EEG-GRAPH

A factor-graph-based model for capturing spatial, temporal, and observational relationships in electroencephalograms

Yogatheesan Varatharajah, Min Jin Chong, Krishnakant Saboo, Brent Berry, Benjamin Brinkmann, Gregory Alan Worrell, Ravishankar Iyer

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

This paper presents a probabilistic-graphical model that can be used to infer characteristics of instantaneous brain activity by jointly analyzing spatial and temporal dependencies observed in electroencephalograms (EEG). Specifically, we describe a factor-graph-based model with customized factor-functions defined based on domain knowledge, to infer pathologic brain activity with the goal of identifying seizure-generating brain regions in epilepsy patients. We utilize an inference technique based on the graph-cut algorithm to exactly solve graph inference in polynomial time. We validate the model by using clinically collected intracranial EEG data from 29 epilepsy patients to show that the model correctly identifies seizure-generating brain regions. Our results indicate that our model outperforms two conventional approaches used for seizure-onset localization (5-7% better AUC: 0.72, 0.67, 0.65) and that the proposed inference technique provides 3-10% gain in AUC (0.72, 0.62, 0.69) compared to sampling-based alternatives.

Original languageEnglish (US)
Pages (from-to)5372-5381
Number of pages10
JournalAdvances in Neural Information Processing Systems
Volume2017-December
StatePublished - Jan 1 2017
Event31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States
Duration: Dec 4 2017Dec 9 2017

Fingerprint

Electroencephalography
Brain
Polynomials
Sampling

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

EEG-GRAPH : A factor-graph-based model for capturing spatial, temporal, and observational relationships in electroencephalograms. / Varatharajah, Yogatheesan; Chong, Min Jin; Saboo, Krishnakant; Berry, Brent; Brinkmann, Benjamin; Worrell, Gregory Alan; Iyer, Ravishankar.

In: Advances in Neural Information Processing Systems, Vol. 2017-December, 01.01.2017, p. 5372-5381.

Research output: Contribution to journalConference article

Varatharajah, Yogatheesan ; Chong, Min Jin ; Saboo, Krishnakant ; Berry, Brent ; Brinkmann, Benjamin ; Worrell, Gregory Alan ; Iyer, Ravishankar. / EEG-GRAPH : A factor-graph-based model for capturing spatial, temporal, and observational relationships in electroencephalograms. In: Advances in Neural Information Processing Systems. 2017 ; Vol. 2017-December. pp. 5372-5381.
@article{efdaf71ede9d46a08a311c58d5d72d3f,
title = "EEG-GRAPH: A factor-graph-based model for capturing spatial, temporal, and observational relationships in electroencephalograms",
abstract = "This paper presents a probabilistic-graphical model that can be used to infer characteristics of instantaneous brain activity by jointly analyzing spatial and temporal dependencies observed in electroencephalograms (EEG). Specifically, we describe a factor-graph-based model with customized factor-functions defined based on domain knowledge, to infer pathologic brain activity with the goal of identifying seizure-generating brain regions in epilepsy patients. We utilize an inference technique based on the graph-cut algorithm to exactly solve graph inference in polynomial time. We validate the model by using clinically collected intracranial EEG data from 29 epilepsy patients to show that the model correctly identifies seizure-generating brain regions. Our results indicate that our model outperforms two conventional approaches used for seizure-onset localization (5-7{\%} better AUC: 0.72, 0.67, 0.65) and that the proposed inference technique provides 3-10{\%} gain in AUC (0.72, 0.62, 0.69) compared to sampling-based alternatives.",
author = "Yogatheesan Varatharajah and Chong, {Min Jin} and Krishnakant Saboo and Brent Berry and Benjamin Brinkmann and Worrell, {Gregory Alan} and Ravishankar Iyer",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
volume = "2017-December",
pages = "5372--5381",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

TY - JOUR

T1 - EEG-GRAPH

T2 - A factor-graph-based model for capturing spatial, temporal, and observational relationships in electroencephalograms

AU - Varatharajah, Yogatheesan

AU - Chong, Min Jin

AU - Saboo, Krishnakant

AU - Berry, Brent

AU - Brinkmann, Benjamin

AU - Worrell, Gregory Alan

AU - Iyer, Ravishankar

PY - 2017/1/1

Y1 - 2017/1/1

N2 - This paper presents a probabilistic-graphical model that can be used to infer characteristics of instantaneous brain activity by jointly analyzing spatial and temporal dependencies observed in electroencephalograms (EEG). Specifically, we describe a factor-graph-based model with customized factor-functions defined based on domain knowledge, to infer pathologic brain activity with the goal of identifying seizure-generating brain regions in epilepsy patients. We utilize an inference technique based on the graph-cut algorithm to exactly solve graph inference in polynomial time. We validate the model by using clinically collected intracranial EEG data from 29 epilepsy patients to show that the model correctly identifies seizure-generating brain regions. Our results indicate that our model outperforms two conventional approaches used for seizure-onset localization (5-7% better AUC: 0.72, 0.67, 0.65) and that the proposed inference technique provides 3-10% gain in AUC (0.72, 0.62, 0.69) compared to sampling-based alternatives.

AB - This paper presents a probabilistic-graphical model that can be used to infer characteristics of instantaneous brain activity by jointly analyzing spatial and temporal dependencies observed in electroencephalograms (EEG). Specifically, we describe a factor-graph-based model with customized factor-functions defined based on domain knowledge, to infer pathologic brain activity with the goal of identifying seizure-generating brain regions in epilepsy patients. We utilize an inference technique based on the graph-cut algorithm to exactly solve graph inference in polynomial time. We validate the model by using clinically collected intracranial EEG data from 29 epilepsy patients to show that the model correctly identifies seizure-generating brain regions. Our results indicate that our model outperforms two conventional approaches used for seizure-onset localization (5-7% better AUC: 0.72, 0.67, 0.65) and that the proposed inference technique provides 3-10% gain in AUC (0.72, 0.62, 0.69) compared to sampling-based alternatives.

UR - http://www.scopus.com/inward/record.url?scp=85047017565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047017565&partnerID=8YFLogxK

M3 - Conference article

VL - 2017-December

SP - 5372

EP - 5381

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -