无需训练，用自适应提示实现跨域医学图像精准分割
MAUP: Training-free Multi-center Adaptive Uncertainty-aware Prompting for Cross-domain Few-shot Medical Image Segmentation
- 基于K-means生成多中心提示，覆盖更全面的解剖区域
- 根据不确定性筛选难分区域提示，提升关键区域分割精度
- 动态调整提示策略，适配不同复杂度的目标区域
跨域少样本医学图像分割（CD-FSMIS）有望利用其他领域的知识，在标注有限的情况下完成医学图像分割。现有模型依赖大量源域医学数据的训练，限制了通用性和部署便捷性。随着自然图像大视觉模型的发展，我们提出一种无需训练的CD-FSMIS方法，通过多中心自适应不确定性提示（MAUP）策略，将仅在自然图像上预训练的Segment Anything Model（SAM）适配至医学分割任务。MAUP包含三项创新：（1）基于K-means聚类生成多中心提示，实现空间全覆盖；（2）依据不确定性选择挑战性区域的提示；（3）根据目标区域复杂度动态优化提示。结合预训练的DINOv2特征编码器，该方法在三个医学数据集上无需额外训练即达到领先性能，优于多个传统及无训练的少样本分割模型。
原文摘要 · Abstract (English)
Cross-domain Few-shot Medical Image Segmentation (CD-FSMIS) is a potential solution for segmenting medical images with limited annotation using knowledge from other domains. The significant performance of current CD-FSMIS models relies on the heavily training procedure over other source medical domains, which degrades the universality and ease of model deployment. With the development of large visual models of natural images, we propose a training-free CD-FSMIS model that introduces the Multi-center Adaptive Uncertainty-aware Prompting (MAUP) strategy for adapting the foundation model Segment Anything Model (SAM), which is trained with natural images, into the CD-FSMIS task. To be specific, MAUP consists of three key innovations: (1) K-means clustering based multi-center prompts generation for comprehensive spatial coverage, (2) uncertainty-aware prompts selection that focuses on the challenging regions, and (3) adaptive prompt optimization that can dynamically adjust according to the target region complexity. With the pre-trained DINOv2 feature encoder, MAUP achieves precise segmentation results across three medical datasets without any additional training compared with several conventional CD-FSMIS models and training-free FSMIS model. The source code is available at: https://github.com/YazhouZhu19/MAUP.
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。