Multimodal histopathologic models stratify hormone receptor-positive early breast cancer

• DOI: 10.1038/s41467-025-57283-x
• Publication Date: 2025-03-02T04:50:46Z
• Authors: Kevin M. Boehm; Omar S. M. El Nahhas; Antonio Marra; Michele Waters; Justin Jee; Lior Braunstein; Nikolaus Schultz; Pier Selenica; Hannah Y. Wen; Britta Weigelt; Evan D. Paul; Pavol Cekan; Ramona Erber; Chiara M. L. Loef...; Elena Guerini-Rocco; Nicola Fusco; Chiara Frascarelli; Eltjona Mane; Elisabetta Munzone; Silvia Dellapasqua; Paola Zagami; Giuseppe Curigliano; Pedram Razavi; Jorge S. Reis-Filho; Fresia Pareja; Sarat Chandarlapaty; Sohrab P. Shah; Jakob Nikolas Kather

The Oncotype DX® Recurrence Score (RS) is an assay for hormone receptor-positive early breast cancer with extensively validated predictive and prognostic value. However, its cost lag time have limited global adoption, previous attempts to estimate it using clinicopathologic variables had success. To address this, we assembled 6172 cases across three institutions developed Orpheus, a multimodal deep learning tool infer the RS from H&E whole-slide images. Our model identifies TAILORx high-risk (RS > 25) area under curve (AUC) of 0.89, compared leading nomogram 0.73. Furthermore, in patients ≤ 25, Orpheus ascertains risk metastatic recurrence more accurately than itself (0.75 vs 0.49 mean time-dependent AUC). These findings potential guide adjuvant therapy tailor surveillance at elevated risk.