Semi-supervised liver segmentation based on local regions self-supervision.

Journal: Medical physics
Published Date:

Abstract

BACKGROUND: Semi-supervised learning has gained popularity in medical image segmentation due to its ability to reduce reliance on image annotation. A typical approach in semi-supervised learning is to select reliable predictions as pseudo-labels and eliminate unreliable predictions. Contrastive learning helps prevent the insufficient utilization of unreliable predictions, but neglecting the anatomical structure of medical images can lead to suboptimal optimization results.

Authors

  • Qiong Lou
    School of Science, Zhejiang University of Science and Technology, Hangzhou 310012, China.
  • Tingyi Lin
    School of Science, Zhejiang University of Science and Technology, Hangzhou, China.
  • Yaguan Qian
    School of Science, Zhejiang University of Science and Technology, Hangzhou 310012, China.
  • Fang Lu
    School of Mathematical Sciences, Zhejiang University, Hangzhou, 310027, China.