but.defence	Studentka Tereza Přidalová prezentovala svou diplomovou práci a zodpověděla dotazy v průběhu diskuze. Studentka svou práci úspěšně obhájila.	cs
but.jazyk	angličtina (English)
but.program	Bioengineering	cs
but.result	práce byla úspěšně obhájena	cs
dc.contributor.advisor	Mehnen, Lars	en
dc.contributor.author	Přidalová, Tereza	en
dc.contributor.referee	Cimbálník, Jan	en
dc.date.created	2022	cs
dc.description.abstract	Epilepsy affects about 50 million people worldwide, with one-third of patients being drugresistant and therefore candidates for an invasive brain resection surgery. Brain resection surgery candidates undergo invasive intracranial encephalography (iEEG) monitoring to determine the seizure onset zone (SOZ). Recorded data can span over weeks and need to be manually reviewed by a physician to assess SOZ. This process can be time-consuming and burdensome due to the vast amount of collected data. This work investigates utilisation of an deep autoencoder for unsupervised data exploration and specifically its ability to discriminate between SOZ and non-SOZ (NSOZ) iEEG channels. The data used in this thesis consists of iEEG collected from 33 patients in two institutes (Mayo Clinic, Rochester, Minnesota, USA and St. Anne´s University Hospital, Brno, Czech Republic - FNUSA) who underwent invasive presurgical monitoring. The autoencoder’s capability to discriminate between SOZ and NSOZ was evaluated using a self-learned embedded feature space representation of the autoencoder network. Autoencoder features were compared to previously established biomarkers for SOZ determination. Discrimination capability was evaluated for both autoencoder features and biomarkers using a Naive Bayes classifier and leave-one-out cross-validation. The achieved area under receiver operating characteristic curve (AUROC) was 0.68 for the FNUSA and 0.56 for the Mayo dataset. Performance in discriminating between SOZ and NSOZ electrodes was not significantly different between the investigated autoencoder features and previously established biomarkers. Selecting the better performing classifier for each patient increased the AUROC to 0.75 and 0.64 for the FNUSA and Mayo dataset, respectively. The results suggest that future approaches combining biomarkers and self-learning methods have a potential to improve the SOZ vs NSOZ discrimination capability of unsupervised iEEG exploration systems, and thus to enhance the surgical management of epilepsy.	en
dc.description.abstract	Epilepsy affects about 50 million people worldwide, with one-third of patients being drugresistant and therefore candidates for an invasive brain resection surgery. Brain resection surgery candidates undergo invasive intracranial encephalography (iEEG) monitoring to determine the seizure onset zone (SOZ). Recorded data can span over weeks and need to be manually reviewed by a physician to assess SOZ. This process can be time-consuming and burdensome due to the vast amount of collected data. This work investigates utilisation of an deep autoencoder for unsupervised data exploration and specifically its ability to discriminate between SOZ and non-SOZ (NSOZ) iEEG channels. The data used in this thesis consists of iEEG collected from 33 patients in two institutes (Mayo Clinic, Rochester, Minnesota, USA and St. Anne´s University Hospital, Brno, Czech Republic - FNUSA) who underwent invasive presurgical monitoring. The autoencoder’s capability to discriminate between SOZ and NSOZ was evaluated using a self-learned embedded feature space representation of the autoencoder network. Autoencoder features were compared to previously established biomarkers for SOZ determination. Discrimination capability was evaluated for both autoencoder features and biomarkers using a Naive Bayes classifier and leave-one-out cross-validation. The achieved area under receiver operating characteristic curve (AUROC) was 0.68 for the FNUSA and 0.56 for the Mayo dataset. Performance in discriminating between SOZ and NSOZ electrodes was not significantly different between the investigated autoencoder features and previously established biomarkers. Selecting the better performing classifier for each patient increased the AUROC to 0.75 and 0.64 for the FNUSA and Mayo dataset, respectively. The results suggest that future approaches combining biomarkers and self-learning methods have a potential to improve the SOZ vs NSOZ discrimination capability of unsupervised iEEG exploration systems, and thus to enhance the surgical management of epilepsy.	cs
dc.description.mark	A	cs
dc.identifier.citation	PŘIDALOVÁ, T. Hluboké učení pro lokalizaci epileptického ložiska [online]. Brno: Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. 2022.	cs
dc.identifier.other	137651	cs
dc.identifier.uri	http://hdl.handle.net/11012/208148
dc.language.iso	en	cs
dc.publisher	Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií	cs
dc.rights	Standardní licenční smlouva - přístup k plnému textu bez omezení	cs
dc.subject	epilepsy	en
dc.subject	seizure onset zone	en
dc.subject	deep learning	en
dc.subject	autoencoder	en
dc.subject	iEEG	en
dc.subject	epilepsy	cs
dc.subject	seizure onset zone	cs
dc.subject	deep learning	cs
dc.subject	autoencoder	cs
dc.subject	iEEG	cs
dc.title	Hluboké učení pro lokalizaci epileptického ložiska	en
dc.title.alternative	Unsupervised Deep Learning Approach for Seizure Onset Zone localization in Epilepsy	cs
dc.type	Text	cs
dc.type.driver	masterThesis	en
dc.type.evskp	diplomová práce	cs
dcterms.dateAccepted	2022-06-21	cs
dcterms.modified	2022-07-21-14:45:34	cs
eprints.affiliatedInstitution.faculty	Fakulta elektrotechniky a komunikačních technologií	cs
sync.item.dbid	137651	en
sync.item.dbtype	ZP	en
sync.item.insts	2025.03.26 14:32:15	en
sync.item.modts	2025.01.15 17:37:14	en
thesis.discipline	bez specializace	cs
thesis.grantor	Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav biomedicínského inženýrství	cs
thesis.level	Inženýrský	cs
thesis.name	Ing.	cs

Hluboké učení pro lokalizaci epileptického ložiska

Files

Original bundle

Collections