报告题目：Bayesian Models on Manifolds for Image Registration and Statistical Shape Analysis
报告人：张妙妙 博士 （MIT）
主持人：沈超敏 副教授
时间：2016年5月23日（周一）上午10:00 – 11:00
地点：信息楼133（闵行校区）

报告摘要：
Investigating clinical hypotheses of diseases and their potential therapeutic implications based on large medical image collections is an important research area in medical imaging. The use of medical images provides clinicians an insightabout anatomical changes caused by diseases; hence is critical to disease diagnosis and treatment planning. However, characterization of the anatomical changes poses computational and statistical challenges due to the high-dimensional and nonlinear nature of the data, as well as a vast number of unknown model parameters. In this talk, I will present efficient, robust, and reliable methods to address these problems. My approach entails creating (i) an efficient image registration approach for deriving anatomical shapes from the large-scale image database, and (ii) novel Bayesian machine learning methods for analyzing the intrinsic variability of high-dimensional manifold-valued data with automatic dimensionality reduction and parameter estimation. The potential practical applications of this work beyond medical imaging include machine learning, computer vision, and computer graphics.

报告人简介：
Miaomiao Zhang is a postdoctoral associate in Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT. She completed her PhD in the Computer Science Department at University of Utah and MS at East China Normal University. Her research work focuses on developing novel models at the intersection of statistics, mathematics, and computer engineering in the field of medical and biological imaging. Miaomiao Zhang received the Young Scientist Award at the 2014 Medical Image Computing and Computer-Assisted Intervention (MICCAI). She will be joining Computer Science department in Lehigh University as a tenure-track assistant professor Fall 2017.