Loading...

Extraction and automatic grouping of joint and individual sources in multi-subject fMRI data using higher order cumulants

Pakravan, M ; Sharif University of Technology | 2018

903 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/JBHI.2018.2840085
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2018
  4. Abstract:
  5. The joint analysis of multiple datasets to extract their interdependency information has wide applications in biomedical and health informatics. In this paper, we propose an algorithm to extract joint and individual sources of multi-subject datasets by using a deflation based procedure, which is referred to as joint/individual thin independent component analysis (JI-ThICA). The proposed algorithm is based on two cost functions utilizing higher order cumulants to extract joint and individual sources. Joint sources are discriminated by fusing signals of all subjects, whereas individual sources are extracted separately for each subject. Furthermore, JI-ThICA algorithm estimates the number of joint sources by applying a simple and efficient strategy to determine the type of sources (joint or individual). The algorithm also categorizes similar sources automatically across datasets through an optimization process. The proposed algorithm is evaluated by analyzing simulated functional Magnetic Resonance Imaging (fMRI) multi-subject datasets, and its performance is compared with existing alternatives. We investigate clean and noisy fMRI signals and consider two source models. Our results reveal that the proposed algorithm outperforms its alternatives in terms of the mean joint Signal to Interference Ratio (jSIR). We also apply the proposed algorithm on a public-available real fMRI multi-subject dataset, which was acquired during naturalistic auditory experience. The extracted results are in accordance with the previous studies on naturalistic audio listening and results of a recent study investigated this dataset, which demonstrates that the JI-ThICA algorithm can be applied to extract reliable and meaningful information from multi-subject fMRI data. IEEE
  6. Keywords:
  7. Analytical models ; Biological system modeling ; Correlation ; Functional magnetic resonance imaging ; Functional magnetic resonance imaging (fMRI) ; Joint and individual source extraction ; Multi-subject data analysis ; Noise measurement ; Signal processing algorithms ; Thin independent component analysis (Thin ICA) ; Cost functions ; Extraction ; Independent component analysis ; Magnetic resonance imaging ; Signal systems ; Brain signals ; Efficient strategy ; Health informatics ; Higher order cumulants ; Signal to interference ratio ; Source extraction ; Functional neuroimaging ; Adult ; Article ; Biology ; Brain ; Controlled study ; Data analysis ; Data mining ; Female ; Human ; Human experiment ; Joint ; Male ; Signal processing ; Simulation
  8. Source: IEEE Journal of Biomedical and Health Informatics ; 24 May , 2018 ; 21682194 (ISSN)
  9. URL: https://ieeexplore.ieee.org/document/8364536