Histo-MExNet: A Unified Framework for Real-World, Cross-Magnification, and Trustworthy Breast Cancer Histopathology

TL;DR

Histo-MExNet is a comprehensive framework that enhances breast cancer histopathology classification by achieving scale invariance, interpretability, and uncertainty quantification, improving robustness across magnifications.

Contribution

It introduces a novel unified model combining multiple backbones, prototype learning, and physics-informed regularization for reliable, interpretable, and scale-invariant histopathological image classification.

Findings

Achieves 96.97% accuracy on BreaKHis dataset.

Improves generalization to unseen magnifications.

Effectively identifies out-of-distribution samples.

Abstract

Accurate and reliable histopathological image classification is essential for breast cancer diagnosis. However, many deep learning models remain sensitive to magnification variability and lack interpretability. To address these challenges, we propose Histo-MExNet, a unified framework designed for scaleinvariant and uncertainty-aware classification. The model integrates DenseNet, ConvNeXt, and EfficientNet backbones within a gated multi-expert architecture, incorporates a prototype learning module for example-driven interpretability, and applies physics-informed regularization to enforce morphology preservation and spatial coherence during feature learning. Monte Carlo Dropout is used to quantify predictive uncertainty. On the BreaKHis dataset, Histo-MExNet achieves 96.97% accuracy under multi-magnification training and demonstrates improved generalization to unseen magnification levels compared to single-expert models, while uncertainty estimation helps identify out-of-distribution samples and reduce overconfident errors, supporting a balanced combination of accuracy, robustness, and interpretability for clinical decision support.