Evidence-Based Artificial Intelligence in Medical Imaging - 20/11/21

Doi : 10.1016/j.cpet.2021.09.005

David L. Streiner, PhD, CPsych ^a,^b,^c, Babak Saboury, MD, MPH, DABR, DABNM ^d,^e,^f, Katherine A. Zukotynski, MD, PhD, FRCPC, PEng ^g,^h,^i,^⁎
^a Department of Psychiatry and Behavioural Neurosciences, McMaster University
^b Department of Psychiatry, University of Toronto
^c St. Joseph’s Healthcare, West 5th Campus, 100 West 5th Street, Hamilton, Ontario L8N 3K7, Canada
^d Department of Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA
^e Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, Baltimore, MD, USA
^f Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, PA, USA
^g Departments of Radiology and Medicine, McMaster University, 1200 Main St. W., Hamilton, ON L8N 3Z5, Canada
^h School of Biomedical Engineering, McMaster University, 1280 Main St. W., Hamilton, ON L8S 4K1, Canada
ⁱ Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, 10 King’s College Rd., Toronto, ON M5S 3G8, Canada

^∗Corresponding author. Department of Medicine, McMaster University, 1200 Main Street West, Hamilton, Ontario L8N 3Z5, Canada.Department of MedicineMcMaster University1200 Main Street WestHamiltonOntarioL8N 3Z5Canada

Résumé

Artificial intelligence (AI) in medical imaging is in its infancy. However, ongoing advances in hardware and software as well as increasing access to ever-expanding datasets for training, validation, and testing purposes are likely to make AI an increasingly prevalent and powerful tool. Of course issues, such as the need to protect the privacy of sensitive health data, remain; nevertheless, it is likely the average imager will need to develop an evidence-based approach to assessing AI in medical imaging. We hope this article will provide insight into just how this can be conducted by applying 5 simple questions, specifically: (1) Who was in the training sample, (2) How was the model trained, (3) How reliable is the algorithm, (4) How was the model validated, and (5) How useable is the algorithm.

Le texte complet de cet article est disponible en PDF.

Keywords : Evidence-based, Medical imaging, Artificial intelligence