A spiking neural network (SNN) for detecting high frequency oscillations (HFOs) in the intraoperative ECoG

Abstract To achieve seizure freedom, epilepsy surgery requires the complete resection of the epileptogenic brain tissue. In intraoperative electrocorticography (ECoG) recordings, high frequency oscillations (HFOs) generated by epileptogenic tissue can be used to tailor the resection margin. However,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Karla Burelo, Mohammadali Sharifshazileh, Niklaus Krayenbühl, Georgia Ramantani, Giacomo Indiveri, Johannes Sarnthein
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/ec4ae24762b6472989197722fe34f691
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ec4ae24762b6472989197722fe34f691
record_format	dspace
spelling	oai:doaj.org-article:ec4ae24762b6472989197722fe34f6912021-12-02T16:36:13ZA spiking neural network (SNN) for detecting high frequency oscillations (HFOs) in the intraoperative ECoG10.1038/s41598-021-85827-w2045-2322https://doaj.org/article/ec4ae24762b6472989197722fe34f6912021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85827-whttps://doaj.org/toc/2045-2322Abstract To achieve seizure freedom, epilepsy surgery requires the complete resection of the epileptogenic brain tissue. In intraoperative electrocorticography (ECoG) recordings, high frequency oscillations (HFOs) generated by epileptogenic tissue can be used to tailor the resection margin. However, automatic detection of HFOs in real-time remains an open challenge. Here we present a spiking neural network (SNN) for automatic HFO detection that is optimally suited for neuromorphic hardware implementation. We trained the SNN to detect HFO signals measured from intraoperative ECoG on-line, using an independently labeled dataset (58 min, 16 recordings). We targeted the detection of HFOs in the fast ripple frequency range (250-500 Hz) and compared the network results with the labeled HFO data. We endowed the SNN with a novel artifact rejection mechanism to suppress sharp transients and demonstrate its effectiveness on the ECoG dataset. The HFO rates (median 6.6 HFO/min in pre-resection recordings) detected by this SNN are comparable to those published in the dataset (Spearman’s $$\rho$$ ρ = 0.81). The postsurgical seizure outcome was “predicted” with 100% (CI [63 100%]) accuracy for all 8 patients. These results provide a further step towards the construction of a real-time portable battery-operated HFO detection system that can be used during epilepsy surgery to guide the resection of the epileptogenic zone.Karla BureloMohammadali SharifshazilehNiklaus KrayenbühlGeorgia RamantaniGiacomo IndiveriJohannes SarntheinNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Karla Burelo Mohammadali Sharifshazileh Niklaus Krayenbühl Georgia Ramantani Giacomo Indiveri Johannes Sarnthein A spiking neural network (SNN) for detecting high frequency oscillations (HFOs) in the intraoperative ECoG
description	Abstract To achieve seizure freedom, epilepsy surgery requires the complete resection of the epileptogenic brain tissue. In intraoperative electrocorticography (ECoG) recordings, high frequency oscillations (HFOs) generated by epileptogenic tissue can be used to tailor the resection margin. However, automatic detection of HFOs in real-time remains an open challenge. Here we present a spiking neural network (SNN) for automatic HFO detection that is optimally suited for neuromorphic hardware implementation. We trained the SNN to detect HFO signals measured from intraoperative ECoG on-line, using an independently labeled dataset (58 min, 16 recordings). We targeted the detection of HFOs in the fast ripple frequency range (250-500 Hz) and compared the network results with the labeled HFO data. We endowed the SNN with a novel artifact rejection mechanism to suppress sharp transients and demonstrate its effectiveness on the ECoG dataset. The HFO rates (median 6.6 HFO/min in pre-resection recordings) detected by this SNN are comparable to those published in the dataset (Spearman’s $$\rho$$ ρ = 0.81). The postsurgical seizure outcome was “predicted” with 100% (CI [63 100%]) accuracy for all 8 patients. These results provide a further step towards the construction of a real-time portable battery-operated HFO detection system that can be used during epilepsy surgery to guide the resection of the epileptogenic zone.
format	article
author	Karla Burelo Mohammadali Sharifshazileh Niklaus Krayenbühl Georgia Ramantani Giacomo Indiveri Johannes Sarnthein
author_facet	Karla Burelo Mohammadali Sharifshazileh Niklaus Krayenbühl Georgia Ramantani Giacomo Indiveri Johannes Sarnthein
author_sort	Karla Burelo
title	A spiking neural network (SNN) for detecting high frequency oscillations (HFOs) in the intraoperative ECoG
title_short	A spiking neural network (SNN) for detecting high frequency oscillations (HFOs) in the intraoperative ECoG
title_full	A spiking neural network (SNN) for detecting high frequency oscillations (HFOs) in the intraoperative ECoG
title_fullStr	A spiking neural network (SNN) for detecting high frequency oscillations (HFOs) in the intraoperative ECoG
title_full_unstemmed	A spiking neural network (SNN) for detecting high frequency oscillations (HFOs) in the intraoperative ECoG
title_sort	spiking neural network (snn) for detecting high frequency oscillations (hfos) in the intraoperative ecog
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/ec4ae24762b6472989197722fe34f691
work_keys_str_mv	AT karlaburelo aspikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT mohammadalisharifshazileh aspikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT niklauskrayenbuhl aspikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT georgiaramantani aspikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT giacomoindiveri aspikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT johannessarnthein aspikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT karlaburelo spikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT mohammadalisharifshazileh spikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT niklauskrayenbuhl spikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT georgiaramantani spikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT giacomoindiveri spikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog AT johannessarnthein spikingneuralnetworksnnfordetectinghighfrequencyoscillationshfosintheintraoperativeecog
_version_	1718383666255626240

A spiking neural network (SNN) for detecting high frequency oscillations (HFOs) in the intraoperative ECoG

Ejemplares similares