SegMix:Shuffle-based Feedback Learning for Semantic Segmentation of Pathology Images

2026-04-17

AI Summary

This work addresses the challenge of weakly supervised semantic segmentation in histopathology images, where pixel-level annotations are costly and image-level labels often yield incomplete or low-quality pseudo-masks. To overcome this limitation, the authors propose a novel weakly supervised learning framework that integrates adaptive patch-level shuffling with a feedback mechanism. Specifically, image patches are dynamically shuffled according to a curriculum learning strategy, and the shuffling intensity is adaptively adjusted based on model feedback to refine the quality of pseudo-labels derived from Class Activation Maps. This approach represents the first effort to incorporate adaptive shuffling and feedback-driven learning into weakly supervised histopathology segmentation, achieving state-of-the-art performance across three public datasets.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Segmentation is a critical task in computational pathology, as it identifies areas affected by disease or abnormal growth and is essential for diagnosis and treatment. However, acquiring high-quality pixel-level supervised segmentation data requires significant workload demands from experienced pathologists, limiting the application of deep learning. To overcome this challenge, relaxing the label conditions to image-level classification labels allows for more data to be used and more scenarios to be enabled. One approach is to leverage Class Activation Map (CAM) to generate pseudo pixel-level annotations for semantic segmentation with only image-level labels. However, this method fails to thoroughly explore the essential characteristics of pathology images, thus identifying only small areas that are insufficient for pseudo masking. In this paper, we propose a novel shuffle-based feedback learning method inspired by curriculum learning to generate higher-quality pseudo-semantic segmentation masks. Specifically, we perform patch level shuffle of pathology images, with the model adaptively adjusting the shuffle strategy based on feedback from previous learning. Experimental results demonstrate that our proposed approach outperforms state-of-the-arts on three different datasets.

Problem

• semantic segmentation
• computational pathology
• weakly supervised learning
• pseudo-labeling
• image-level labels

Innovation

• shuffle-based learning
• feedback learning
• pseudo-label generation
• semantic segmentation
• computational pathology