Where, why, and how is bias learned in medical image analysis models? A study of bias encoding within convolutional networks using synthetic data
Open Access
- 12 December 2024
- journal article
- Published by Elsevier in EBioMedicine
- Vol. 111, 105501
Abstract
No abstract availableKeywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada
- Canada Research Chairs Program
- Alberta Innovates
- Killam Trusts
- Parkinson Association of Alberta
- Calgary Foundation
This publication has 16 references indexed in Scilit:
- Acquisition parameters influence AI recognition of race in chest x-rays and mitigating these factors reduces underdiagnosis biasNature Communications, 2024
- “Shortcuts” Causing Bias in Radiology Artificial Intelligence: Causes, Evaluation, and MitigationJournal of the American College of Radiology, 2023
- Detecting shortcut learning for fair medical AI using shortcut testingNature Communications, 2023
- Algorithmic encoding of protected characteristics in chest X-ray disease detection modelsEBioMedicine, 2023
- AI recognition of patient race in medical imaging: a modelling studyThe Lancet Digital Health, 2022
- Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populationsNature Medicine, 2021
- Radiology “forensics”: determination of age and sex from chest radiographs using deep learningEmergency Radiology, 2021
- Causality matters in medical imagingNature Communications, 2020
- Machine Learning and Health Care Disparities in DermatologyJAMA Dermatology, 2018
- Evolving Knowledge of Sex Differences in Brain Structure, Function, and ChemistryBiological Psychiatry, 2007