Prediction of molecular subclasses of uveal melanoma by deep learning using routine haematoxylin-eosin-stained tissue slides.

Farhan Akram Daniël P de BruynQuincy C C van den BoschTeodora E TrandafirThierry P P van den BoschRob M VerdijkAnnelies de KleinEmine KiliçAndrew P StubbsErwin Brosens Jan H von der Thusen

Published in: Histopathology (2024)

This study showcases the potential of the deep-learning methodology for predicting molecular subclasses in a multiclass manner using HE-stained WSI. This development holds promise for advanced prognostication of UM patients without the need of molecular or immunohistochemical testing. Additionally, this study suggests there are distinct histopathological features per subclass; mainly utilizing epithelioid cellular morphology for BAP1-classification, but an unknown feature distinguishes EIF1AX and SF3B1.

Keyphrases

deep learning
machine learning
end stage renal disease
artificial intelligence
newly diagnosed
single molecule
peritoneal dialysis
prognostic factors
big data
climate change