DCS-ST for Classification of Breast Cancer Histopathology Images with Limited Annotations

2025-05-06

AI Summary

Medical image annotation is costly, and deep learning models suffer severe performance degradation under few-shot settings. To address this, we propose the Dual-Cooperative Self-Training (DCS-ST) framework, which innovatively integrates inter-teacher model consistency constraints with a region-level dynamic pseudo-label selection mechanism. Our method combines self-supervised pretraining, multi-teacher collaborative knowledge distillation, weak-strong data augmentation, and confidence-adaptive threshold adjustment. Evaluated on the Camelyon16/17 benchmarks, DCS-ST achieves 98.2% classification accuracy using only 5% labeled data—outperforming the current state-of-the-art by 3.7 percentage points. This demonstrates significantly improved few-shot generalization capability. The framework provides an efficient and reliable solution for low-resource computational pathology analysis, particularly where labeled data are scarce.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Deep learning methods have shown promise in classifying breast cancer histopathology images, but their performance often declines with limited annotated data, a critical challenge in medical imaging due to the high cost and expertise required for annotations.

Problem

• Classify breast cancer histopathology images with limited annotations
• Address performance decline in deep learning with scarce labeled data
• Overcome high annotation costs and expertise requirements in medical imaging

Innovation

• DCS-ST for limited annotation classification
• Deep learning with scarce labeled data
• Medical image analysis cost reduction