随机复杂结构与数据科学重点实验室
学术报告


浏览次数:

 
Speaker:

Dr.Xinyuan Song,Department of Statistics,The Chinese University of Hong Kong

Inviter: 孙六全 研究员
Title:
Big data analytics with applications in medical research
Time & Venue:

2019.7.1 15:00 N702

Abstract:

Medical imaging data have been widely used in modern health care, particularly in the prognosis, screening, diagnosis, and treatment of various diseases. This talk introduces novel statistical models for analyzing ultrahigh dimensional imaging data in the presence of latent variables and nonignorable missing data. Scalar- and latent factor-on-image regression models that regress a scalar/latent factor on ultrahigh dimensional imaging covariates are considered. We propose a two-stage approach for statistical inference. In the first stage, an efficient functional principle component analysis method is used to reduce the dimension and extract useful features/eigenimages. In the second stage, a joint modeling approach is proposed to conduct regression analysis with extracted eigenimages. A fully Bayesian method with an adjust spike-and-slab absolute shrinkage and selection operator (lasso) procedure is developed for the estimation and selection of influential features/eigenimages. Applications to medical research, such as discovery of associations between cognitive decline and magnetic resonance images for patients with Alzheimer's disease, are presented.

Affiliation:  

学术报告中国科学院数学与系统科学研究院应用数学研究所
地址 北京市海淀区中关村东路55号 思源楼6-7层 南楼5-6、8层 100190
?2000-2013 京ICP备05058656号