Title: Artificial Intelligence: Hype, Reality, and Future Implications for Diagnostic Imaging
Speaker: Eliot L. Siegel, MD, FACR, FSIIM
The Department of Imaging is honored to have Eliot L. Siegel, MD, FACR, FSIIM, presenting at our Grand Rounds on Wednesday, January 15th, at 12:00 pm in the College of Medicine, Room 2117.
Dr. Eliot Siegel is Professor and Vice Chair of Research Information Systems at the University of Maryland School of Medicine, Department of Diagnostic Radiology, as well as Chief of Radiology and Nuclear Medicine for the Veterans Affairs Maryland Healthcare System, both in Baltimore, MD. He has adjunct appointments as Professor of Bioengineering at the University of Maryland College Park and as Professor of Computer Science at the University of Maryland Baltimore County campus. Dr. Siegel has authored hundreds of articles, book chapters, and made more than 1,000 presentations globally. Dr. Siegel has won numerous awards and serves on a number of clinical, advisory, and editorial boards currently co-chairing of the annual Conference on Machine Learning in Medical Imaging. His areas of interest and responsibility at both the local and national levels include digital imaging and PACS, telemedicine, the electronic medical record, and informatics and artificial intelligence in medicine.
Abstract: A variety of difficult challenges in data science can be solved best with the creation of a “machine” which can provide a simulation or model to discern patterns in a dataset and make predictions. The rapid adoption of “machine” and specifically, “Deep Learning” in Diagnostic Imaging has resulted in the development of algorithms for detection, diagnosis, and quantification of medical images at an ever-accelerating pace. Major successes in the application of “Deep Learning/AI” in speech recognition, self-driving cars, translation and strategic games such as Chess, Go, and Poker have resulted in major financial investments and bold and controversial predictions by “experts” about the rapidity of general adoption in Radiology and other medical imaging specialties such as pathology, dermatology, and ophthalmology. However, tremendous challenges exist in the implementation of machine learning. The current state of the art would require thousands of algorithms and many millions of imaging studies to replace more than a tiny fraction of the tasks of a diagnostic radiology and would require hundreds of thousands or millions of hours of “expert” time to tag these. Although algorithm development times have been drastically reduced, the time and effort required for testing, verification, and validation of these algorithms in clinical practice has not decreased. Regulatory bottlenecks and medico-legal issues and constraints will need to change substantially for widespread adoption within the next several years or decades. Finally, Deep Learning may have its greatest initial success in solving non-image related challenges such as image quality, workflow efficiency, improved communication and patient safety.
College of Medicine, Room 2117