Seminar

 
Abstract:
A Quantitative Imaging Biomarkers (QIB) is an objective characteristic derived from an in vivo image measured on a ratio or interval scale as indicators of normal biological processes, pathogenic processes or a response to a therapeutic intervention. The advantage of QIB’s over qualitative imaging biomarkers is that they are better suited to be used for follow-up of patients or in clinical trials.
In this talk I will introduce image segmentation and registration techniques, and their application for supporting quantification, treatment planning and surgery simulation. First, model-based segmentation techniques for extracting bone and soft tissues in CT and MR images are shown. Second, improved CV and graph-cut based segmentation techniques are introduced for solving several difficulties of original methods and for extracting lung tumors in chest CT images. Finally, rigid and non-rigid registration techniques are introduced for matching corresponding pulmonary nodules in follow-up CT images and analyzing lung motion in respiratory chest CT images.
 
Bio:
Helen Hong received BS degree (1994), MS degree (1996) and PhD degree (2001) in Computer Engineering at the Ewha Womans University, Seoul, Korea. From 2001 to 2003, she was at the Seoul National University as a post doctor. In 2003, she was at the INFINITT Co. Ltd. as a principal researcher. From 2003 to 2005, she was at the Seoul National University as a research professor. Since 2006, she is a professor in the Department of Software Convergence at the Seoul Women’s University, Seoul, Korea. Her current research interests include medical image analysis, image segmentation and registration.