What question did this study set out to answer?

To develop and assess a deep learning tool, ESPWA, for predicting estrogen receptor status in Haitian breast cancer patients.

February 22, 2026

Abstract PS3-04-28: Espwa: a deep learning-enabled computational pathology tool that facilitates precision oncology for haitian breast cancer patients

Key Points

To develop and assess a deep learning tool, ESPWA, for predicting estrogen receptor status in Haitian breast cancer patients.
Curated a dataset of H&E whole slide images (WSIs) linked to ER status from 3448 patients.
Employed weakly-supervised learning on H&E images to train models predicting ER status.
Utilized both binary classification and regression models for outcomes of ER status.
Applied data augmentation techniques to enhance model training.
Split datasets into training, validation, and testing sets to evaluate model performance.
The TCGA-trained model achieved an AUROC of 0.846 on its test set but only 0.671 on the ZL test set, indicating domain sensitivity.
The ZL-trained models achieved an AUROC of 0.790 and a correlation coefficient of 0.524, showcasing moderate performance.
ESPWA's accuracy of 0.726 surpassed the pathologist's 0.639 in ER status determination across multiple subgroups.
Performance varied, with less effectiveness on ER-weak positive tumors and poorly differentiated tumors.

Abstract

Abstract Background: Global disparities in breast cancer outcomes are a public health crisis. In Haiti, one of the most resource-limited health care settings in the world, the challenge is especially dire. With only five practicing pathologists serving the entire country, timely and complete pathologic assessment of tumor tissue is nearly impossible. As estrogen receptor (ER) assessment with immunohistochemistry (IHC) cannot be performed, all Haitian breast cancer patients are empirically treated with endocrine therapy (ET). This “one-size-fits-all” strategy results in increased morbidity and mortality. To address this unmet need, we present ESPWA: ER Status assessment using deep learning-enabled histoPathology Whole slide imaging (WSI) Analysis, a low-cost tool that informs precision-based use of ET for Haitian patients. Methods: To develop ESPWA, we curated a dataset of H/abstract Citation Format: D. Pulido-Arias, R. Henderson, J. Lormil, C. Millien, M. Djenane Jose, G. Flambert, M. Mathelier, M. Corrielus, T. Goncalves, J. Kalpathy-Cramer, E. Gerstner, K. Landgraf, A. Brown, P. Castle, J. Jeronimo, S. Sirintrapun, S. Wander, D. Milner, J. Brock, C. Bridge, A. E. Kim. Espwa: a deep learning-enabled computational pathology tool that facilitates precision oncology for haitian breast cancer patients abstract. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nrPS3-04-28.

Bookmark

Abstract PS3-04-28: Espwa: a deep learning-enabled computational pathology tool that facilitates precision oncology for haitian breast cancer patients

Key Points

Abstract

Cite This Study