TY  - JOUR
AU  - El Nahhas, Omar S M
AU  - Loeffler, Chiara M L
AU  - Carrero, Zunamys I
AU  - van Treeck, Marko
AU  - Kolbinger, Fiona R
AU  - Hewitt, Katherine J
AU  - Muti, Hannah S
AU  - Graziani, Mara
AU  - Zeng, Qinghe
AU  - Calderaro, Julien
AU  - Ortiz-Brüchle, Nadina
AU  - Yuan, Tanwei
AU  - Hoffmeister, Michael
AU  - Brenner, Hermann
AU  - Brobeil, Alexander
AU  - Reis-Filho, Jorge S
AU  - Kather, Jakob Nikolas
TI  - Regression-based Deep-Learning predicts molecular biomarkers from pathology slides.
JO  - Nature Communications
VL  - 15
IS  - 1
SN  - 2041-1723
CY  - [London]
PB  - Nature Publishing Group UK
M1  - DKFZ-2024-00316
SP  - 1253
PY  - 2024
AB  - 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.
LB  - PUB:(DE-HGF)16
C6  - pmid:38341402
C2  - pmc:PMC10858881
DO  - DOI:10.1038/s41467-024-45589-1
UR  - https://inrepo02.dkfz.de/record/288058
ER  -