A segment anything model-guided and match-based semi-supervised segmentation framework for medical imaging.
Journal:
Medical physics
Published Date:
Mar 29, 2025
Abstract
BACKGROUND: Semi-supervised segmentation leverages sparse annotation information to learn rich representations from combined labeled and label-less data for segmentation tasks. The Match-based framework, by using the consistency constraint of segmentation results from different models/augmented label-less inputs, is found effective in semi-supervised learning. This approach, however, is challenged by the low quality of pseudo-labels generated as intermediate products for training the network, due to the lack of the ''ground-truth'' reference.
