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

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.

Entropy‐guided contrastive learning for semi‐supervised medical image segmentation

“…For instance, Rizve et al [47] proposed a unified thresholding approach that combines probability and uncertainty thresholds to select low-entropy regions for SSL. Furthermore, Zheng et al [38] employed Monte Carlo Sampling as an estimation method to obtain lowentropy and high-entropy maps. By emphasizing the valuable regions (i.e.…”

“…To validate the overall segmentation performance of the proposed method, we conduct experiments and compared the results with those obtained using state-of-the-art SSL methods. These methods included Mean Teacher (MT) [33], EM [45], Deep Adversarial Network (DAN) [31], Deep Co-Training (DCT) [38], Cross Pseudo Supervision (CPS) [46], Cross Teaching between CNN and Transformer (CTCT) [43], and Uncertainty Rectified Pyramid Consistency (URPC) [21]. For a fair comparison, all methods used the same backbone and training setting.…”