Scribble-Supervised Medical Image Segmentation with Dynamic Teacher Switching and Hierarchical Consistency
This work addresses the annotation burden in medical image segmentation for healthcare applications, representing an incremental improvement over existing scribble-supervised methods.
The paper tackles the problem of noisy pseudo-label propagation in scribble-supervised medical image segmentation by proposing SDT-Net, a dual-teacher, single-student framework with dynamic teacher switching and hierarchical consistency, achieving state-of-the-art performance on ACDC and MSCMRseg datasets.
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.