Prediction of heart transplant rejection from routine pathology slides with self-supervised deep learning.

Tobias Paul Seraphin Mark LueddeChristoph RoderburgMarko van TreeckPascal ScheiderRoman David Bülow Peter Boor Sven Heiko LoosenZdenek ProvaznikDaniel MendelsohnFilip BerishaChristina Magnussen Dirk Westermann Tom Luedde Christoph Brochhausen Samuel Sossalla Jakob Nikolas Kather

Published in: European heart journal. Digital health (2023)

We conclude that artificial intelligence can detect patterns of cellular transplant rejection in routine pathology, even when trained on small cohorts.

Keyphrases

artificial intelligence
deep learning
machine learning
big data
clinical practice
convolutional neural network
heart failure
resistance training
atrial fibrillation