Biostatistics Weekly Seminar

New ICA methods for brain network analysis using neuroimaging data

Ying Guo, PhD

Director, Center for Biomedical Imaging Statistics (CBIS)
Department of Biostatistics and Bioinformatics
Rollins School of Public Health
Emory University

In recent years, Independent Component Analysis (ICA) has gained significant popularity in diverse fields such as medical imaging, signal processing, and machine learning. In neuroscience, ICA has become an important tool for identifying and characterizing brain functional networks using neuroimaging data. Although widely applied, existing ICA methods have several limitations that reduce their applicability in imaging studies. First, an important goal in imaging data analysis is to investigate how brain functional networks are affected by subjects’ clinical and demographic characteristics. Existing ICA methods, however, cannot directly incorporate covariate effects in ICA decomposition. Secondly, the collection of multimodal neuroimaging (e.g. fMRI and DTI) has become common practice in the neuroscience community. But current ICA methods are not flexible to accommodate multimodal imaging data that have different scales and data representations (scalar/array/matrix). In this talk, I am going to present new ICA models that aim to extend the ICA methodology to address these needs in neuroimaging applications. I will first introduce a hierarchical covariate-adjusted ICA (hc-ICA) model that provides a formal statistical framework for estimating covariate effects and testing group differences in brain functional networks. hc-ICA provides a more reliable and powerful statistical tool for evaluating group differences in brain functional networks while appropriately controlling for potential confounding factors. I will present computationally efficient estimation and inference procedure for hc-ICA. A GUI-based Matlab toolbox HINT (Hierarchical INdependent component analysis Toolbox) has been developed for implementing hc-ICA. Next, I will introduce a novel Distributional Independent Component Analysis (DICA) framework for decomposing neuroimaging from diverse modalities such as fMRI and DTI. Unlike traditional ICA which separates observed data, the proposed DICA aims to perform ICA on the distribution level. The DICA can potentially provide a unified framework to extract neural features across imaging modalities. The connection and distinction between standard ICA and DICA will be discussed. The proposed methods will be illustrated through simulation studies and real-world applications in neuroimaging studies.

MRBIII, Room 1220
27 February 2019

Speaker Itinerary

Topic revision: r6 - 19 Mar 2019, SrKrueger

This site is powered by FoswikiCopyright © 2013-2020 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Vanderbilt Biostatistics Wiki? Send feedback