Scribble-supervised methods have emerged to mitigate the prohibitive annotation burden in medical image segmentation. However, the inherent sparsity of these annotations introduces significant ambiguity, which results in noisy pseudo-label propagation and hinders the learning of robust anatomical boundaries. To address this challenge, we propose SDT-Net, a novel dual-teacher, single-student framework designed to maximize supervision quality from these weak signals. Our method features a Dynamic Teacher Switching (DTS) module to adaptively select the most reliable teacher. This selected teacher then guides the student via two synergistic mechanisms: high-confidence pseudo-labels, refined by a Pick Reliable Pixels (PRP) mechanism, and multi-level feature alignment, enforced by a Hierarchical Consistency (HiCo) module. Extensive experiments on the ACDC and MSCMRseg datasets demonstrate that SDT-Net achieves state-of-the-art performance, producing more accurate and anatomically plausible segmentation.
@article{arxiv.2601.14563,
title = {Scribble-Supervised Medical Image Segmentation with Dynamic Teacher Switching and Hierarchical Consistency},
author = {Thanh-Huy Nguyen and Hoang-Loc Cao and Dat T. Chung and Mai-Anh Vu and Thanh-Minh Nguyen and Minh Le and Phat K. Huynh and Ulas Bagci},
journal= {arXiv preprint arXiv:2601.14563},
year = {2026}
}