Efficient Fine-Tuning of SAM for Interactive Medical Image Multi-Organ Segmentation

• Published in: Proceedings (International Symposium on Biomedical Imaging) pp. 01 - 05
• Main Authors: Wang, Mengxin, Liao, Linglin, Jiang, Na, Geng, Qichuan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14.04.2025
• Subjects: Biological systems; Biomedical imaging; Costs; Data models; Data pruning; Fine-tuning of SAM; Hands; Human factors; Image segmentation; Interactive medical image segmentation; Synapses; Testing; Training

Recently, Segment Anything Model (SAM) has significantly advanced interactive segmentation techniques, particularly its fine-tuned variants in medical imaging. Although previous approaches can adapt SAM to diverse downstream tasks with additional data, two challenges persist. On the one hand, organ...