Nature Communications (Mar 2025)
Multimodal histopathologic models stratify hormone receptor-positive early breast cancer
- 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. Loeffler,
- 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
Affiliations
- Kevin M. Boehm
- Computational Oncology Service, Memorial Sloan Kettering Cancer Center
- Omar S. M. El Nahhas
- Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden
- Antonio Marra
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center
- Michele Waters
- Computational Oncology Service, Memorial Sloan Kettering Cancer Center
- Justin Jee
- Computational Oncology Service, Memorial Sloan Kettering Cancer Center
- Lior Braunstein
- Department of Radiation Oncology, Memorial Sloan Kettering Cancer Center
- Nikolaus Schultz
- Computational Oncology Service, Memorial Sloan Kettering Cancer Center
- Pier Selenica
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center
- Hannah Y. Wen
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center
- Britta Weigelt
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center
- Evan D. Paul
- MultiplexDX, s.r.o., Ilkovičova 8, 841 04 Karlova Ves, Comenius University Science Park
- Pavol Cekan
- MultiplexDX, s.r.o., Ilkovičova 8, 841 04 Karlova Ves, Comenius University Science Park
- Ramona Erber
- Institute of Pathology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, Comprehensive Cancer Center Erlangen-EMN (CCC ER-EMN)
- Chiara M. L. Loeffler
- Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden
- Elena Guerini-Rocco
- Department of Pathology, European Institute of Oncology IRCCS
- Nicola Fusco
- Department of Pathology, European Institute of Oncology IRCCS
- Chiara Frascarelli
- Department of Pathology, European Institute of Oncology IRCCS
- Eltjona Mane
- Department of Pathology, European Institute of Oncology IRCCS
- Elisabetta Munzone
- Division of Medical Senology, European Institute of Oncology IRCCS
- Silvia Dellapasqua
- Division of Medical Senology, European Institute of Oncology IRCCS
- Paola Zagami
- Early Drug Development for Innovative Therapies, European Institute of Oncology IRCCS
- Giuseppe Curigliano
- Early Drug Development for Innovative Therapies, European Institute of Oncology IRCCS
- Pedram Razavi
- Department of Medicine, Memorial Sloan Kettering Cancer Center
- Jorge S. Reis-Filho
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center
- Fresia Pareja
- Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center
- Sarat Chandarlapaty
- Department of Medicine, Memorial Sloan Kettering Cancer Center
- Sohrab P. Shah
- Computational Oncology Service, Memorial Sloan Kettering Cancer Center
- Jakob Nikolas Kather
- Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden
- DOI
- https://doi.org/10.1038/s41467-025-57283-x
- Journal volume & issue
-
Vol. 16,
no. 1
pp. 1 – 14
Abstract
Abstract 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 and lag time have limited global adoption, and previous attempts to estimate it using clinicopathologic variables have had limited success. To address this, we assembled 6172 cases across three institutions and developed Orpheus, a multimodal deep learning tool to infer the RS from H&E whole-slide images. Our model identifies TAILORx high-risk cases (RS > 25) with an area under the curve (AUC) of 0.89, compared to a leading clinicopathologic nomogram with 0.73. Furthermore, in patients with RS ≤ 25, Orpheus ascertains risk of metastatic recurrence more accurately than the RS itself (0.75 vs 0.49 mean time-dependent AUC). These findings have the potential to guide adjuvant therapy for high-risk cases and tailor surveillance for patients at elevated metastatic recurrence risk.