Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study.

Jakob Nikolas Kather Johannes KrisamPornpimol CharoentongTom LueddeEsther HerpelCleo-Aron Weis Timo GaiserAlexander MarxNektarios A ValousDyke FerberLina Jansen Constantino Carlos Reyes-AldasoroInka ZörnigDirk JägerHermann BrennerJenny Chang-ClaudeMichael HoffmeisterNiels Halama

Published in: PLoS medicine (2019)

In our retrospective study, we show that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images.

Keyphrases

deep learning
convolutional neural network
endothelial cells
artificial intelligence
machine learning
induced pluripotent stem cells
optical coherence tomography
free survival