# A deep learning pipeline for PAM50 subtype classification using histopathology images and multi-objective patch selection

arXiv: https://arxiv.org/abs/2604.01798 · HTML: https://mlsanity.com/paper/2604.01798/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 54 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [A Review of Uncertainty Estimation and its Application in Medical Imaging](https://mlsanity.com/paper/2302.08119/) (2023)
- [SlideGraph+: Whole Slide Image Level Graphs to Predict HER2Status in Breast Cancer](https://mlsanity.com/paper/2110.06042/) (2021)
- [Overcoming the limitations of patch-based learning to detect cancer in whole slide images](https://mlsanity.com/paper/2012.00617/) (2020)
- [Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2403.07939/) (2024)
- [Generalisation effects of predictive uncertainty estimation in deep learning for digital pathology](https://mlsanity.com/paper/2112.09693/) (2021)
- [Breast MRI radiomics and machine learning radiomics-based predictions of response to neoadjuvant chemotherapy -- how are they affected by variations in tumour delineation?](https://mlsanity.com/paper/2309.01210/) (2023)
- [Breast Cancer Molecular Subtypes Prediction on Pathological Images with Discriminative Patch Selecting and Multi-Instance Learning](https://mlsanity.com/paper/2203.07659/) (2022)
- [Creating an Atlas of Normal Tissue for Pruning WSI Patching Through Anomaly Detection](https://mlsanity.com/paper/2310.03106/) (2023)
- [Multiple Instance Learning with random sampling for Whole Slide Image Classification](https://mlsanity.com/paper/2403.05351/) (2024)
- [Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images](https://mlsanity.com/paper/2409.09053/) (2024)
- [Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networks](https://mlsanity.com/paper/2412.10570/) (2024)
- [Bayesian Dropout](https://mlsanity.com/paper/1508.02905/) (2015)
- [Classification of Luminal Subtypes in Full Mammogram Images Using Transfer Learning](https://mlsanity.com/paper/2301.09282/) (2023)
- [Introducing an ensemble method for the early detection of Alzheimer's disease through the analysis of PET scan images](https://mlsanity.com/paper/2403.15443/) (2024)
- [Deep learning generates custom-made logistic regression models for explaining how breast cancer subtypes are classified](https://mlsanity.com/paper/2001.06988/) (2020)
- [An Integrated Optimization and Deep Learning Pipeline for Predicting Live Birth Success in IVF Using Feature Optimization and Transformer-Based Models](https://mlsanity.com/paper/2412.19696/) (2024)

## Abstract (arXiv)

Breast cancer is a highly heterogeneous disease with diverse molecular profiles. The PAM50 gene signature is widely recognized as a standard for classifying breast cancer into intrinsic subtypes, enabling more personalized treatment strategies. In this study, we introduce a novel optimization-driven deep learning framework that aims to reduce reliance on costly molecular assays by directly predicting PAM50 subtypes from H&E-stained whole-slide images (WSIs). Our method jointly optimizes patch informativeness, spatial diversity, uncertainty, and patch count by combining the non-dominated sorting genetic algorithm II (NSGA-II) with Monte Carlo dropout-based uncertainty estimation. The proposed method can identify a small but highly informative patch subset for classification. We used a ResNet18 backbone for feature extraction and a custom CNN head for classification. For evaluation, we used the internal TCGA-BRCA dataset as the training cohort and the external CPTAC-BRCA dataset as the test cohort. On the internal dataset, an F1-score of 0.8812 and an AUC of 0.9841 using 627 WSIs from the TCGA-BRCA cohort were achieved. The performance of the proposed approach on the external validation dataset showed an F1-score of 0.7952 and an AUC of 0.9512. These findings indicate that the proposed optimization-guided, uncertainty-aware patch selection can achieve high performance and improve the computational efficiency of histopathology-based PAM50 classification compared to existing methods, suggesting a scalable imaging-based replacement that has the potential to support clinical decision-making.