Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.14416 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911517977346048 |
|---|---|
| author | Taufika, Enam Ahmed Arafatha, Md Ahasanul Ghoshb, Abhijit Kumar Rezab, Md. Tanzim Alamc, Md Ashad |
| author_facet | Taufika, Enam Ahmed Arafatha, Md Ahasanul Ghoshb, Abhijit Kumar Rezab, Md. Tanzim Alamc, Md Ashad |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14416 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Histo-MExNet: A Unified Framework for Real-World, Cross-Magnification, and Trustworthy Breast Cancer Histopathology Taufika, Enam Ahmed Arafatha, Md Ahasanul Ghoshb, Abhijit Kumar Rezab, Md. Tanzim Alamc, Md Ashad Computer Vision and Pattern Recognition 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. |
| title | Histo-MExNet: A Unified Framework for Real-World, Cross-Magnification, and Trustworthy Breast Cancer Histopathology |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.14416 |