Machine Learning and Bias in Medical Imaging: Opportunities and Challenges
Circulation: Cardiovascular Imaging · 2024-02 · 17 (2)
DOI: 10.1161/circimaging.123.015495 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Circulation: Cardiovascular Imaging, 2024-02. Verfasst von Amey Vrudhula und 3 weiteren Autor:innen. Beteiligte Einrichtung: Icahn School of Medicine at Mount Sinai, New York (A.V.). Hauptthemen laut MEDLINE: Machine Learning, Algorithms. Die Arbeit wurde bisher 82-mal zitiert (Crossref) und nennt 98 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS, American Heart Association-American Stroke Association, NCATS NIH HHS.
Abstract (Originalsprache)
Bias in health care has been well documented and results in disparate and worsened outcomes for at-risk groups. Medical imaging plays a critical role in facilitating patient diagnoses but involves multiple sources of bias including factors related to access to imaging modalities, acquisition of images, and assessment (ie, interpretation) of imaging data. Machine learning (ML) applied to diagnostic imaging has demonstrated the potential to improve the quality of imaging-based diagnosis and the precision of measuring imaging-based traits. Algorithms can leverage subtle information not visible to the human eye to detect underdiagnosed conditions or derive new disease phenotypes by linking imaging features with clinical outcomes, all while mitigating cognitive bias in interpretation. Importantly, however, the application of ML to diagnostic imaging has the potential to either reduce or propagate bias. Understanding the potential gain as well as the potential risks requires an understanding of how and what ML models learn. Common risks of propagating bias can arise from unbalanced training, suboptimal architecture design or selection, and uneven application of models. Notwithstanding these risks, ML may yet be applied to improve gain from imaging across all 3A’s (access, acquisition, and assessment) for all patients. In this review, we present a framework for understanding the balance of opportunities and challenges for minimizing bias in medical imaging, how ML may improve current approaches to imaging, and what specific design considerations should be made as part of efforts to maximize the quality of health care for all.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Icahn School of Medicine at Mount Sinai, New York (A.V.).
- Department of Cardiology, Smidt Heart Institute (A.V., A.C.K., D.O., S.C.), Cedars-Sinai Medical Center.
- Division of Artificial Intelligence in Medicine, Department of Medicine (D.O.), Cedars-Sinai Medical Center.
ORCID-Profile: Amey Vrudhula, Alan C Kwan, David Ouyang, Susan Cheng
Förderung
- NHLBI NIH HHS
- American Heart Association-American Stroke Association
- NCATS NIH HHS
Zitieren
APA
Vrudhula, A., Kwan, A. C., Ouyang, D., & Cheng, S. (2024). Machine Learning and Bias in Medical Imaging: Opportunities and Challenges. Circulation: Cardiovascular Imaging, 17(2). https://doi.org/10.1161/circimaging.123.015495
Vancouver
Vrudhula A, Kwan AC, Ouyang D, Cheng S. Machine Learning and Bias in Medical Imaging: Opportunities and Challenges. Circulation: Cardiovascular Imaging. 2024;17(2). doi:10.1161/circimaging.123.015495
BibTeX
@article{Vrudhula2024,
author = {Vrudhula, Amey and Kwan, Alan C and Ouyang, David and Cheng, Susan},
title = {Machine Learning and Bias in Medical Imaging: Opportunities and Challenges},
journal = {Circulation: Cardiovascular Imaging},
year = {2024},
volume = {17},
number = {2},
doi = {10.1161/circimaging.123.015495}
}
EUVIMED