English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep Learning (DL) can predict biomarkers from cancer histopathology. Severalclinically approved applications use this technology. Most approaches, however,predict categorical labels, whereas biomarkers are often continuousmeasurements. We hypothesized that regression-based DL outperformsclassification-based DL. Therefore, we developed and evaluated a newself-supervised attention-based weakly supervised regression method thatpredicts continuous biomarkers directly from images in 11,671 patients acrossnine cancer types. We tested our method for multiple clinically andbiologically relevant biomarkers: homologous repair deficiency (HRD) score, aclinically used pan-cancer biomarker, as well as markers of key biologicalprocesses in the tumor microenvironment. Using regression significantlyenhances the accuracy of biomarker prediction, while also improving theinterpretability of the results over classification. In a large cohort ofcolorectal cancer patients, regression-based prediction scores provide a higherprognostic value than classification-based scores. Our open-source regressionapproach offers a promising alternative for continuous biomarker analysis incomputational pathology.

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