Weakly-supervised deep learning models in computational pathology
Tanya Nadine Augustine · EBioMedicine · 2022
Computational pathology is a burgeoning field which shows promise in increasing access to health care, particularly in resource-limited settings with a shortage of experienced pathologists.1 Complementing advances in artificial intelligence (AI) methods in identifying patterns of disease, is the advent of publicly available haematoxylin and eosin (H&E)-stained whole slide datasets from the Cancer Genome Atlas (TCGA), and other consortia that have provided a basis on which AI models can be trained and tested.