Unknown

Dataset Information

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


ABSTRACT:

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 sources of bias in real-world medical imaging data are easily identifiable, it is challenging to comprehensively assess their impacts. In this article, we introduce an analysis framework for systematically and objectively investigating the impact of biases in medical images on AI models.

Materials and methods

Our framework utilizes synthetic neuroimages with known disease effects and sources of bias. We evaluated the impact of bias effects and the efficacy of 3 bias mitigation strategies in counterfactual data scenarios on a convolutional neural network (CNN) classifier.

Results

The ana

SUBMITTER: Stanley EAM 

PROVIDER: S-EPMC11491635 | biostudies-literature | 2024 Nov

REPOSITORIES: biostudies-literature