Concatenate, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation

arXiv:2403.11229v1 Announce Type: new
Abstract: Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in this work, we leverage the capabilities of SAM for establishing semi-supervised medical image segmentation models. Rethinking the requirements of effectiveness, efficiency, and compatibility, we propose a three-stage framework, i.e., Concatenate, Fine-tuning, and Re-training (CFR). The current fine-tuning approaches mostly involve 2D slice-wise fine-tuning …

abstract annotation annotations arxiv capabilities cost cs.cv fine-tuning framework image medical performance reduce sam segment segment anything segment anything model segmentation semi-supervised training type work