A model for classification based on the functional connectivity pattern dynamics of the brain

Regina Meszlenyi, Ladislav Peska, Viktor Gal, Z. Vidnyánszky, Krisztian Buza

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Synchronized spontaneous low frequency fluctuations of the so called BOLD signal, as measured by functional Magnetic Resonance Imaging (fMRI), are known to represent the functional connections of different brain areas. Dynamic Time Warping (DTW) distance can be used as a similarity measure between BOLD signals of brain regions as an alternative of the traditionally used correlation coefficient and the usage of the DTW algorithm has further advantages: Beside the DTW distance, the algorithm generates the warping path, i.e. the time-delay function between the compared two time-series. In this paper, we propose to use the relative length of the warping path as classification feature and demonstrate that the warping path itself carries important information when classifying patients according to cannabis addiction. We discuss biomedical relevance of our findings as well.

Original languageEnglish
Title of host publicationProceedings - 2016 3rd European Network Intelligence Conference, ENIC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages203-208
Number of pages6
ISBN (Electronic)9781509034550
DOIs
Publication statusPublished - Jan 31 2017
Event3rd European Network Intelligence Conference, ENIC 2016 - Wroclaw, Poland
Duration: Sep 5 2016Sep 7 2016

Other

Other3rd European Network Intelligence Conference, ENIC 2016
CountryPoland
CityWroclaw
Period9/5/169/7/16

Fingerprint

Brain
brain
Time series
Time delay
addiction
fluctuation
time series
Cannabis
Magnetic Resonance Imaging
time

Keywords

  • classification
  • dynamic time warping
  • fMRI
  • functional connectivity patterns
  • warping path

ASJC Scopus subject areas

  • Communication
  • Artificial Intelligence
  • Computer Networks and Communications
  • Social Psychology

Cite this

Meszlenyi, R., Peska, L., Gal, V., Vidnyánszky, Z., & Buza, K. (2017). A model for classification based on the functional connectivity pattern dynamics of the brain. In Proceedings - 2016 3rd European Network Intelligence Conference, ENIC 2016 (pp. 203-208). [7838066] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ENIC.2016.037

A model for classification based on the functional connectivity pattern dynamics of the brain. / Meszlenyi, Regina; Peska, Ladislav; Gal, Viktor; Vidnyánszky, Z.; Buza, Krisztian.

Proceedings - 2016 3rd European Network Intelligence Conference, ENIC 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 203-208 7838066.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Meszlenyi, R, Peska, L, Gal, V, Vidnyánszky, Z & Buza, K 2017, A model for classification based on the functional connectivity pattern dynamics of the brain. in Proceedings - 2016 3rd European Network Intelligence Conference, ENIC 2016., 7838066, Institute of Electrical and Electronics Engineers Inc., pp. 203-208, 3rd European Network Intelligence Conference, ENIC 2016, Wroclaw, Poland, 9/5/16. https://doi.org/10.1109/ENIC.2016.037
Meszlenyi R, Peska L, Gal V, Vidnyánszky Z, Buza K. A model for classification based on the functional connectivity pattern dynamics of the brain. In Proceedings - 2016 3rd European Network Intelligence Conference, ENIC 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 203-208. 7838066 https://doi.org/10.1109/ENIC.2016.037
Meszlenyi, Regina ; Peska, Ladislav ; Gal, Viktor ; Vidnyánszky, Z. ; Buza, Krisztian. / A model for classification based on the functional connectivity pattern dynamics of the brain. Proceedings - 2016 3rd European Network Intelligence Conference, ENIC 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 203-208
@inproceedings{0fd3311d1163486d843550d5cc01674d,
title = "A model for classification based on the functional connectivity pattern dynamics of the brain",
abstract = "Synchronized spontaneous low frequency fluctuations of the so called BOLD signal, as measured by functional Magnetic Resonance Imaging (fMRI), are known to represent the functional connections of different brain areas. Dynamic Time Warping (DTW) distance can be used as a similarity measure between BOLD signals of brain regions as an alternative of the traditionally used correlation coefficient and the usage of the DTW algorithm has further advantages: Beside the DTW distance, the algorithm generates the warping path, i.e. the time-delay function between the compared two time-series. In this paper, we propose to use the relative length of the warping path as classification feature and demonstrate that the warping path itself carries important information when classifying patients according to cannabis addiction. We discuss biomedical relevance of our findings as well.",
keywords = "classification, dynamic time warping, fMRI, functional connectivity patterns, warping path",
author = "Regina Meszlenyi and Ladislav Peska and Viktor Gal and Z. Vidny{\'a}nszky and Krisztian Buza",
year = "2017",
month = "1",
day = "31",
doi = "10.1109/ENIC.2016.037",
language = "English",
pages = "203--208",
booktitle = "Proceedings - 2016 3rd European Network Intelligence Conference, ENIC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A model for classification based on the functional connectivity pattern dynamics of the brain

AU - Meszlenyi, Regina

AU - Peska, Ladislav

AU - Gal, Viktor

AU - Vidnyánszky, Z.

AU - Buza, Krisztian

PY - 2017/1/31

Y1 - 2017/1/31

N2 - Synchronized spontaneous low frequency fluctuations of the so called BOLD signal, as measured by functional Magnetic Resonance Imaging (fMRI), are known to represent the functional connections of different brain areas. Dynamic Time Warping (DTW) distance can be used as a similarity measure between BOLD signals of brain regions as an alternative of the traditionally used correlation coefficient and the usage of the DTW algorithm has further advantages: Beside the DTW distance, the algorithm generates the warping path, i.e. the time-delay function between the compared two time-series. In this paper, we propose to use the relative length of the warping path as classification feature and demonstrate that the warping path itself carries important information when classifying patients according to cannabis addiction. We discuss biomedical relevance of our findings as well.

AB - Synchronized spontaneous low frequency fluctuations of the so called BOLD signal, as measured by functional Magnetic Resonance Imaging (fMRI), are known to represent the functional connections of different brain areas. Dynamic Time Warping (DTW) distance can be used as a similarity measure between BOLD signals of brain regions as an alternative of the traditionally used correlation coefficient and the usage of the DTW algorithm has further advantages: Beside the DTW distance, the algorithm generates the warping path, i.e. the time-delay function between the compared two time-series. In this paper, we propose to use the relative length of the warping path as classification feature and demonstrate that the warping path itself carries important information when classifying patients according to cannabis addiction. We discuss biomedical relevance of our findings as well.

KW - classification

KW - dynamic time warping

KW - fMRI

KW - functional connectivity patterns

KW - warping path

UR - http://www.scopus.com/inward/record.url?scp=85014357908&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014357908&partnerID=8YFLogxK

U2 - 10.1109/ENIC.2016.037

DO - 10.1109/ENIC.2016.037

M3 - Conference contribution

AN - SCOPUS:85014357908

SP - 203

EP - 208

BT - Proceedings - 2016 3rd European Network Intelligence Conference, ENIC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -