From whole-slide image to biomarker prediction

• Verfasst von: El Nahhas, Omar S. M. [VerfasserIn]
• Verfasst von: Treeck, Marko van [VerfasserIn]
• Verfasst von: Wölflein, Georg [VerfasserIn]
• Verfasst von: Unger, Michaela [VerfasserIn]
• Verfasst von: Försch, Sebastian [VerfasserIn]
• Verfasst von: Lenz, Tim [VerfasserIn]
• Verfasst von: Wagner, Sophia J. [VerfasserIn]
• Verfasst von: Hewitt, Katherine J. [VerfasserIn]
• Verfasst von: Khader, Firas [VerfasserIn]
• Verfasst von: Försch, Sebastian [VerfasserIn]
• Verfasst von: Truhn, Daniel [VerfasserIn]
• Verfasst von: Kather, Jakob Nikolas [VerfasserIn]
• Titel: From whole-slide image to biomarker prediction
• Titelzusatz: end-to-end weakly supervised deep learning in computational pathology
• Verf.angabe: Omar S.M. El Nahhas, Marko van Treeck, Georg Wölflein, Michaela Unger, Marta Ligero, Tim Lenz, Sophia J. Wagner, Katherine J. Hewitt, Firas Khader, Sebastian Foersch, Daniel Truhn & Jakob Nikolas Kather
• E-Jahr: 2025
• Jahr: January 2025
• Umfang: 24 S.
• Illustrationen: Illustrationen
• Fussnoten: Veröffentlicht: 16. September 2024 ; Gesehen am 24.06.2025
• Titel Quelle: Enthalten in: Nature protocols
• Ort Quelle: Basingstoke : Nature Publishing Group, 2006
• Jahr Quelle: 2025
• Band/Heft Quelle: 20(2025), 1 vom: Jan., Seite 293-316
• ISSN Quelle: 1750-2799
• DOI: doi:10.1038/s41596-024-01047-2
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Bioinformatics
• Sach-SW: Cancer imaging
• Sach-SW: Image processing
• K10plus-PPN: 1928951813

Abstract

Hematoxylin- and eosin-stained whole-slide images (WSIs) are the foundation of diagnosis of cancer. In recent years, development of deep learning-based methods in computational pathology has enabled the prediction of biomarkers directly from WSIs. However, accurately linking tissue phenotype to biomarkers at scale remains a crucial challenge for democratizing complex biomarkers in precision oncology. This protocol describes a practical workflow for solid tumor associative modeling in pathology (STAMP), enabling prediction of biomarkers directly from WSIs by using deep learning. The STAMP workflow is biomarker agnostic and allows for genetic and clinicopathologic tabular data to be included as an additional input, together with histopathology images. The protocol consists of five main stages that have been successfully applied to various research problems: formal problem definition, data preprocessing, modeling, evaluation and clinical translation. The STAMP workflow differentiates itself through its focus on serving as a collaborative framework that can be used by clinicians and engineers alike for setting up research projects in the field of computational pathology. As an example task, we applied STAMP to the prediction of microsatellite instability (MSI) status in colorectal cancer, showing accurate performance for the identification of tumors high in MSI. Moreover, we provide an open-source code base, which has been deployed at several hospitals across the globe to set up computational pathology workflows. The STAMP workflow requires one workday of hands-on computational execution and basic command line knowledge.