Towards a Comprehensive, Efficient and Promptable Anatomic Structure Segmentation Model using 3D Whole-body CT Scans

arXiv:2403.15063v1 Announce Type: new
Abstract: Segment anything model (SAM) demonstrates strong generalization ability on natural image segmentation. However, its direct adaption in medical image segmentation tasks shows significant performance drops with inferior accuracy and unstable results. It may also requires an excessive number of prompt points to obtain a reasonable accuracy. For segmenting 3D radiological CT or MRI scans, a 2D SAM model has to separately handle hundreds of 2D slices. Although quite a few studies explore adapting SAM into …

abstract accuracy arxiv cs.cv however image medical natural performance prompt results sam scans segment segment anything segment anything model segmentation shows tasks type