Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation
This addresses the need for extensive labeled data in medical imaging by improving segmentation accuracy for histopathology, though it is an incremental advance combining existing techniques.
The paper tackles the problem of noisy pseudo-labels in semi-supervised histopathology image segmentation by introducing Semi-MoE, a multi-task Mixture-of-Experts framework, which outperforms state-of-the-art methods on GlaS and CRAG benchmarks in low-label settings.
Semi-supervised learning has been employed to alleviate the need for extensive labeled data for histopathology image segmentation, but existing methods struggle with noisy pseudo-labels due to ambiguous gland boundaries and morphological misclassification. This paper introduces Semi-MOE, to the best of our knowledge, the first multi-task Mixture-of-Experts framework for semi-supervised histopathology image segmentation. Our approach leverages three specialized expert networks: A main segmentation expert, a signed distance field regression expert, and a boundary prediction expert, each dedicated to capturing distinct morphological features. Subsequently, the Multi-Gating Pseudo-labeling module dynamically aggregates expert features, enabling a robust fuse-and-refine pseudo-labeling mechanism. Furthermore, to eliminate manual tuning while dynamically balancing multiple learning objectives, we propose an Adaptive Multi-Objective Loss. Extensive experiments on GlaS and CRAG benchmarks show that our method outperforms state-of-the-art approaches in low-label settings, highlighting the potential of MoE-based architectures in advancing semi-supervised segmentation. Our code is available at https://github.com/vnlvi2k3/Semi-MoE.