Keynotes
Medical Image Perception Through the Eyes of the Observer
Elizabeth Anne Krupinski
Professor and Vice Chair for Research, Department of Radiology and Imaging Sciences; Emory University School of Medicine,
Bio:
Dr. Krupinski is Professor and Vice-Chair of Research at Emory University in the Departments of Radiology, Psychology and Bioinformatics. She received her BA from Cornell, MA from Montclair State and PhD from Temple, all in Experimental Psychology. Her interests are in medical image perception, observer performance, decision making, and human factors. She is Past President of the American Telemedicine Association, Past Chair of Society for Imaging Informatics in Medicine, Past Chair of SPIE Medical Imaging, President of the Society for Education and the Advancement of Connected Health, and President of the Medical Image Perception Society. She is Editor of Telemedicine Reports and the Journal of Digital Imaging.
Abstract.: Medical images constitute a core portion of the information physicians utilize to render diagnostic and treatment decisions. At a fundamental level, the diagnostic process involves two aspects – visually inspecting the image (perception) and rendering an interpretation (cognition). Key indications of expert interpretation of medical images are consistent, accurate and efficient diagnostic performance, but how do we know when someone has attained the level of training required to be considered an expert? How do we know the best way to present images to the clinician to optimize accuracy and efficiency? Artificial intelligence schemes are being developed to assist with medical image acquisition, interpretation, and treatment decision-making, but to optimize and integrate these tools into everyday clinical routines, we need to consider both the technology and the human part of the human-technology interface equation. The advent of digital imaging and associated tools in many clinical specialties, including radiology, pathology, and dermatology, has dramatically changed the way that clinicians view images, how residents are trained, and thus potentially the way they interpret image information, emphasizing our need to understand how clinicians interact with the information in an image during the interpretation process. With improved understanding using tools such as eye-tracking we can develop ways to further improve decision-making and thus improve patient care.
Toward Appearance-based Gaze Estimation Open to Diverse People and Environments
Yusuke Sugano
Associate professor at the Institute of Industrial Science, The University of Tokyo
Bio:
Yusuke Sugano is an associate professor at the Institute of Industrial Science, The University of Tokyo. His research interests focus on computer vision and human-computer interaction. He received his Ph.D. in information science and technology from the University of Tokyo in 2010. He was previously an associate professor at the Graduate School of Information Science and Technology, Osaka University, a postdoctoral researcher at Max Planck Institute for Informatics, and a project research associate at the Institute of Industrial Science, the University of Tokyo..
Abstract.: Camera-based remote gaze estimation is a long-awaited and essential technology for bringing eye tracking applications into our everyday life. Appearance-based or learning-based gaze estimation techniques, which have seen dramatic advances in the computer vision community over the past decade, have the potential to turn an ordinary camera into an eye tracker. Will appearance-based gaze estimation go beyond basic research and make breakthroughs in bringing eye tracking into our daily lives? In this talk, I will review the history of appearance-based gaze estimation, introduce my recent research attempts, and consider the aspects necessary to make this technique truly open to the real world.