The Department of Biomedical Informatics
presents
Jun Kong, PhD
Dr. Jun Kong is an Assistant Professor in the Department of Biomedical Informatics at Emory University. He received a Ph.D. degree in Electrical and Computer Engineering from Ohio State University in 2008. His research interests include pathology imaging analytics, statistical machine learning, biomedical image processing, computer-aided diagnosis, computer vision, and heterogeneous data integration and mining for oncology translational research.
“Big Data Analytics in Biomedical Imaging Research”
Monday April 20, 2015
1:00 pm - 2:30 pm
BMI Conference Room, HSC L3-045
Contact the Department of Biomedical Informatics at (631) 444-8459 with any questions regarding this event.
Bio
Jun Kong is an Assistant Professor in the Department of Biomedical Informatics and Department of Mathematics and Computer Science at Emory University. He received a Ph.D. degree in Electrical and Computer Engineering from Ohio State University in 2008. His research interests span a few key areas in bioinformatics, with special emphases on big data analytics on whole-slide pathology microcopy images, statistical machine learning, biomedical image processing, computer-aided diagnosis, computer vision, and heterogeneous data integration and mining for oncology translational research.
Abstract
In biomedical research, availability of an increasing array of high-throughput and high-resolution instruments has given rise to large datasets of imaging data - such as whole-slide histology and fluorescent microscopy imaging. These datasets provide highly detailed views of tissue structures at the cellular level and present a strong potential to revolutionize biomedical translational research. However, traditional human-based pathology review is not feasible to obtain this wealth of imaging information due to the overwhelming data scale and unacceptable inter- and intra- observer variability. In this talk, I will describe how to efficiently process digital microscopy images for highly discriminating phenotypic information with development of Computer-Aided Diagnosis (CAD) systems and big data analytical approaches for processing and managing massive in-situ micro-anatomical imaging features. Equipped with statistical machine learning techniques, these systems can automatically detect, measure, group, and classify a large scale of anatomical structures, such as cells, from microscopy images of histological specimens to support higher-level diagnosis and follow-up scientific investigations. I will also illustrate my work on geometric model fitting where a new ellipse-fitting framework tied to statistical models is developed to represent common biological objects in numerous biomedical studies. Additionally, I will also present two funded 3D microscopy image analysis projects on tumor cell migration investigation and liver vessel reconstruction, respectively, where a new geometric active contour formulation is proposed to segment a large amount of pathological objects and structures of interest. The ultimate goal of these research efforts is to develop a suite of cloud based pathology imaging analytics algorithms to support efficient image analysis and spatial analytics of large-scale 3D pathology image data volumes.