Brain fingerprinting using EEG graph inference

Maliheh Miri; Vahid Abootalebi; Enrico Amico; Hamid Saeedi-Sourck; Dimitri Van De Ville; Hamid Behjat

doi:10.1101/2023.03.11.532201

Brain fingerprinting using EEG graph inference

Maliheh Miri, Vahid Abootalebi, Enrico Amico, Hamid Saeedi-Sourck, Dimitri Van De Ville, Hamid Behjat

Mathematics

Research output: Working paper/Preprint › Preprint

Abstract

Taking advantage of the human brain functional connectome as an individual’s fingerprint has attracted great research in recent years. Conventionally, Pearson correlation between regional time-courses is used as a pairwise measure for each edge weight of the connectome. Building upon recent advances in graph signal processing, we propose here to estimate the graph structure as a whole by considering all time-courses at once. Using data from two publicly available datasets, we show the superior performance of such learned brain graphs over correlation-based functional connectomes in characterizing an individual.

Original language	English
Publisher	bioRxiv
DOIs	https://doi.org/10.1101/2023.03.11.532201
Publication status	Published - 18 Jun 2023

Access to Document

10.1101/2023.03.11.532201Licence: Creative Commons: Attribution-NonCommercial-NoDerivs (CC BY-NC-ND)

1 Conference contribution

Brain fingerprinting using EEG graph inference
Miri, M., Abootalebi, V., Amico, E., Saeedi-Sourck, H., Van De Ville, D. & Behjat, H., 1 Nov 2023, 2023 31st European Signal Processing Conference (EUSIPCO). IEEE, p. 1025-1029 5 p. (European Signal Processing Conference).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Cite this

@techreport{e36f2e15d7fb4969a80faa63828e7660,

title = "Brain fingerprinting using EEG graph inference",

abstract = "Taking advantage of the human brain functional connectome as an individual{\textquoteright}s fingerprint has attracted great research in recent years. Conventionally, Pearson correlation between regional time-courses is used as a pairwise measure for each edge weight of the connectome. Building upon recent advances in graph signal processing, we propose here to estimate the graph structure as a whole by considering all time-courses at once. Using data from two publicly available datasets, we show the superior performance of such learned brain graphs over correlation-based functional connectomes in characterizing an individual.",

author = "Maliheh Miri and Vahid Abootalebi and Enrico Amico and Hamid Saeedi-Sourck and {Van De Ville}, Dimitri and Hamid Behjat",

year = "2023",

month = jun,

day = "18",

doi = "10.1101/2023.03.11.532201",

language = "English",

publisher = "bioRxiv",

type = "WorkingPaper",

institution = "bioRxiv",

}

TY - UNPB

T1 - Brain fingerprinting using EEG graph inference

AU - Miri, Maliheh

AU - Abootalebi, Vahid

AU - Amico, Enrico

AU - Saeedi-Sourck, Hamid

AU - Van De Ville, Dimitri

AU - Behjat, Hamid

PY - 2023/6/18

Y1 - 2023/6/18

N2 - Taking advantage of the human brain functional connectome as an individual’s fingerprint has attracted great research in recent years. Conventionally, Pearson correlation between regional time-courses is used as a pairwise measure for each edge weight of the connectome. Building upon recent advances in graph signal processing, we propose here to estimate the graph structure as a whole by considering all time-courses at once. Using data from two publicly available datasets, we show the superior performance of such learned brain graphs over correlation-based functional connectomes in characterizing an individual.

AB - Taking advantage of the human brain functional connectome as an individual’s fingerprint has attracted great research in recent years. Conventionally, Pearson correlation between regional time-courses is used as a pairwise measure for each edge weight of the connectome. Building upon recent advances in graph signal processing, we propose here to estimate the graph structure as a whole by considering all time-courses at once. Using data from two publicly available datasets, we show the superior performance of such learned brain graphs over correlation-based functional connectomes in characterizing an individual.

U2 - 10.1101/2023.03.11.532201

DO - 10.1101/2023.03.11.532201

M3 - Preprint

BT - Brain fingerprinting using EEG graph inference

PB - bioRxiv

ER -

Brain fingerprinting using EEG graph inference

Abstract

Access to Document

Fingerprint

Research output

Brain fingerprinting using EEG graph inference

Cite this