The Segment Anything Model (SAM), developed by Meta, demonstrates exceptional performance in medical image segmentation, particularly for lung CTs and chest X-rays, achieving an average Jaccard index of 91.45 % and an average Dice score of 94.95 % with minimal user intervention. Notably, SAM surpasses the recommended 70 % threshold in the literature and rivals state-of-the-art models designed explicitly for medical segmentation.
