Improving the detection of mtbi via complexity analysis in resting - State magnetoencephalography

Marios Antonakakis, Stavros I. Dimitriadis, Andrew Papanicolaou, George Zouridakis, Michalis Zervakis

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

3 Citations (Scopus)

Abstract

Diagnosis of mild Traumatic Brain Injury (mTBI) is difficult due to the variability of obvious brain lesions using imaging scans. A promising tool for exploring potential biomarkers for mTBI is magnetoencephalography which has the advantage of high spatial and temporal resolution. By adopting proper analytic tools from the field of symbolic dynamics like Lempel-Ziv complexity, we can objectively characterize neural network alterations compared to healthy control by enumerating the different patterns of a symbolic sequence. This procedure oversimplifies the rich information of brain activity captured via MEG. For that reason, we adopted neural-gas algorithm which can transform a time series into more than two symbols by learning brain dynamics with a small reconstructed error. The proposed analysis was applied to recordings of 30 mTBI patients and 50 normal controls in δ frequency band. Our results demonstrated that mTBI patients could be separated from normal controls with more than 97% classification accuracy based on high complexity regions corresponding to right frontal areas. In addition, a reverse relation between complexity and transition rate was demonstrated for both groups. These findings indicate that symbolic complexity could have a significant predictive value in the development of reliable biomarkers to help with the early detection of mTBI.

Original languageEnglish (US)
Title of host publicationIST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages156-160
Number of pages5
ISBN (Electronic)9781509018178
DOIs
StatePublished - Nov 7 2016
Event2016 IEEE International Conference on Imaging Systems and Techniques, IST 2016 - Chania, Crete Island, Greece
Duration: Oct 4 2016Oct 6 2016

Publication series

NameIST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings

Other

Other2016 IEEE International Conference on Imaging Systems and Techniques, IST 2016
CountryGreece
CityChania, Crete Island
Period10/4/1610/6/16

Fingerprint

Brain Concussion
Magnetoencephalography
brain damage
Systems Analysis
Brain
brain
biomarkers
Biomarkers
temporal resolution
lesions
learning
spatial resolution
Gases
recording
Learning
Frequency bands
high resolution
Time series
gases
Neural networks

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Radiology Nuclear Medicine and imaging
  • Instrumentation

Cite this

Antonakakis, M., Dimitriadis, S. I., Papanicolaou, A., Zouridakis, G., & Zervakis, M. (2016). Improving the detection of mtbi via complexity analysis in resting - State magnetoencephalography. In IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings (pp. 156-160). [7738215] (IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IST.2016.7738215

Improving the detection of mtbi via complexity analysis in resting - State magnetoencephalography. / Antonakakis, Marios; Dimitriadis, Stavros I.; Papanicolaou, Andrew; Zouridakis, George; Zervakis, Michalis.

IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 156-160 7738215 (IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings).

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

Antonakakis, M, Dimitriadis, SI, Papanicolaou, A, Zouridakis, G & Zervakis, M 2016, Improving the detection of mtbi via complexity analysis in resting - State magnetoencephalography. in IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings., 7738215, IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 156-160, 2016 IEEE International Conference on Imaging Systems and Techniques, IST 2016, Chania, Crete Island, Greece, 10/4/16. https://doi.org/10.1109/IST.2016.7738215
Antonakakis M, Dimitriadis SI, Papanicolaou A, Zouridakis G, Zervakis M. Improving the detection of mtbi via complexity analysis in resting - State magnetoencephalography. In IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 156-160. 7738215. (IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings). https://doi.org/10.1109/IST.2016.7738215
Antonakakis, Marios ; Dimitriadis, Stavros I. ; Papanicolaou, Andrew ; Zouridakis, George ; Zervakis, Michalis. / Improving the detection of mtbi via complexity analysis in resting - State magnetoencephalography. IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 156-160 (IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings).
@inproceedings{c817e8cf0ef54ebd90a92c8dde24b1cd,
title = "Improving the detection of mtbi via complexity analysis in resting - State magnetoencephalography",
abstract = "Diagnosis of mild Traumatic Brain Injury (mTBI) is difficult due to the variability of obvious brain lesions using imaging scans. A promising tool for exploring potential biomarkers for mTBI is magnetoencephalography which has the advantage of high spatial and temporal resolution. By adopting proper analytic tools from the field of symbolic dynamics like Lempel-Ziv complexity, we can objectively characterize neural network alterations compared to healthy control by enumerating the different patterns of a symbolic sequence. This procedure oversimplifies the rich information of brain activity captured via MEG. For that reason, we adopted neural-gas algorithm which can transform a time series into more than two symbols by learning brain dynamics with a small reconstructed error. The proposed analysis was applied to recordings of 30 mTBI patients and 50 normal controls in δ frequency band. Our results demonstrated that mTBI patients could be separated from normal controls with more than 97{\%} classification accuracy based on high complexity regions corresponding to right frontal areas. In addition, a reverse relation between complexity and transition rate was demonstrated for both groups. These findings indicate that symbolic complexity could have a significant predictive value in the development of reliable biomarkers to help with the early detection of mTBI.",
author = "Marios Antonakakis and Dimitriadis, {Stavros I.} and Andrew Papanicolaou and George Zouridakis and Michalis Zervakis",
year = "2016",
month = "11",
day = "7",
doi = "10.1109/IST.2016.7738215",
language = "English (US)",
series = "IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "156--160",
booktitle = "IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings",
address = "United States",

}

TY - GEN

T1 - Improving the detection of mtbi via complexity analysis in resting - State magnetoencephalography

AU - Antonakakis, Marios

AU - Dimitriadis, Stavros I.

AU - Papanicolaou, Andrew

AU - Zouridakis, George

AU - Zervakis, Michalis

PY - 2016/11/7

Y1 - 2016/11/7

N2 - Diagnosis of mild Traumatic Brain Injury (mTBI) is difficult due to the variability of obvious brain lesions using imaging scans. A promising tool for exploring potential biomarkers for mTBI is magnetoencephalography which has the advantage of high spatial and temporal resolution. By adopting proper analytic tools from the field of symbolic dynamics like Lempel-Ziv complexity, we can objectively characterize neural network alterations compared to healthy control by enumerating the different patterns of a symbolic sequence. This procedure oversimplifies the rich information of brain activity captured via MEG. For that reason, we adopted neural-gas algorithm which can transform a time series into more than two symbols by learning brain dynamics with a small reconstructed error. The proposed analysis was applied to recordings of 30 mTBI patients and 50 normal controls in δ frequency band. Our results demonstrated that mTBI patients could be separated from normal controls with more than 97% classification accuracy based on high complexity regions corresponding to right frontal areas. In addition, a reverse relation between complexity and transition rate was demonstrated for both groups. These findings indicate that symbolic complexity could have a significant predictive value in the development of reliable biomarkers to help with the early detection of mTBI.

AB - Diagnosis of mild Traumatic Brain Injury (mTBI) is difficult due to the variability of obvious brain lesions using imaging scans. A promising tool for exploring potential biomarkers for mTBI is magnetoencephalography which has the advantage of high spatial and temporal resolution. By adopting proper analytic tools from the field of symbolic dynamics like Lempel-Ziv complexity, we can objectively characterize neural network alterations compared to healthy control by enumerating the different patterns of a symbolic sequence. This procedure oversimplifies the rich information of brain activity captured via MEG. For that reason, we adopted neural-gas algorithm which can transform a time series into more than two symbols by learning brain dynamics with a small reconstructed error. The proposed analysis was applied to recordings of 30 mTBI patients and 50 normal controls in δ frequency band. Our results demonstrated that mTBI patients could be separated from normal controls with more than 97% classification accuracy based on high complexity regions corresponding to right frontal areas. In addition, a reverse relation between complexity and transition rate was demonstrated for both groups. These findings indicate that symbolic complexity could have a significant predictive value in the development of reliable biomarkers to help with the early detection of mTBI.

UR - http://www.scopus.com/inward/record.url?scp=85004025603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85004025603&partnerID=8YFLogxK

U2 - 10.1109/IST.2016.7738215

DO - 10.1109/IST.2016.7738215

M3 - Conference contribution

T3 - IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings

SP - 156

EP - 160

BT - IST 2016 - 2016 IEEE International Conference on Imaging Systems and Techniques, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -