Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation

arXiv:2403.05912v1 Announce Type: cross
Abstract: Tumor lesion segmentation on CT or MRI images plays a critical role in cancer diagnosis and treatment planning. Considering the inherent differences in tumor lesion segmentation data across various medical imaging modalities and equipment, integrating medical knowledge into the Segment Anything Model (SAM) presents promising capability due to its versatility and generalization potential. Recent studies have attempted to enhance SAM with medical expertise by pre-training on large-scale medical segmentation datasets. However, challenges still exist in …

abstract arxiv cancer cancer diagnosis capability cs.cv data diagnosis differences eess.iv equipment images imaging knowledge medical medical imaging mri planning role sam segment segment anything segment anything model segmentation semantic treatment type