Presentation 2021-07-05
Epileptic Spike Detection from Electroencephalogram with Self-Attention Mechanism
Kosuke Fukumori, Noboru Yoshida, Hidenori Sugano, Madoka Nakajima, Toshihisa Tanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Automated identification of epileptiform discharges for the diagnosis of epilepsy can mitigate the burden of the exhaustive manual search in electroencephalogram (EEG). Recent studies have indicated that a two-step method that consists of detection of candidate waveforms with signal processing and pattern matching followed by machine learning-based classification is effective. However, the overall performance depends on the detector of candidates. This paper thus considers a scenario without candidate waveforms, that is, we propose a recurrent neural network (RNN)-based self-attention model that can be fitted from the EEG segments generated without detecting spike candidates. In comparison with the state-of-the-art machine learning models which can be applied for EEG classification (LightGBM and EEGNet), the proposed model achieved higher performance (average accuracy: 90.2%). This result strongly suggests that the self-attention mechanism is suitable to an automated identification of the epileptiform discharge in the EEG.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) epilepsy / epileptiform discharge / neural networks / electroencephalogram (EEG)
Paper # CAS2021-3,VLD2021-3,SIP2021-13,MSS2021-3
Date of Issue 2021-06-28 (CAS, VLD, SIP, MSS)

Conference Information
Committee SIP / CAS / VLD / MSS
Conference Date 2021/7/5(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yukihiro Bandou(NTT) / Hiroki Sato(Sony LSI Design) / Kazutoshi Kobayashi(Kyoto Inst. of Tech.) / Atsuo Ozaki(Osaka Inst. of Tech.)
Vice Chair Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) / Takayuki Nakachi(Ryukyu Univ.) / Yoshinobu Maeda(Niigata Univ.) / Minako Ikeda(NTT) / Shingo Yamaguchi(Yamaguchi Univ.)
Secretary Toshihisa Tanaka(Xiaomi) / Takayuki Nakachi(Takushoku Univ.) / Yoshinobu Maeda(Tokyo Univ. Agri.&Tech.) / Minako Ikeda(Sony LSI Design) / Shingo Yamaguchi(NIT, Toyama college)
Assistant Taichi Yoshida(UEC) / Seisuke Kyochi(Univ. of Kitakyushu) / Motoi Yamaguchi(TECHNOPRO) / Yohei Nakamura(Hitachi) / Takahide Sato(Univ. of Yamanashi) / Yasutoshi Aibara(Murata Manufacturing) / / Masato Shirai(Shimane Univ.)

Paper Information
Registration To Technical Committee on Signal Processing / Technical Committee on Circuits and Systems / Technical Committee on VLSI Design Technologies / Technical Committee on Mathematical Systems Science and its Applications
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Epileptic Spike Detection from Electroencephalogram with Self-Attention Mechanism
Sub Title (in English)
Keyword(1) epilepsy
Keyword(2) epileptiform discharge
Keyword(3) neural networks
Keyword(4) electroencephalogram (EEG)
1st Author's Name Kosuke Fukumori
1st Author's Affiliation Tokyo University of Agriculture and Technology(TUAT)
2nd Author's Name Noboru Yoshida
2nd Author's Affiliation Juntendo University Nerima Hospital(Juntendo Univ.)
3rd Author's Name Hidenori Sugano
3rd Author's Affiliation Juntendo University(Juntendo Univ.)
4th Author's Name Madoka Nakajima
4th Author's Affiliation Juntendo University(Juntendo Univ.)
5th Author's Name Toshihisa Tanaka
5th Author's Affiliation Tokyo University of Agriculture and Technology(TUAT)
Date 2021-07-05
Paper # CAS2021-3,VLD2021-3,SIP2021-13,MSS2021-3
Volume (vol) vol.121
Number (no) CAS-89,VLD-90,SIP-91,MSS-92
Page pp.pp.11-15(CAS), pp.11-15(VLD), pp.11-15(SIP), pp.11-15(MSS),
#Pages 5
Date of Issue 2021-06-28 (CAS, VLD, SIP, MSS)