A4 Article in conference proceedings
Dynamic Functional Connectivity Captures Individuals’ Unique Brain Signatures (2020)

Gandhi, R., Garimella, A., Toiviainen, P., & Alluri, V. (2020). Dynamic Functional Connectivity Captures Individuals’ Unique Brain Signatures. In M. Mahmud, S. Vassanelli, M. S. Kaiser, & N. Zhong (Eds.), BI 2020 : 13th International Conference on Brain Informatics, Proceedings (pp. 97-106). Springer. Lecture Notes in Computer Science, 12241. https://doi.org/10.1007/978-3-030-59277-6_9

JYU authors or editors

Publication details

All authors or editors: Gandhi, Rohan; Garimella, Arun; Toiviainen, Petri; Alluri, Vinoo

Parent publication: BI 2020 : 13th International Conference on Brain Informatics, Proceedings

Parent publication editors: Mahmud, Mufti; Vassanelli, Stefano; Kaiser, M. Shamim; Zhong, Ning


  • International Conference on Brain Informatics

Place and date of conference: Padua, Italy, 19.9.2020

ISBN: 978-3-030-59276-9

eISBN: 978-3-030-59277-6

Journal or series: Lecture Notes in Computer Science

ISSN: 0302-9743

eISSN: 1611-3349

Publication year: 2020

Number in series: 12241

Pages range: 97-106

Number of pages in the book: 378

Publisher: Springer

Place of Publication: Cham

Publication country: Switzerland

Publication language: English

DOI: https://doi.org/10.1007/978-3-030-59277-6_9

Publication open access: Not open

Publication channel open access:

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/72913


Recent neuroimaging evidence suggest that there exists a unique individual-specific functional connectivity (FC) pattern consistent across tasks. The objective of our study is to utilize FC patterns to identify an individual using a supervised machine learning approach. To this end, we use two previously published data sets that comprises resting-state and task-based fMRI responses. We use static FC measures as input to a linear classifier to evaluate its performance. We additionally extend this analysis to capture dynamic FC using two approaches: the common sliding window approach and the more recent phase synchrony-based measure. We found that the classification models using dynamic FC patterns as input outperform their static analysis counterpart by a significant margin for both data sets. Furthermore, sliding window-based analysis proved to capture more individual-specific brain connectivity patterns than phase synchrony measures for resting-state data while the reverse pattern was observed for the task-based data set. Upon investigating the effects of feature reduction, we found that feature elimination significantly improved results up to a point with near-perfect classification accuracy for the task-based data set while a gradual decrease in the accuracy was observed for resting-state data set. The implications of these findings are discussed. The results we have are promising and present a novel direction to investigate further.

Keywords: functional magnetic resonance imaging; individual; recognition; machine learning

Free keywords: fMRI; functional connectivity; classification; variance inflation factor; individual differences

Contributing organizations

Ministry reporting: Yes

Reporting Year: 2020

JUFO rating: 1

Last updated on 2021-07-07 at 21:30