Invited Commentary: The Double-edged Sword of Bias in Medical Imaging Artificial Intelligence

HomeRadioGraphicsVol. 44, No. 5 PreviousNext InformaticsInvited Commentary: The Double-edged Sword of Bias in Medical Imaging Artificial IntelligencePouria Rouzrokh, Bradley J. Erickson Pouria Rouzrokh, Bradley J. Erickson Author AffiliationsFrom the Mayo Clinic Artificial Intelligence Laboratory and Radiology Informatics Laboratory, Department of Radiology, Mayo Clinic, 200 First St SW, Rochester, MN 55905.Address correspondence to B.J.E. (email: [email protected]).Pouria RouzrokhBradley J. Erickson Published Online:Apr 18 2024https://doi.org/10.1148/rg.230243See also the article by Tejani et al in this issue.MoreSectionsFull textPDF ToolsAdd to favoritesCiteTrack CitationsPermissionsReprints ShareShare onFacebookXLinked In References1. Tejani AS, Ng YS, Xi Y, Rayan JC. Understanding and Mitigating Bias in Imaging Artificial Intelligence. RadioGraphics 2024;44(5):e230067. Google Scholar2. Rouzrokh P, Khosravi B, Faghani S, et al. Mitigating Bias in Radiology Machine Learning: 1. Data Handling. Radiol Artif Intell 2022;4(5):e210290. Link, Google Scholar3. Zhang K, Khosravi B, Vahdati S, et al. Mitigating Bias in Radiology Machine Learning: 2. Model Development. Radiol Artif Intell 2022;4(5):e220010. Link, Google Scholar4. Faghani S, Khosravi B, Zhang K, et al. Mitigating Bias in Radiology Machine Learning: 3. Performance Metrics. Radiol Artif Intell 2022;4(5):e220061. Link, Google Scholar5. Drukker K, Chen W, Gichoya J, et al. Toward fairness in artificial intelligence for medical image analysis: identification and mitigation of potential biases in the roadmap from data collection to model deployment. J Med Imaging (Bellingham) 2023;10(6):061104. Medline, Google Scholar6. Langlotz CP. The Future of AI and Informatics in Radiology: 10 Predictions. Radiology 2023;309(1):e231114. Link, Google Scholar7. Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 2019;366(6464):447–453. Crossref, Medline, Google Scholar8. Lacson R, Eskian M, Licaros A, Kapoor N, Khorasani R. Machine Learning Model Drift: Predicting Diagnostic Imaging Follow-Up as a Case Example. J Am Coll Radiol 2022;19(10):1162–1169. Crossref, Medline, Google Scholar9. Goyal A, Bengio Y. Inductive biases for deep learning of higher-level cognition. Proc R Soc A Math Phys Eng Sci 2022;478(2266):20210068. Google ScholarArticle HistoryReceived: Dec 21 2023Accepted: Dec 28 2023Published online: Apr 18 2024 FiguresReferencesRelatedDetailsAccompanying This ArticleUnderstanding and Mitigating Bias in Imaging Artificial IntelligenceApr 18 2024RadioGraphicsRecommended Articles Comprehensive Imaging Review of Pleural Fistulas from Diagnosis to ManagementRadioGraphics2022Volume: 42Issue: 7pp. 1940-1955Overview of Interventional Pulmonology for RadiologistsRadioGraphics2021Volume: 41Issue: 7pp. 1916-1935Understanding and Mitigating Bias in Imaging Artificial IntelligenceRadioGraphics2024Volume: 44Issue: 5Quantitative Burden of COVID-19 Pneumonia at Chest CT Predicts Adverse Outcomes: A Post Hoc Analysis of a Prospective International RegistryRadiology: Cardiothoracic Imaging2020Volume: 2Issue: 5Imaging Manifestations of Chest TraumaRadioGraphics2021Volume: 41Issue: 5pp. 1321-1334See More RSNA Education Exhibits Outsmarting AI: What Role Can The Radiologist Play In The Making And Deployment Of Artificial Intelligence ApplicationsDigital Posters2021When To Call On-call: 15 Must Know Portable Cxr Cases And MimicsDigital Posters2021Test Your Knowledge: Lung Ultrasound From A-lines To Z-linesDigital Posters2021 RSNA Case Collection Pulmonary aspergillomaRSNA Case Collection2020Dynamic MRI findings of COVID-19 pneumoniaRSNA Case Collection2020Acute COVID-19 virus infection RSNA Case Collection2020 Vol. 44, No. 5 Abbreviations Abbreviations: AI artificial intelligence Metrics Altmetric Score PDF download