报告人：Jinyi Qi，Professor，UC Davis
报告摘要：PET is a highly sensitive molecular imaging modality that is widely used in oncology, neurology, and biological research. It is capable of monitoringe the spatiotemporal distribution of radiotracers without any mechanical or electronic scanning. Thus PET data is intrinsically dynamic and the temporal resolution is only limited by the counting statistics. In this talk I will describe our work on applying kernel learning to dynamic PET image reconstruction to reduce statistical noise and hence to improve temporal resolution as well as to reduce radiation dose. I will first cover the basic concept of kernel based PET image reconstruction and then explain how to incorporate anatomical information into the kernel framework. Finally, I will introduce our recent work on the extension of the kernel method to direct parametric reconstruction using both simplified linear model and compartment models.
报告人简介：Jinyi Qi is a Professor in the Department of Biomedical Engineering at the University of California - Davis (UC Davis). He received his B.S. degree from Tsinghua University and M.S. and Ph.D. degrees from the University of Southern California (USC). He was a Research Scientist at the Lawrence Berkeley National Laboratory before joining the faculty of UC Davis in 2004. He was the interim Chair of the Department of Biomedical Engineering at UC Davis from 2015 to 2016. Dr. Qi is an Associate Editor of IEEE Transactions of Medical Imaging. He received the IEEE NMIS Young Investigator Medical Image Science Award in 2001 and IEEE NPSS Early Achievement Award in 2009. He is a Fellow of AIMBE and IEEE. His research interests include statistical image reconstruction, medical image processing, image quality evaluation, and imaging system optimization.