Abstract: In recent years, Independent Component Analysis (ICA) has gained significant popularity in diverse fields such as medical imaging, signal processing, and machine learning. In particular, ICA has become an important tool for identifying and characterizing brain functional networks in neuroimaging studies. Although widely applied, current 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 two new ICA models that we have developed 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 differences between 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. Computationally efficient estimation and inference procedure has been developed for the hc-ICA model. Next, I will present 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 as a mixture of independent components, the proposed DICA represents a new approach that aims to perform ICA on the distribution level. The DICA can potentially provide a unified framework to extract neural features across imaging modalities. I will discuss the connection and distinction between standard ICA and DICA. The proposed methods will be illustrated through simulation studies and real-world applications in neuroimaging studies.
Dr. Guo is an Associate Professor in the Department of Biostatistics and Bioinformatics at Emory University. She is currently serving as the Director of the Center for Biomedical Imaging Statistics (CBIS) at Emory and is an appointed Graduate Faculty of the Neuroscience Program at Emory. Dr. Guo’s research interests focus on brain network analysis, independent component analysis (ICA), multimodal neuroimaging and imaging-based prediction methods.