Meeting Banner
Abstract #3921

EMD-derived Energy-Period Profiles of Brain Networks in fMRI Resting-State Data: An Application to Parkinson’s Disease

Dietmar Cordes1,2, Muhammad Kaleem3, Zhengshi Yang1, Xiaowei Zhuang1, Tim Curran2, Karthik Sreenivasan1, Virendra Mishra1, Rajesh Nandy4, and Ryan Walsh5
1Cleveland Clinic Lou Ruvo Center for Brain Health, Las Vegas, NV, United States, 2University of Colorado, Boulder, CO, United States, 3University of Management & Technology, Lahore, Pakistan, 4University of North Texas Health Science Center, Fort Worth, TX, United States, 5Muhammad Ali Parkinson Center at Barrow Neurological Institute, Phoenix, AZ, United States

Traditionally, functional networks in resting-state data were investigated with Fourier and wavelet-related methods to characterize their frequency content. In this study, Empirical Mode Decomposition (EMD), a nonlinear method, is used to determine energy-period profiles of Intrinsic Mode Functions (IMFs) for different resting-state networks. In an application to early Parkinson’s disease (PD) vs. normal controls (NC), energy and period content were computed with EMD and compared with results using short-time Fourier transform (STFT) and maximal overlap discrete wavelet transform (MODWT) methods. Using a support vector machine, EMD achieved highest prediction accuracy in classifying NC and PD subjects among the three methods.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here