A Framework for Prospective Deployment of Deep Learning in MRI

Recent years have seen large advances in new artificial intelligence (AI) techniques for improving the current status of medical imaging, and specifically, magnetic resonance imaging (MRI). However, despite these advances, there have been few instances of successful prospective clinical applications of artificial intelligence for MRI. In this manuscript, we broadly categorize the different applications of AI in MRI and provide a framework for important considerations and challenges for prospectively deploying these promising tools in the clinic to enhance patient care.

Chaudhari AS, Sandino CM, Cole EK, Larson DB, Gold GE, Vasanawala SS, Lungren MP, Hargreaves BA, Langlotz CP. Prospective deployment of deep learning in MRI: A framework for important considerations, challenges, and recommendations for best practices. J Magn Reson Imaging. 2020 Aug 24. doi: 10.1002/jmri.27331. Online ahead of print.

Online Journal Article

An example of one of three general use-cases for deep learning and convolutional neural networks in MRI.

Assistant Professor (Research) of Radiology (Integrative Biomedical Imaging Informatics at Stanford) and, by courtesy, of Biomedical Data Science
Associate Professor of Neurology, of Neurosurgery and of Bioengineering and, by courtesy, of Electrical Engineering
Stanford Medicine Professor of Radiology and Biomedical Imaging
Professor of Radiology (Radiological Sciences Laboratory) and, by courtesy, of Electrical Engineering and of Bioengineering
Associate Professor of Radiology (Musculoskeletal Imaging) and, by courtesy, of Orthopaedic Surgery

Contact Information

Lucas Center for Imaging 
1201 Welch Rd, Stanford, CA 94305-5488

Directions: Lucas Ctr. or Porter Dr. Locations