Unsupervised learning of spike patterns for seizure detection and wavefront estimation of high resolution micro electrocorticographic (μ ECoG) data

Yilin Song, Yao Wang, Jonathan Viventi

Research output: Contribution to journalArticle

Abstract

For the past few years, we have developed flexible, active, and multiplexed recording devices for high resolution recording over large, clinically relevant areas in the brain. While this technology has enabled a much higher-resolution view of the electrical activity of the brain, the analytical methods to process, categorize, and respond to the huge volumes of seizure data produced by these devices have not yet been developed. In this paper, we proposed an unsupervised learning framework for spike analysis, which by itself reveals spike pattern. By applying advanced video processing techniques for separating a multi-channel recording into individual spike segments, unfolding the spike segments manifold, and identifying natural clusters for spike patterns, we are able to find the common spike motion patterns. And we further explored using these patterns for more interesting and practical problems as seizure prediction and spike wavefront prediction. These methods have been applied to in vivo feline seizure recordings and yielded promising results.

Original languageEnglish (US)
Article number7945476
Pages (from-to)418-427
Number of pages10
JournalIEEE Transactions on Nanobioscience
Volume16
Issue number6
DOIs
StatePublished - Sep 1 2017

Fingerprint

Unsupervised learning
Wavefronts
Brain
Seizures
Learning
Equipment and Supplies
Felidae
Processing
Technology

Keywords

  • Clustering
  • manifold
  • seizure detection
  • wavefront prediction

ASJC Scopus subject areas

  • Biotechnology
  • Bioengineering
  • Medicine (miscellaneous)
  • Biomedical Engineering
  • Pharmaceutical Science
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Unsupervised learning of spike patterns for seizure detection and wavefront estimation of high resolution micro electrocorticographic (μ ECoG) data. / Song, Yilin; Wang, Yao; Viventi, Jonathan.

In: IEEE Transactions on Nanobioscience, Vol. 16, No. 6, 7945476, 01.09.2017, p. 418-427.

Research output: Contribution to journalArticle

@article{f0ee925a655f4d73bf2d86b7c7de4289,
title = "Unsupervised learning of spike patterns for seizure detection and wavefront estimation of high resolution micro electrocorticographic (μ ECoG) data",
abstract = "For the past few years, we have developed flexible, active, and multiplexed recording devices for high resolution recording over large, clinically relevant areas in the brain. While this technology has enabled a much higher-resolution view of the electrical activity of the brain, the analytical methods to process, categorize, and respond to the huge volumes of seizure data produced by these devices have not yet been developed. In this paper, we proposed an unsupervised learning framework for spike analysis, which by itself reveals spike pattern. By applying advanced video processing techniques for separating a multi-channel recording into individual spike segments, unfolding the spike segments manifold, and identifying natural clusters for spike patterns, we are able to find the common spike motion patterns. And we further explored using these patterns for more interesting and practical problems as seizure prediction and spike wavefront prediction. These methods have been applied to in vivo feline seizure recordings and yielded promising results.",
keywords = "Clustering, manifold, seizure detection, wavefront prediction",
author = "Yilin Song and Yao Wang and Jonathan Viventi",
year = "2017",
month = "9",
day = "1",
doi = "10.1109/TNB.2017.2714460",
language = "English (US)",
volume = "16",
pages = "418--427",
journal = "IEEE Transactions on Nanobioscience",
issn = "1536-1241",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Unsupervised learning of spike patterns for seizure detection and wavefront estimation of high resolution micro electrocorticographic (μ ECoG) data

AU - Song, Yilin

AU - Wang, Yao

AU - Viventi, Jonathan

PY - 2017/9/1

Y1 - 2017/9/1

N2 - For the past few years, we have developed flexible, active, and multiplexed recording devices for high resolution recording over large, clinically relevant areas in the brain. While this technology has enabled a much higher-resolution view of the electrical activity of the brain, the analytical methods to process, categorize, and respond to the huge volumes of seizure data produced by these devices have not yet been developed. In this paper, we proposed an unsupervised learning framework for spike analysis, which by itself reveals spike pattern. By applying advanced video processing techniques for separating a multi-channel recording into individual spike segments, unfolding the spike segments manifold, and identifying natural clusters for spike patterns, we are able to find the common spike motion patterns. And we further explored using these patterns for more interesting and practical problems as seizure prediction and spike wavefront prediction. These methods have been applied to in vivo feline seizure recordings and yielded promising results.

AB - For the past few years, we have developed flexible, active, and multiplexed recording devices for high resolution recording over large, clinically relevant areas in the brain. While this technology has enabled a much higher-resolution view of the electrical activity of the brain, the analytical methods to process, categorize, and respond to the huge volumes of seizure data produced by these devices have not yet been developed. In this paper, we proposed an unsupervised learning framework for spike analysis, which by itself reveals spike pattern. By applying advanced video processing techniques for separating a multi-channel recording into individual spike segments, unfolding the spike segments manifold, and identifying natural clusters for spike patterns, we are able to find the common spike motion patterns. And we further explored using these patterns for more interesting and practical problems as seizure prediction and spike wavefront prediction. These methods have been applied to in vivo feline seizure recordings and yielded promising results.

KW - Clustering

KW - manifold

KW - seizure detection

KW - wavefront prediction

UR - http://www.scopus.com/inward/record.url?scp=85030113534&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030113534&partnerID=8YFLogxK

U2 - 10.1109/TNB.2017.2714460

DO - 10.1109/TNB.2017.2714460

M3 - Article

C2 - 28613179

AN - SCOPUS:85030113534

VL - 16

SP - 418

EP - 427

JO - IEEE Transactions on Nanobioscience

JF - IEEE Transactions on Nanobioscience

SN - 1536-1241

IS - 6

M1 - 7945476

ER -