Adaptation of Segment Anything Model enhanced by contrastive-manifold-regularised SSL and YOLO prompting for liver tumour segmentation.
MED-SAM is presented, a 2D semi-supervised framework employing the medical SAM adapter (Med-SA), trained with contrastive manifold regularisation and YOLO-guided click prompts, indicating that MED-SAM can support treatment-planning workflows in hepatobiliary surgery while addressing the challenges of scarce annotations...