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

Nahhas, Omar S. M. El, Loeffler, Chiara M. L., Carrero, Zunamys I., van Treeck, Marko, Kolbinger, Fiona R., Hewitt, Katherine J., Muti, Hannah S., Graziani, Mara, Zeng, Qinghe, Calderaro, Julien, Ortiz-Brüchle, Nadina, Yuan, Tanwei, Hoffmeister, Michael, Brenner, Hermann, Brobeil, Alexander, Reis-Filho, Jorge S., Kather, Jakob Nikolas

arXiv.org Artificial Intelligence 

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 hypothesized that regression-based DL outperforms classification-based DL. Therefore, we developed and evaluated a new self-supervised attention-based weakly supervised regression method that predicts continuous biomarkers directly from images in 11,671 patients across nine cancer types. We tested our method for multiple clinically and biologically relevant biomarkers: homologous repair deficiency (HRD) 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 interpretability of the results 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.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found