Near-Term Clinical Applications of Artificial Intelligence in Diagnostic Imaging
Please join Eliot Siegel, M.D., Professor and Vice Chair, University of Maryland School of Medicine, Department of Diagnostic Radiology and Nuclear Medicine; Chief, Imaging, VA Maryland Healthcare System.
Date: Wednesday, November 16, 2016
Time: 2 PM to 3 PM EST
Amid growing fears of artificial intelligence technology replacing the radiologist with auto-population of findings directly in the radiology report, Dr. Siegel takes a hard look at what’s real today and what’s futuristic. While artificial intelligence is not yet the silver bullet that some hoped it would be, there are real, near-term achievable applications that can have significant and immediate impact on diagnostic imaging and patient outcomes.
Hear Dr. Siegel discuss applications of artificial intelligence that can be adopted today and in the near future for the smarter, safer and more cost effective practice of diagnostic imaging. This can be accomplished while simultaneously laying the framework for incremental improvements in deep learning algorithms that will get us closer to realizing the larger vision in the future. Some of the exciting radiology applications of artificial intelligence that can be explored today include:
- Making prior imaging data easily discoverable and accessible from the EHR, especially within the radiology workflow
- Normalizing and standardizing data (using SNOMED CT, LOINC, HL-7, DICOM, etc.) to make high-quality data easily consumable by machine learning systems
- Intelligently tracking critical findings and follow-up communications to eliminate life-threatening gaps in patient care
- Providing algorithms and accessing databases that can intelligently present information and assist clinicians in understanding complex problems and support smarter decision making
- Improving departmental efficiency by decreasing waiting times and increasing throughput
Please join us for this highly informative and interactive webinar to learn why artificial intelligence and deep-learning systems should be embraced rather than feared for the game-changing impact they can have on radiologists’ efficiency and patient care and safety – today and in the near future.