Regression-based Deep-Learning predicts molecular biomarkers from pathology slides

Omar S. M. El Nahhas, Chiara M. L. Loeffler, Zunamys I. Carrero, Marko Treeck, Fiona R. Kolbinger, Katherine J. Hewitt, Hannah S. Muti, Mara Graziani, Qinghe Zeng, Julien Calderaro, Nadina Ortiz-Brüchle, Tanwei Yuan, Michael Hoffmeister, Hermann Brenner, Alexander Brobeil, Jorge S. Reis-Filho and Jakob Nikolas Kather ()
Additional contact information
Omar S. M. El Nahhas: TUD Dresden University of Technology
Chiara M. L. Loeffler: TUD Dresden University of Technology
Zunamys I. Carrero: TUD Dresden University of Technology
Marko Treeck: TUD Dresden University of Technology
Fiona R. Kolbinger: TUD Dresden University of Technology
Katherine J. Hewitt: TUD Dresden University of Technology
Hannah S. Muti: TUD Dresden University of Technology
Mara Graziani: University of Applied Sciences of Western Switzerland (HES-SO Valais)
Qinghe Zeng: Sorbonne Université, Université Paris Cité
Julien Calderaro: Assistance Publique-Hôpitaux de Paris, Département de Pathologie, CHU Henri Mondor
Nadina Ortiz-Brüchle: University Hospital RWTH Aachen
Tanwei Yuan: German Cancer Research Center (DKFZ)
Michael Hoffmeister: German Cancer Research Center (DKFZ)
Hermann Brenner: German Cancer Research Center (DKFZ)
Alexander Brobeil: University Hospital Heidelberg
Jorge S. Reis-Filho: Memorial Sloan Kettering Cancer Center
Jakob Nikolas Kather: TUD Dresden University of Technology

Nature Communications, 2024, vol. 15, issue 1, 1-13

Abstract: Abstract Deep Learning (DL) can predict biomarkers from cancer histopathology. Several clinically approved applications use this technology. Most approaches, however, predict categorical labels, whereas biomarkers are often continuous measurements. We hypothesize that regression-based DL outperforms classification-based DL. Therefore, we develop and evaluate a self-supervised attention-based weakly supervised regression method that predicts continuous biomarkers directly from 11,671 images of patients across nine cancer types. We test our method for multiple clinically and biologically relevant biomarkers: homologous recombination deficiency score, a clinically used pan-cancer biomarker, as well as markers of key biological processes in the tumor microenvironment. Using regression significantly enhances the accuracy of biomarker prediction, while also improving the predictions’ correspondence to regions of known clinical relevance over classification. In a large cohort of colorectal cancer patients, regression-based prediction scores provide a higher prognostic value than classification-based scores. Our open-source regression approach offers a promising alternative for continuous biomarker analysis in computational pathology.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-45589-1 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-45589-1

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-45589-1

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().