Deep learning for automated scoring of immunohistochemically stained tumour tissue sections – Validation across tumour types based on patient outcomes

We aimed to develop deep learning (DL) models to detect protein expression in immunohistochemically (IHC) stained tissue-sections, and to compare their accuracy and performance with manually scored clinically relevant proteins in common cancer types.Five cancer patient cohorts (colon, two prostate,...

Full description

Bibliographic Details

Published in:	Heliyon
Main Authors:	Wanja Kildal, Karolina Cyll, Joakim Kalsnes, Rakibul Islam, Frida M. Julbø, Manohar Pradhan, Elin Ersvær, Neil Shepherd, Ljiljana Vlatkovic, Xavier Tekpli, Øystein Garred, Gunnar B. Kristensen, Hanne A. Askautrud, Tarjei S. Hveem, Håvard E. Danielsen, Tone F. Bathen, Elin Borgen, Anne-Lise Børresen-Dale, Olav Engebråten, Britt Fritzman, Olaf Johan Hartman-Johnsen, Jürgen Geisler, Gry Aarum Geitvik, Solveig Hofvind, Rolf Kåresen, Anita Langerød, Ole Christian Lingjærde, Gunhild M. Mælandsmo, Bjørn Naume, Hege G. Russnes, Kristine Kleivi Sahlberg, Torill Sauer, Helle Kristine Skjerven, Ellen Schlichting, Therese Sørlie
Format:	Article
Language:	English
Published:	Elsevier 2024-07-01
Subjects:	Deep learning Digital image analysis Immunohistochemistry Cancer Prognosis
Online Access:	http://www.sciencedirect.com/science/article/pii/S2405844024085608