Multiple instance learning on tile level-pathologyimages provides accurate and interpretableclassification for breast cancer molecular subtypes
Konstantinos Athanasios Papagoras, Ole Lund, Carolina Barra
This paper presents a weakly supervised deep learning approach for breast cancer molecular subtyping using tile-level pathology images without tumor annotations, achieving high accuracy and interpretability.
bioRxiv · Dec 22, 2025 · PreprintBioinformatics