Semi-supervised liver segmentation based on local regions self-supervision.
Journal:
Medical physics
Published Date:
Dec 18, 2023
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.