Modern Dual Optimization Methods to Medical Image Analysis: Unified Theory and High-Performance Algorithms
Dr. Yuan Jing
About the Speaker
Dr. Yuan is working as the research scientist in Robarts research institute of Western university, Canada, and the adjunct research professor in Schulich medical school, Western university. He obtained his M.Sc. from Peking University, China, and Ph.D. with excellence from the Mathematics and Computer Science Department in Heidelberg University, Germany. Before joining Robarts Research Institute, he used to work with Prof. Yuri Boykov in the Computer Science Department, Western University, Canada. He proposed a series of novel convex optimization models and developed high-performance algorithms upon modern dual optimization theories, which were implemented in parallel computing platforms and successfully applied in image processing and computer vision, especially with applications to the challenging medical image analysis in practice. He is also serving in the program committee of the top medical imaging conference of MICCAI and computer vision conference of EMMCVPR; meanwhile, as the reviewer of many top international journals and conferences: IEEE PAMI, SIAM on Imaging Sciences, IJCV, Medical Image Analysis, IEEE Trans. Med. Img., CVPR, ICCV etc. He published over 70 papers on the top journals and conferences, and managed three open-source projects.
Many problems of medical image analysis are challenging due to the associated complex optimization formulations and constraints, extremely big image data volumes to be processed, poor imaging quality, missing data etc. On the other hand, it is highly desired in clinical practices to process and analyze the acquired imaging data, for example segmentation and registration, in an automated and efficient numerical way, which motivated vast active studies during the last 30 years, in a rather broad sense, to deliver advanced mathematical analysis and develop high-performance numerical schemes. This talk targets to present an overview of modern dual optimization theories, which becomes one most successful optimization framework of image processing developed recently, with a wide spectrum of applications to medical image analysis. It focuses on the optimization problems arising from two most interesting topics: medical image segmentation and registration, and presents both analysis and high-performance numerical solutions in a unified manner in terms of dual optimization.
All are welcome！