Search papers, labs, and topics across Lattice.
This paper introduces FAME, a comprehensive benchmark designed to evaluate few-shot medical image segmentation (FS-MIS) solutions across various paradigms, including specialist, SAM-based, CLIP-based, and MLLM-based methods. The evaluation, which encompasses 14,958 test samples from diverse anatomical sites and imaging modalities, reveals that direct visual adaptation outperforms prompt-based strategies, and that the effectiveness of additional support examples is contingent on the models' ability to utilize them effectively. Notably, the study highlights the challenges of semantic transfer compared to imaging-domain adaptation, emphasizing that strong localization does not guarantee reliable recognition of absent targets.
Direct visual adaptation in few-shot medical image segmentation outperforms prompt-based strategies, revealing critical insights into model performance.
Few-shot medical image segmentation (FS-MIS) aims to segment novel regions of interest (ROIs) from a few annotated support examples. Despite rapid progress, existing FS-MIS solutions span diverse paradigms but are evaluated under inconsistent settings, leaving their relative effectiveness unclear. We introduce FAME, a unified benchmark for evaluating FS-MIS solutions, covering specialists, SAM-based methods, CLIP-based methods, and MLLM-based methods. FAME contains 14,958 test samples across 7 anatomical sites, 9 imaging modalities, and 14 ROI categories, and evaluates models under zero-shot and ten-shot settings with additional assessment of target-absence recognition and generalization under covariate and semantic shifts. Our evaluation reveals several findings. First, effective few-shot segmentation depends on how models exploit support examples: direct visual adaptation generally outperforms prompt-based strategies. Second, increasing support examples improves performance only when models can effectively utilize them. Third, semantic transfer remains substantially more challenging than imaging-domain adaptation, and strong localization ability does not necessarily imply reliable target-absence recognition. We hope FAME provides a comprehensive understanding of current FS-MIS solutions and facilitates the development of more effective and reliable few-shot medical segmentation methods.
