Invited talk by Dr. Kevin Zhou: Medical Image Detection, Segmentation, and Parsing: Machine Learning and Multiple Object Perspectives

Speaker: Dr. Kevin Zhou Date: Thursday, December 11, 2014 Time: 15:00-16:00 Location: Media room 00.13.009A, TUM Informatics Faculty, Garching

Abstract

Although medical image detection and segmentation has been actively studied over the past two decades, conventional methods mostly focus on detection and segmentation algorithms for a single object typically with some manual inputs. Recently with the availability of large datasets and the advance of statistical machine learning, a new trend that goes beyond the conventional wisdom has emerged, that is , fully automatic approaches for recognizing or detecting multiple objects from an image and further parsing or segmenting a medical image into a cohort of anatomical structures have gained more prevalence in the literature. In this talk, I will introduce research challenges in designing such algorithms and present our machine learning based methods that leverage anatomical context embedded in the medical images for efficient and effective medical image parsing, along with demonstrations of real product contributions.

Bio

Dr. S. Kevin Zhou obtained his Ph.D. degree in Electrical Engineering from University of Maryland and is currently a Principal Key Expert of Whole Body Image Analytics at Siemens Corporate Technology, dedicated to researching and developing innovative solutions for medical and industrial imaging products. His research interests lie in computer vision and machine learning and their applications to medical image recognition and parsing, face recognition and modeling, etc. Dr. Zhou has published over 150 book chapters and peer-reviewed journal and conference papers, has registered over 200 patents and inventions, has written two research monographs, and has edited two books. In addition, he has actively served the community via being area chair and program committee member for premier computer vision and medical imaging conferences, giving three tutorial talks, and organizing two workshops. Dr. Zhou has won multiple awards honoring his publications, patents and products, including two Best Paper Awards (Medical Computer Vision 2010 and High-Performance Medical Image Computing for Image-Assisted Clinical Intervention and Decision-Making 2010), Runner-Up Award from Prostate MR Image Segmentation Challenge (2012), Thomas Alva Edison Patent Award (2013) from NJ R&D Council, two Johnson & Johnson Supplier Enable Innovation (SEI) Awards (2013), R&D 100 Award or Oscar of invention (2014), and Siemens Inventor of the Year (2104).