Towards objective and systematic evaluation of bias in artificial intelligence for medical imaging

EAM Stanley, R Souza, AJ Winder… - Journal of the …, 2024 - academic.oup.com
Objective Artificial intelligence (AI) models trained using medical images for clinical tasks
often exhibit bias in the form of subgroup performance disparities. However, since not all …

Towards objective and systematic evaluation of bias in medical imaging AI

EAM Stanley, R Souza, A Winder, V Gulve… - arXiv preprint arXiv …, 2023 - arxiv.org
Artificial intelligence (AI) models trained using medical images for clinical tasks often exhibit
bias in the form of disparities in performance between subgroups. Since not all sources of …

Where, why, and how is bias learned in medical image analysis models? A study of bias encoding within convolutional networks using synthetic data

EAM Stanley, R Souza, M Wilms, ND Forkert - EBioMedicine, 2025 - thelancet.com
Background Understanding the mechanisms of algorithmic bias is highly challenging due to
the complexity and uncertainty of how various unknown sources of bias impact deep …