RT Journal Article
SR Electronic
T1 Deceptive learning in histopathology
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2022.04.21.489110
DO 10.1101/2022.04.21.489110
A1 Sahar Shahamatdar
A1 Daryoush Saeed-Vafa
A1 Drew Linsley
A1 Farah Khalil
A1 Katherine Lovinger
A1 Lester Li
A1 Howard McLeod
A1 Sohini Ramachandran
A1 Thomas Serre
YR 2022
UL http://biorxiv.org/content/early/2022/04/22/2022.04.21.489110.abstract
AB Deep learning holds immense potential for histopathology, automating tasks that are simple for expert pathologists, and revealing novel biology for tasks that were previously considered difficult or impossible to solve by eye alone. However, the extent to which the visual strategies learned by deep learning models in histopathological analysis are trustworthy or not has yet to be systematically analyzed. In this work, we address this problem and discover new limits on the histopathological tasks for which deep learning models learn trustworthy versus deceptive solutions. While tasks that have been extensively studied in the field like tumor detection are reliable and trustworthy, recent advances demonstrating the ability to learn molecular profiling from hematoxylin and eosin (H&E) stained slides do not hold up to closer scrutiny. Our analysis framework represents a new approach in understanding the capabilities of deep learning models, which should be incorporated into the computational pathologists toolkit.Competing Interest StatementThe authors have declared no competing interest.