A Dual-Headed Teacher–Student Framework with an Uncertainty-Guided Mechanism for Semi-Supervised Skin Lesion Segmentation

Medical image segmentation is a challenging task due to limited annotated data, complex lesion boundaries, and the inherent variability in medical images. These challenges make accurate and robust segmentation crucial for clinical applications. In this study, we propose the Uncertainty-Driven Auxiliary Mean Teacher (UDAMT) model, a novel semi-supervised framework specifically designed for skin lesion segmentation. Our approach employs a dual-headed teacher–student architecture with an uncertainty-guided mechanism, enhancing feature learning and boundary precision. Extensive experiments on the ISIC 2016, ISIC 2017, and ISIC 2018 datasets demonstrate that UDAMT achieves significant improvements over state-of-the-art methods, with increases of 1.17 percentage points in the Dice coefficient and 1.31 percentage points in mean Intersection over Union (mIoU) under low-label settings (5% labeled data). Furthermore, UDAMT requires 12.9 M parameters, which is slightly higher than the baseline model (12.5 M) but significantly lower than MT (14.8 M) and UAMT (15.2 M). It also achieves an inference time of 25.7 ms per image, ensuring computational efficiency. Ablation studies validate the contributions of each component, and cross-dataset evaluations on the PH2 benchmark confirm robustness to small lesions. This work provides a scalable and efficient solution for semi-supervised medical image segmentation, balancing accuracy, efficiency, and clinical applicability.