Uncertainty-aware consistency learning for semi-supervised medical image segmentation

Min Dong, Ating Yang, Zhenhang Wang, Dezhen Li, Jing Yang, Rongchang Zhao

Abstract: Highlights•Multi-perturbations are used to fully explore the structural information of organs.•The UAC is proposed to address the noise sensitivity in semi-supervised learning.•Voxel-wise contrastive learning is used to enhance the class separability of feature.