Biased data, biased AI: deep networks predict the acquisition site of TCGA images

Biased data, biased AI: deep networks predict the acquisition site of TCGA images

Abstract Background Deep learning models applied to healthcare applications including digital pathology have been increasing their scope and importance in recent years. Many of these models have been trained on The Cancer Genome Atlas (TCGA) atlas of digital images, or use it as a validation source....

Full description

Bibliographic Details
Main Authors: Taher Dehkharghanian, Azam Asilian Bidgoli, Abtin Riasatian, Pooria Mazaheri, Clinton J. V. Campbell, Liron Pantanowitz, H. R. Tizhoosh, Shahryar Rahnamayan
Format: Article
Language:English
Published: BMC 2023-05-01
Series:Diagnostic Pathology
Subjects:
Digital pathology
Deep Learning
AI bias
AI ethics
TCGA
Cancer
Online Access:https://doi.org/10.1186/s13000-023-01355-3

Internet

https://doi.org/10.1186/s13000-023-01355-3

Similar Items