A hierarchical approach for online temporal lobe seizure detection in long-term intracranial EEG recordings

Sheng Fu Liang, Yi Chun Chen, Yu Lin Wang, Pin Tzu Chen, Chia Hsiang Yang, Herming Chiueh

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Objective. Around 1% of the world's population is affected by epilepsy, and nearly 25% of patients cannot be treated effectively by available therapies. The presence of closed-loop seizure-triggered stimulation provides a promising solution for these patients. Realization of fast, accurate, and energy-efficient seizure detection is the key to such implants. In this study, we propose a two-stage on-line seizure detection algorithm with low-energy consumption for temporal lobe epilepsy (TLE). Approach. Multi-channel signals are processed through independent component analysis and the most representative independent component (IC) is automatically selected to eliminate artifacts. Seizure-like intracranial electroencephalogram (iEEG) segments are fast detected in the first stage of the proposed method and these seizures are confirmed in the second stage. The conditional activation of the second-stage signal processing reduces the computational effort, and hence energy, since most of the non-seizure events are filtered out in the first stage. Main results. Long-term iEEG recordings of 11 patients who suffered from TLE were analyzed via leave-one-out cross validation. The proposed method has a detection accuracy of 95.24%, a false alarm rate of 0.09/h, and an average detection delay time of 9.2 s. For the six patients with mesial TLE, a detection accuracy of 100.0%, a false alarm rate of 0.06/h, and an average detection delay time of 4.8 s can be achieved. The hierarchical approach provides a 90% energy reduction, yielding effective and energy-efficient implementation for real-time epileptic seizure detection. Significance. An on-line seizure detection method that can be applied to monitor continuous iEEG signals of patients who suffered from TLE was developed. An IC selection strategy to automatically determine the most seizure-related IC for seizure detection was also proposed. The system has advantages of (1) high detection accuracy, (2) low false alarm, (3) short detection latency, and (4) energy-efficient design for hardware implementation.

Original languageEnglish
Article number045004
JournalJournal of Neural Engineering
Volume10
Issue number4
DOIs
Publication statusPublished - 2013 Aug 1

Fingerprint

Temporal Lobe
Electroencephalography
Seizures
Temporal Lobe Epilepsy
Time delay
Independent component analysis
Signal processing
Energy utilization
Chemical activation
Hardware
Epilepsy
Electrocorticography
Artifacts
Population

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Cellular and Molecular Neuroscience

Cite this

@article{ab34a9e4d50843fd957d5d446a8cdaad,
title = "A hierarchical approach for online temporal lobe seizure detection in long-term intracranial EEG recordings",
abstract = "Objective. Around 1{\%} of the world's population is affected by epilepsy, and nearly 25{\%} of patients cannot be treated effectively by available therapies. The presence of closed-loop seizure-triggered stimulation provides a promising solution for these patients. Realization of fast, accurate, and energy-efficient seizure detection is the key to such implants. In this study, we propose a two-stage on-line seizure detection algorithm with low-energy consumption for temporal lobe epilepsy (TLE). Approach. Multi-channel signals are processed through independent component analysis and the most representative independent component (IC) is automatically selected to eliminate artifacts. Seizure-like intracranial electroencephalogram (iEEG) segments are fast detected in the first stage of the proposed method and these seizures are confirmed in the second stage. The conditional activation of the second-stage signal processing reduces the computational effort, and hence energy, since most of the non-seizure events are filtered out in the first stage. Main results. Long-term iEEG recordings of 11 patients who suffered from TLE were analyzed via leave-one-out cross validation. The proposed method has a detection accuracy of 95.24{\%}, a false alarm rate of 0.09/h, and an average detection delay time of 9.2 s. For the six patients with mesial TLE, a detection accuracy of 100.0{\%}, a false alarm rate of 0.06/h, and an average detection delay time of 4.8 s can be achieved. The hierarchical approach provides a 90{\%} energy reduction, yielding effective and energy-efficient implementation for real-time epileptic seizure detection. Significance. An on-line seizure detection method that can be applied to monitor continuous iEEG signals of patients who suffered from TLE was developed. An IC selection strategy to automatically determine the most seizure-related IC for seizure detection was also proposed. The system has advantages of (1) high detection accuracy, (2) low false alarm, (3) short detection latency, and (4) energy-efficient design for hardware implementation.",
author = "Liang, {Sheng Fu} and Chen, {Yi Chun} and Wang, {Yu Lin} and Chen, {Pin Tzu} and Yang, {Chia Hsiang} and Herming Chiueh",
year = "2013",
month = "8",
day = "1",
doi = "10.1088/1741-2560/10/4/045004",
language = "English",
volume = "10",
journal = "Journal of Neural Engineering",
issn = "1741-2560",
publisher = "IOP Publishing Ltd.",
number = "4",

}

A hierarchical approach for online temporal lobe seizure detection in long-term intracranial EEG recordings. / Liang, Sheng Fu; Chen, Yi Chun; Wang, Yu Lin; Chen, Pin Tzu; Yang, Chia Hsiang; Chiueh, Herming.

In: Journal of Neural Engineering, Vol. 10, No. 4, 045004, 01.08.2013.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A hierarchical approach for online temporal lobe seizure detection in long-term intracranial EEG recordings

AU - Liang, Sheng Fu

AU - Chen, Yi Chun

AU - Wang, Yu Lin

AU - Chen, Pin Tzu

AU - Yang, Chia Hsiang

AU - Chiueh, Herming

PY - 2013/8/1

Y1 - 2013/8/1

N2 - Objective. Around 1% of the world's population is affected by epilepsy, and nearly 25% of patients cannot be treated effectively by available therapies. The presence of closed-loop seizure-triggered stimulation provides a promising solution for these patients. Realization of fast, accurate, and energy-efficient seizure detection is the key to such implants. In this study, we propose a two-stage on-line seizure detection algorithm with low-energy consumption for temporal lobe epilepsy (TLE). Approach. Multi-channel signals are processed through independent component analysis and the most representative independent component (IC) is automatically selected to eliminate artifacts. Seizure-like intracranial electroencephalogram (iEEG) segments are fast detected in the first stage of the proposed method and these seizures are confirmed in the second stage. The conditional activation of the second-stage signal processing reduces the computational effort, and hence energy, since most of the non-seizure events are filtered out in the first stage. Main results. Long-term iEEG recordings of 11 patients who suffered from TLE were analyzed via leave-one-out cross validation. The proposed method has a detection accuracy of 95.24%, a false alarm rate of 0.09/h, and an average detection delay time of 9.2 s. For the six patients with mesial TLE, a detection accuracy of 100.0%, a false alarm rate of 0.06/h, and an average detection delay time of 4.8 s can be achieved. The hierarchical approach provides a 90% energy reduction, yielding effective and energy-efficient implementation for real-time epileptic seizure detection. Significance. An on-line seizure detection method that can be applied to monitor continuous iEEG signals of patients who suffered from TLE was developed. An IC selection strategy to automatically determine the most seizure-related IC for seizure detection was also proposed. The system has advantages of (1) high detection accuracy, (2) low false alarm, (3) short detection latency, and (4) energy-efficient design for hardware implementation.

AB - Objective. Around 1% of the world's population is affected by epilepsy, and nearly 25% of patients cannot be treated effectively by available therapies. The presence of closed-loop seizure-triggered stimulation provides a promising solution for these patients. Realization of fast, accurate, and energy-efficient seizure detection is the key to such implants. In this study, we propose a two-stage on-line seizure detection algorithm with low-energy consumption for temporal lobe epilepsy (TLE). Approach. Multi-channel signals are processed through independent component analysis and the most representative independent component (IC) is automatically selected to eliminate artifacts. Seizure-like intracranial electroencephalogram (iEEG) segments are fast detected in the first stage of the proposed method and these seizures are confirmed in the second stage. The conditional activation of the second-stage signal processing reduces the computational effort, and hence energy, since most of the non-seizure events are filtered out in the first stage. Main results. Long-term iEEG recordings of 11 patients who suffered from TLE were analyzed via leave-one-out cross validation. The proposed method has a detection accuracy of 95.24%, a false alarm rate of 0.09/h, and an average detection delay time of 9.2 s. For the six patients with mesial TLE, a detection accuracy of 100.0%, a false alarm rate of 0.06/h, and an average detection delay time of 4.8 s can be achieved. The hierarchical approach provides a 90% energy reduction, yielding effective and energy-efficient implementation for real-time epileptic seizure detection. Significance. An on-line seizure detection method that can be applied to monitor continuous iEEG signals of patients who suffered from TLE was developed. An IC selection strategy to automatically determine the most seizure-related IC for seizure detection was also proposed. The system has advantages of (1) high detection accuracy, (2) low false alarm, (3) short detection latency, and (4) energy-efficient design for hardware implementation.

UR - http://www.scopus.com/inward/record.url?scp=84883155165&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883155165&partnerID=8YFLogxK

U2 - 10.1088/1741-2560/10/4/045004

DO - 10.1088/1741-2560/10/4/045004

M3 - Article

C2 - 23723141

AN - SCOPUS:84883155165

VL - 10

JO - Journal of Neural Engineering

JF - Journal of Neural Engineering

SN - 1741-2560

IS - 4

M1 - 045004

ER -