Course presenters

Learn from the brightest minds in artificial intelligence (AI) at AI Implementation: Building Expertise and Influence. During this two-day course, you’ll build a foundational understanding of AI in radiology and learn how to implement this technology in your practice.

Course directors

Chen

Po-Hao Chen, MD

United States
Po-Hao Chen, MD, is the chief informatics officer at the Cleveland Clinic (CC) Imaging Institute, the IT medical director of Enterprise Radiology and is a practicing musculoskeletal radiologist. Dr. Chen earned his MD and MBA from Harvard in 2012, completed his radiology training at the University of Pennsylvania and has received awards from national innovation challenges, hackathons and research presentations. Dr. Chen's current academic interest is in the "last-mile" challenges of AI, such as creating a scalable data pipeline to validate and continuously monitor AI models.
Chen

Yan Chen, PhD

United Kingdom
Yan Chen, PhD, is an associate professor of cancer screening at the University of Nottingham. Her research interests primarily concern human and machine performance evaluations in medical imaging applications in the widest sense, using visual search and computer science approaches. This currently encompasses the radiological areas of breast screenings, prostate cancer imaging, lung cancer imaging and chest CT scans as well as digital pathology and surgical areas of orthopedic and laparoscopic surgery. In these domains, Dr. Chen has performed many eye tracking analyses and other investigations. She is interested in artificial intelligence testing and evaluation in radiology and pathology.

Marc

Marc Kohli, MD

United States
Marc Kohli, MD, is the medical director of imaging informatics at UCSF, a position he assumed in November 2015 following six years spent leading radiology informatics at Indiana University. Dr. Kohli has an extensive record of service to informatics, including chair-elect of the Board of Directors for the Society of Imaging Informatics in Medicine (SIIM). Dr. Kohli also sits on the Radiology Informatics Committee (RIC) for RSNA as the co-chair of a joint RSNA/American College of Radiology (ACR) Common Data Element (CDE) Steering Subcommittee, which oversees RadElement.org. RadElement.org houses human- and machine-readable data definitions, and the committee has actively engaged EHR, speech recognition and PACS vendors to enable interoperability. Dr. Kohli has participated in several webinars and has lectured over 70 times at national and international conferences. His YouTube video on radiology informatics has been viewed more than 25,000 times and is used for imaging informatics education around the globe. Recently, Dr. Kohli has focused on AI implementation and ethics.

Preveldello

Luciano M. Prevedello, MD

United States
Luciano M. Prevedello, MD, is the vice chair of medical informatics and augmented intelligence in imaging in the department of radiology at The Ohio State University (OSU) Wexner Medical Center. Dr. Prevedello is also an associate professor of radiology at the OSU Wexner Medical Center and is the medical director of the 3D and Advanced Visualization Lab. Following his residency in radiology, Dr. Prevedello received formal training in imaging informatics, quality and safety as well as diagnostic radiology with an emphasis on evidence-based imaging, diagnostic neuroimaging and emergency radiology at Brigham and Women’s Hospital at Harvard Medical School. He obtained his master’s degree in public health at the Harvard School of Public Health and is board certified in radiology, neuroradiology and clinical informatics. At RSNA, Dr. Prevedello is a member of the Machine Learning Steering Subcommittee, Imaging Informatics Subcommittee and Radiology Informatics Committee (RIC) and is an associate editor of the journal, Radiology: Artificial Intelligence. Dr. Prevedello is part of the Board of Directors of the Society for Imaging Informatics in Medicine (SIIM) and is a member of the Informatics Advisory Council at the ACR.

Case-based instructors

Gichoya

Judy W. Gichoya, MBChB

United States
Judy W. Gichoya, MBChB, is a multidisciplinary researcher, trained as both an informatician and a clinically active radiologist. She has been funded through the Grand Challenges Canada and the National Science Foundation’s (NSF) division of Electrical, Communications and Cyber Systems (ECCS). Dr. Gichoya focuses her career on validating machine learning (ML) models for health in real clinical settings and explores explainability and fairness with a specific focus on how algorithms fail. She has worked on the curation of datasets for the SIIM hackathon and ML committee. She volunteers on the ACR and RSNA machine learning committees to support the AI ecosystem and advance development and use of AI in medicine. Dr. Gichoya is currently working on the sociotechnical context for AI explainability for radiology, with an emphasis on the dimensions of human factors that govern user perceptions and preferences of Explainable Artificial Intelligence (XAI) systems.

Felipe

Felipe Campos Kitamura, MD

Brazil
Felipe Kitamura, MD, head of AI at Dasa, is also a neuroradiologist and an MSc and PhD candidate in the department of diagnostic imaging at Universidade Federal de São Paulo (UNIFESP). Dr. Kitamura is also a Radiology in Training deputy editor of the Radiology journal and is co-chair of the ML Education Subcommittee at SIIM and has won gold medals in the RSNA and SIIM ML Challenges.

Sharma

Nisha Sharma, MBChB

United Kingdom
Nisha Sharma, MBChB, is the director of the breast screening program at Leeds Teaching Hospitals in the United Kingdom. She is a radiologist consultant who specializes in breast imaging and is active in research and audits with a particular interest in the role of AI within breast imaging.