H&E to Oncotype DX: Predicting recurrence risk in HR+/HER2- breast cancer

  • Onur Can Koyun*
  • , Yongxin Guo
  • , Ziyu Su
  • , Hao Lu
  • , Mostafa Rezapour
  • , Robert Wesolowski
  • , Gary Tozbikian
  • , M. Khalid Khan Niazi
  • , Metin N. Gurcan
  • *Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The Oncotype DX® Recurrence Score (ODX) is a clinically validated prognostic assay for hormone receptor-positive early-stage breast cancer. Despite its utility, widespread adoption remains limited due to high costs and lengthy turnaround times. In this study, we propose AnchorMIL, a novel framework that predicts ODX scores directly from H&E stained whole-slide images, with the potential to decrease dependence on molecular profiling. AnchorMIL employs an anchored regression-classification mechanism to predict both continuous risk scores and binary risk predictions. On the TCGA-BRCA and OSU cohort, AnchorMIL achieved AUCs of 0.89 and 0.86, respectively, Beyond predictive accuracy, AnchorMIL demonstrates promising generalizability, and its interpretability reveals biologically meaningful features of aggressive tumor biology. The model captures complex prognostic interactions, and prioritizes dominant risk factors in high-risk cases. AnchorMIL offers a scalable, cost-effective tool for risk stratification, with the potential to reduce reliance on genomic assays, accelerate treatment decisions, and support equitable breast cancer care.

Original languageEnglish
Article number130469
JournalExpert Systems with Applications
Volume303
DOIs
Publication statusPublished - 25 Mar 2026
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2025 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license. http://creativecommons.org/licenses/by/4.0/

Keywords

  • Breast cancer
  • Digital pathology
  • Oncotype dx
  • Risk prediction
  • Transformer

Fingerprint

Dive into the research topics of 'H&E to Oncotype DX: Predicting recurrence risk in HR+/HER2- breast cancer'. Together they form a unique fingerprint.

Cite this