MaskSAM: Towards Auto-prompt SAM with Mask Classification for Medical Image Segmentation

arXiv:2403.14103v1 Announce Type: new
Abstract: Segment Anything Model~(SAM), a prompt-driven foundation model for natural image segmentation, has demonstrated impressive zero-shot performance. However, SAM does not work when directly applied to medical image segmentation tasks, since SAM lacks the functionality to predict semantic labels for predicted masks and needs to provide extra prompts, such as points or boxes, to segment target regions. Meanwhile, there is a huge gap between 2D natural images and 3D medical images, so the performance of SAM …

abstract arxiv auto classification cs.cv foundation foundation model however image labels masks medical natural performance prompt sam segment segment anything segment anything model segmentation semantic tasks type work zero-shot