Weakly Supervised Teacher-Student Framework with Progressive Pseudo-mask Refinement for Gland Segmentation

2026-03-09

AI Summary

This work addresses the challenge of gland segmentation in colorectal cancer histopathology, which typically relies on extensive pixel-level annotations. To alleviate this dependency, the authors propose a weakly supervised teacher-student collaborative framework that achieves high-quality gland segmentation using only sparse annotations. The method integrates an exponentially moving average-stabilized teacher network, confidence-based filtering, adaptive fusion of ground-truth and pseudo-labels, and a curriculum learning–guided progressive refinement strategy for pseudo-masks, collectively enhancing supervision for non-discriminative glandular structures. Evaluated on the Gland Segmentation dataset, the approach attains an mIoU of 80.10 and a Dice score of 89.10, while demonstrating strong generalization performance in cross-cohort assessments on TCGA COAD/READ.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Background and objectives: Colorectal cancer histopathological grading depends on accurate segmentation of glandular structures. Current deep learning approaches rely on large scale pixel level annotations that are labor intensive and difficult to obtain in routine clinical practice. Weakly supervised semantic segmentation offers a promising alternative. However, class activation map based methods often produce incomplete pseudo masks that emphasize highly discriminative regions and fail to supervise unannotated glandular structures. We propose a weakly supervised teacher student framework that leverages sparse pathologist annotations and an Exponential Moving Average stabilized teacher network to generate refined pseudo masks. Methods: The framework integrates confidence based filtering, adaptive fusion of teacher predictions with limited ground truth, and curriculum guided refinement to progressively segment unannotated glandular regions. The method was evaluated on an institutional colorectal cancer cohort from The Ohio State University Wexner Medical Center consisting of 60 hematoxylin and eosin stained whole slide images and on public datasets including the Gland Segmentation dataset, TCGA COAD, TCGA READ, and SPIDER. Results: On the Gland Segmentation dataset the framework achieved a mean Intersection over Union of 80.10 and a mean Dice coefficient of 89.10. Cross cohort evaluation demonstrated robust generalization on TCGA COAD and TCGA READ without additional annotations, while reduced performance on SPIDER reflected domain shift. Conclusions: The proposed framework provides an annotation efficient and generalizable approach for gland segmentation in colorectal histopathology.

Problem

• gland segmentation
• weakly supervised learning
• pseudo-mask refinement
• histopathology
• colorectal cancer

Innovation

• weakly supervised learning
• teacher-student framework
• pseudo-mask refinement
• gland segmentation
• exponential moving average