Uncertainty-Aware Adapter: Adapting Segment Anything Model (SAM) for Ambiguous Medical Image Segmentation

arXiv:2403.10931v1 Announce Type: cross
Abstract: The Segment Anything Model (SAM) gained significant success in natural image segmentation, and many methods have tried to fine-tune it to medical image segmentation. An efficient way to do so is by using Adapters, specialized modules that learn just a few parameters to tailor SAM specifically for medical images. However, unlike natural images, many tissues and lesions in medical images have blurry boundaries and may be ambiguous. Previous efforts to adapt SAM ignore this challenge …

abstract adapter arxiv cs.cv eess.iv image learn medical modules natural parameters sam segment segment anything segment anything model segmentation success type uncertainty