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

Hematoxylin- and eosin (H&E) stained whole-slide images (WSIs) are thefoundation of diagnosis of cancer. In recent years, development of deeplearning-based methods in computational pathology enabled the prediction ofbiomarkers directly from WSIs. However, accurately linking tissue phenotype tobiomarkers at scale remains a crucial challenge for democratizing complexbiomarkers in precision oncology. This protocol describes a practical workflowfor solid tumor associative modeling in pathology (STAMP), enabling predictionof biomarkers directly from WSIs using deep learning. The STAMP workflow isbiomarker agnostic and allows for genetic- and clinicopathologic tabular datato be included as an additional input, together with histopathology images. Theprotocol consists of five main stages which have been successfully applied tovarious research problems: formal problem definition, data preprocessing,modeling, evaluation and clinical translation. The STAMP workflowdifferentiates itself through its focus on serving as a collaborative frameworkthat can be used by clinicians and engineers alike for setting up researchprojects in the field of computational pathology. As an example task, weapplied STAMP to the prediction of microsatellite instability (MSI) status incolorectal cancer, showing accurate performance for the identification ofMSI-high tumors. Moreover, we provide an open-source codebase which has beendeployed at several hospitals across the globe to set up computationalpathology workflows. The STAMP workflow requires one workday of hands-oncomputational execution and basic command line knowledge.

From Whole-slide Image to Biomarker Prediction: A Protocol for End-to-End Deep Learning in Computational Pathology