Chong-Yaw Wee1,2, Pew-Thian Yap1, Dinggang Shen1,3. 1. Image Display, Enhancement, and Analysis (IDEA) Laboratory, Biomedical Research Imaging Center (BRIC) and Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina USA. 2. Department of Biomedical Engineering, Faculty of Engineering, National University of Singapore, Singapore. 3. Department of Brain and Cognitive Engineering, Korea University, Seoul, Korea.
Abstract
INTRODUCTION: Resting-state functional magnetic resonance imaging (R-fMRI) is dynamic in nature as neural activities constantly change over the time and are dominated by repeating brief activations and deactivations involving many brain regions. Each region participates in multiple brain functions and is part of various functionally distinct but spatially overlapping networks. Functional connectivity computed as correlations over the entire time series always overlooks interregion interactions that often occur repeatedly and dynamically in time, limiting its application to disease diagnosis. AIMS: We develop a novel framework that uses short-time activation patterns of brain connectivity to better detect subtle disease-induced disruptions of brain connectivity. A clustering algorithm is first used to temporally decompose R-fMRI time series into distinct clusters with similar spatial distribution of neural activity based on the assumption that functionally distinct networks should be largely temporally distinct as brain states do not simultaneously coexist in general. A Pearson correlation-based functional connectivity network is then constructed for each cluster to allow for better exploration of spatiotemporal dynamics of individual neural activity. To reduce significant intersubject variability and to remove possible spurious connections, we use a group-constrained sparse regression model to construct a backbone sparse network for each cluster and use it to weight the corresponding Pearson correlation network. RESULTS: The proposed method outperforms the conventional static, temporally dependent fully connected correlation-based networks by at least 7% on a publicly available autism dataset. We were able to reproduce similar results using data from other centers. CONCLUSIONS: By combining the advantages of temporal independence and group-constrained sparse regression, our method improves autism diagnosis.
INTRODUCTION: Resting-state functional magnetic resonance imaging (R-fMRI) is dynamic in nature as neural activities constantly change over the time and are dominated by repeating brief activations and deactivations involving many brain regions. Each region participates in multiple brain functions and is part of various functionally distinct but spatially overlapping networks. Functional connectivity computed as correlations over the entire time series always overlooks interregion interactions that often occur repeatedly and dynamically in time, limiting its application to disease diagnosis. AIMS: We develop a novel framework that uses short-time activation patterns of brain connectivity to better detect subtle disease-induced disruptions of brain connectivity. A clustering algorithm is first used to temporally decompose R-fMRI time series into distinct clusters with similar spatial distribution of neural activity based on the assumption that functionally distinct networks should be largely temporally distinct as brain states do not simultaneously coexist in general. A Pearson correlation-based functional connectivity network is then constructed for each cluster to allow for better exploration of spatiotemporal dynamics of individual neural activity. To reduce significant intersubject variability and to remove possible spurious connections, we use a group-constrained sparse regression model to construct a backbone sparse network for each cluster and use it to weight the corresponding Pearson correlation network. RESULTS: The proposed method outperforms the conventional static, temporally dependent fully connected correlation-based networks by at least 7% on a publicly available autism dataset. We were able to reproduce similar results using data from other centers. CONCLUSIONS: By combining the advantages of temporal independence and group-constrained sparse regression, our method improves autism diagnosis.
Authors: Antonio Y Hardan; Sri Muddasani; Madhuri Vemulapalli; Matcheri S Keshavan; Nancy J Minshew Journal: Am J Psychiatry Date: 2006-07 Impact factor: 18.112
Authors: Koene R A Van Dijk; Trey Hedden; Archana Venkataraman; Karleyton C Evans; Sara W Lazar; Randy L Buckner Journal: J Neurophysiol Date: 2009-11-04 Impact factor: 2.714
Authors: Jeffrey S Anderson; T Jason Druzgal; Alyson Froehlich; Molly B DuBray; Nicholas Lange; Andrew L Alexander; Tracy Abildskov; Jared A Nielsen; Annahir N Cariello; Jason R Cooperrider; Erin D Bigler; Janet E Lainhart Journal: Cereb Cortex Date: 2010-10-12 Impact factor: 5.357
Authors: Daniel A Handwerker; Vinai Roopchansingh; Javier Gonzalez-Castillo; Peter A Bandettini Journal: Neuroimage Date: 2012-07-14 Impact factor: 6.556
Authors: Lisa E Mash; Annika C Linke; Lindsay A Olson; Inna Fishman; Thomas T Liu; Ralph-Axel Müller Journal: Hum Brain Mapp Date: 2019-01-25 Impact factor: 5.038
Authors: Barnaly Rashid; Laura M E Blanken; Ryan L Muetzel; Robyn Miller; Eswar Damaraju; Mohammad R Arbabshirani; Erik B Erhardt; Frank C Verhulst; Aad van der Lugt; Vincent W V Jaddoe; Henning Tiemeier; Tonya White; Vince Calhoun Journal: Hum Brain Mapp Date: 2018-03-30 Impact factor: 5.038