多基于启发式规则，易引发负向迁移。本文提出一种主动且序列化的域自适应框架（ASAP），通过将FSDA建模为多臂老虎机问题，设计高效奖励函数，仅通过单轮微调即可优先选择与目标任务高度对齐的辅助数据集。在多个医学分割数据集上的实验证明，该方法性能优越，相较于现有最佳方法，在MRI数据集上平均提升27.75%的Dice分数，在CT数据集上提升7.52%。代码已开源。
原文摘要 · Abstract (English)
Recent advances in foundation models have brought promising results in computer vision, including medical image segmentation. Fine-tuning foundation models on specific low-resource medical tasks has become a standard practice. However, ensuring reliable and robust model adaptation when the target task has a large domain gap and few annotated samples remains a challenge. Previous few-shot domain adaptation (FSDA) methods seek to bridge the distribution gap between source and target domains by utilizing auxiliary data. The selection and scheduling of auxiliaries are often based on heuristics, which can easily cause negative transfer. In this work, we propose an Active and Sequential domain AdaPtation (ASAP) framework for dynamic auxiliary dataset selection in FSDA. We formulate FSDA as a multi-armed bandit problem and derive an efficient reward function to prioritize training on auxiliary datasets that align closely with the target task, through a single-round fine-tuning. Empirical validation on diverse medical segmentation datasets demonstrates that our method achieves favorable segmentation performance, significantly outperforming the state-of-the-art FSDA methods, achieving an average gain of 27.75% on MRI and 7.52% on CT datasets in Dice score. Code is available at the git repository: https://github.com/techicoco/ASAP.
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。