学　术

　　题　目：A Manifold-based Framework to Highly Accelerated Dynamic Magnetic Resonance Imaging

　　时　间：2019年1月14日（周一）10:00

　　地　点：清水河校区科研楼B108

　　主讲人：纽约州立大学布法罗分校　应蕾 教授

　　主要内容：

　　Magnetic Resonance Imaging (MRI) is well known to be slow in data acquisition, which limits imaging of moving organs and causes patient discomfort. Because the MRI acquisition time is directly related to the amount of data to be acquired, to address this issue of acquisition speed, mathematical models and algorithms have been developed to allow the MR images to be reconstructed from data acquired far below the Nyquist rate.Sparsity and low-rank models have been successfully used for fast imaging.  Here we will introduce a new manifold framework which extends the existing models to more general ones. Specifically, the MR image series/patches are assumed to be on a smooth manifold, and the underlying manifold geometry is learned through training data. Moreover, low-dimensional embeddings which preserve the learned manifold geometry and effect parsimonious data representations are computed. Capitalizing on the learned manifold geometry, computational algorithms are introduced to reconstruct dynamic MR images from highly undersampled k-space data. Some examples on phantom and in-vivo data sets will be presented.

　　主讲人简介：

　　Leslie Ying received her B.E. in Electronics Engineering from Tsinghua University, China in 1997 and both her M.S. and Ph.D. in Electrical Engineering from the University of Illinois at Urbana - Champaign in 1999 and 2003, respectively. She was an Assistant and then Associate Professor of Electrical Engineering and Computer Science at the University of Wisconsin - Milwaukee (UWM) from 2003 to 2011. She was an Assistant and then Associate Professor of Electrical Engineering and Computer Science at the University of Wisconsin - Milwaukee (UWM) from 2003 to 2011. She joined the University at Buffalo in Spring 2012 and is currently a full professor of Biomedical Engineering and Electrical Engineering there. Her research interests include magnetic resonance imaging, compressed sensing, image reconstruction, and machine learning. She received a CAREER award from the National Science Foundation in 2009. Dr. Ying has three issued US utility patents and one pending patent. She served as an Associate Editor of IEEE Transactions on Biomedical Engineering and was on the Administrative Committee of IEEE Engineering in Medicine and Biology Society and the Steering Committee of IEEE Transactions on Medical Imaging. She is now a Deputy Editor of Magnetic Resonance in Medicine and an editorial board member of Scientific Reports.

　　　　　　　　　　　　　　　　　　　　　信息与通信工程学院

　　　　　　　　　　　　　　　　　　　　　　 2019年1月8日