Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a quality-guided semi-supervised learning (SSL) framework that enhances medical image segmentation by estimating segmentation quality from image-mask pairs. By training a dedicated network on variable-quality masks and integrating it into SSL through quality-aware regularization and pseudolabel reweighting, the method addresses the limitations of traditional SSL approaches that rely on self-referential confidence measures. Extensive experiments across five datasets show that this approach consistently outperforms existing SSL methods, advancing the state-of-the-art in the field.
Quality-guided SSL can significantly boost the performance of medical image segmentation models by leveraging a dedicated quality predictor, leading to state-of-the-art results across multiple datasets.
Training accurate medical image segmentation models requires large amounts of densely annotated data, which is costly and time-consuming to obtain. Semi-supervised learning (SSL) alleviates this by learning from both abundant unlabeled data and limited labeled data. However, most modern SSL methods rely on pseudolabels for unlabeled data, and typically assess their reliability through model confidence or uncertainty, measures that are self-referential and lack explicit grounding in segmentation quality. Instead, we propose a quality-guided SSL framework that trains a dedicated network to estimate segmentation quality from image-mask pairs. The predictor is trained on variable-quality masks generated through synthetic corruptions augmented with imperfect outputs from partially trained segmentation models, capturing realistic error patterns encountered during training. We integrate the quality predictor into SSL through two complementary mechanisms: a quality-aware regularization loss and a quality-based pseudolabel sample reweighting scheme. We show that our method serves as a drop-in enhancement to existing SSL frameworks. Extensive experiments across five datasets and multiple architectures demonstrate consistent improvements over competing SSL methods, advancing the state-of-the-art in semi-supervised medical image segmentation.