Distinguished Lecturer Series
University of Maryland College Park
Improving Medicine, Saving Lives: Developing Visual Computing Technologies for Health Care
Large-scale healthcare datasets are poised to transform how we approach medicine. Multidimensional medical datasets need new tools to identify disease subtypes and patterns of disease progression across diverse biomarkers, outcomes, and demographic subgroups. Conducting longitudinal studies of multidimensional data is challenging because of the limited human capacity to comprehend the subtle patterns as well as numerous interactions among a large number of variables. The immense cognitive load of such complex tasks often causes these analyses to be time-consuming and ineffective.
In this talk, I will present a number of applications in medicine and healthcare in which we are finding that visual computing is enhancing our understanding and providing new insights. I will present an overview of Winnow, a tool to help elucidate and interpret inter-relationships between a broad range of outcome measures and patient subgroups for Parkinson’s disease that we have developed in a close collaboration with clinical scientists.
Designing volume visualizations showing various structures of interest is critical to the exploratory analysis of volumetric data. I will also present our recent work on using information-theoretic measures as well as deep-learning-assisted volume visualization to depict complex structures, which are otherwise challenging for conventional approaches. In collaboration with radiologists at our Medical School we have built interactive visual computing tools for visualization of diffusion kurtosis imaging (DKI) datasets. Inspired by lighting in computer games, our research explores the use of spherical harmonics illumination with DKI to better depict changes in the brain microstructure in and around severe to mild traumatic brain injuries, frontal lobe damage, and tumors.
I will conclude my talk by presenting some of our ongoing research in facilitating new health care discoveries using virtual and augmented reality for surgical resident training, augmented reality for ultrasound, and portable multi-camera arrays for advanced telemedicine.
Amitabh Varshney is the Interim Vice President for Research and Professor of Computer Science at the University of Maryland at College Park. Varshney’s research focus is on exploring the applications of high-performance computing and visualization in engineering, science, and medicine. He has worked on a number of research areas including visual saliency, summarization of large visual datasets, and visual computing for big data. He is currently exploring applications of virtual and augmented reality in several applications, including healthcare and telemedicine. He has served in various roles in the IEEE Visualization and Graphics Technical Committee, including as its Chair, 2008–2012. He received the IEEE Visualization Technical Achievement Award in 2004. He is a Fellow of IEEE