Uncertainty-Aware Deep Co-training for Semi-supervised Medical Image Segmentation

TL;DR

This paper introduces an uncertainty-aware semi-supervised learning method for medical image segmentation that leverages Monte Carlo sampling to focus training on uncertain regions, improving performance over existing methods.

Contribution

It proposes a novel uncertainty-aware scheme using Monte Carlo sampling to guide semi-supervised learning in medical image segmentation, enhancing model focus and convergence.

Findings

Achieved significant improvements on three medical datasets.

Outperformed state-of-the-art semi-supervised segmentation methods.

Demonstrated effective focus on uncertain regions improves accuracy.

Abstract

Semi-supervised learning has made significant strides in the medical domain since it alleviates the heavy burden of collecting abundant pixel-wise annotated data for semantic segmentation tasks. Existing semi-supervised approaches enhance the ability to extract features from unlabeled data with prior knowledge obtained from limited labeled data. However, due to the scarcity of labeled data, the features extracted by the models are limited in supervised learning, and the quality of predictions for unlabeled data also cannot be guaranteed. Both will impede consistency training. To this end, we proposed a novel uncertainty-aware scheme to make models learn regions purposefully. Specifically, we employ Monte Carlo Sampling as an estimation method to attain an uncertainty map, which can serve as a weight for losses to force the models to focus on the valuable region according to the characteristics of supervised learning and unsupervised learning. Simultaneously, in the backward process, we joint unsupervised and supervised losses to accelerate the convergence of the network via enhancing the gradient flow between different tasks. Quantitatively, we conduct extensive experiments on three challenging medical datasets. Experimental results show desirable improvements to state-of-the-art counterparts.