Adaptive Change Point Detection of Dynamic Functional Connectivity Networks

• Type of Material: Conference Paper
• Authors: Sadia Shakil, Georgia Institute of Technology; Shella Keilholz, Emory University; Chin-Hui Lee, Georgia Institute of Technology
• Language: English
• Date: 2016-01-01
• Publisher: Emory University Libraries
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2016 IEEE.
• Final Published Version (URL): http://dx.doi.org/10.1109/EMBC.2016.7590904
• Title of Journal or Parent Work: 2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)
• Conference or Event Name: 38th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)
• Volume: 2016-October
• Start Page: 1135
• End Page: 1138
• Keywords: Engineering, Biomedical; Dynamic functional connectivity; Adaptive change point detection; Engineering; Resting-state functional MRI; Technology; Science & Technology; Engineering, Electrical & Electronic
• Research Categories: Biology, Neuroscience; Engineering, Biomedical; Computer Science

Abstract

This study presents a new algorithm to adaptively detect change points of functional connectivity networks in the brain. It uses scans from resting-state functional magnetic resonance imaging (rsfMRI) which is one of the major tools to investigate intrinsic brain functionality. Different regions of the resting brain form networks that change states within a few seconds to minutes. The change points of these networks are different in normal and disordered brain functions and their understanding can help in identification of brain disorders. These changes arise from many unknown factors and extraction of these change points is one of the the major challenges in the absence of any ground truth. Our algorithm detects these change points adaptively by computing sum of absolute sign differences of adjacent images in rsfMRI scans using measures from image and video processing. We demonstrate the effectiveness of the proposed algorithm and show that these change points can be detected reliably in both task-based and resting-state networks. The outcomes also point to new directions for future work.