{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:52:17Z","timestamp":1777697537486,"version":"3.51.4"},"reference-count":14,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDT"],"published-print":{"date-parts":[[2023,4,20]]},"abstract":"<jats:p>Deep Neural Networks (DNN) have significantly improved the capabilities for analysis and classification of data, including that of biomedical signals (eg. ElectroencephalogramEEG). Optimal classification of EEG signals from seizure onset zones has been challenging especially given the complexity of signals arising from multiple locations. Also, underlying electrophysiological abnormalities which signify epileptogenic zones have not been clearly defined. Previous studies have demonstrated, automatic feature generation based on deep learning as a useful tool for interictal epileptiform discharge (IEDs) detection. Also signals with transformations have been used in convolutional neural network (CNN) based models in the past for classifying EEG data. We explored the use of deep learning for identification of the seizure onset zones using regular dense neural network and CNN based models. After the training the model using sample data the results were validated with a smaller percentage (10%) of the data. The models were noted to be accurate in predicting the seizure onset zones with significant degree of accuracy (87\u201399%) with a much shorter duration of signal recorded, compared to previous studies. We further investigated model\u2019s decision-making process with heatmapping (gradient-weighted class activation map: Grad-CAM) approach, combining with signal processing using Hilbert transform. To identify the visible features in the signal, which maximally contribute to the seizure onset zone prediction, correlation of heatmap and analytical signal of the EEG, was calculated. A high correlation between heatmap and analytical signal was noted, suggesting that the model may be utilizing the higher power regions of the data in decision making process. This study demonstrates the potential use of DNN based strategies in identifying the epileptogenic zones in the intracranial EEG. It also shows the heatmapping strategies can help in establishing how specific signal patterns may be contributing to the decision making of DNN.<\/jats:p>","DOI":"10.3233\/idt-228040","type":"journal-article","created":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T12:09:29Z","timestamp":1678795769000},"page":"43-53","source":"Crossref","is-referenced-by-count":4,"title":["Deep neural networks and gradient-weighted class activation mapping to classify and analyze EEG"],"prefix":"10.1177","volume":"17","author":[{"given":"Elakkat D.","family":"Gireesh","sequence":"first","affiliation":[{"name":"University of Central Florida, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Holly","family":"Skinner","sequence":"additional","affiliation":[{"name":"AdventHealth Hospital, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joohee","family":"Seo","sequence":"additional","affiliation":[{"name":"AdventHealth, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Po","family":"Ching","sequence":"additional","affiliation":[{"name":"AdventHealth, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lee Ki","family":"Hyeong","sequence":"additional","affiliation":[{"name":"AdventHealth, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Baumgartner","sequence":"additional","affiliation":[{"name":"AdventHealth, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Varadraj","family":"Gurupur","sequence":"additional","affiliation":[{"name":"University of Central Florida, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"45","key":"10.3233\/IDT-228040_ref1","first-page":"909","article-title":"Epilepsy in adults and access to care \u2013 United States","volume":"61","author":"for Disease Control","year":"2012","journal-title":"2010. MMWR Morbidity and Mortality Weekly Report."},{"issue":"1","key":"10.3233\/IDT-228040_ref2","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1111\/j.1528-1167.2009.02141.x","article-title":"Early versus late remission in a cohort of patients with newly diagnosed epilepsy","volume":"51","author":"Del Felice","year":"2010","journal-title":"Epilepsia"},{"issue":"8","key":"10.3233\/IDT-228040_ref3","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1007\/s00701-010-0697-3","article-title":"Surgery for extratemporal nonlesional epilepsy in adults: An outcome meta-analysis","volume":"152","author":"Ansari","year":"2010","journal-title":"Acta Neurochirurgica"},{"issue":"3","key":"10.3233\/IDT-228040_ref4","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1001\/jama.2014.17426","article-title":"Resective epilepsy surgery for drug-resistant focal epilepsy: A review","volume":"313","author":"Jobst","year":"2015","journal-title":"Jama"},{"issue":"9","key":"10.3233\/IDT-228040_ref6","doi-asserted-by":"crossref","first-page":"1120","DOI":"10.1109\/LSP.2014.2325781","article-title":"Convolutional neural networks for distant speech recognition","volume":"21","author":"Swietojanski","year":"2014","journal-title":"IEEE Signal Processing Letters"},{"key":"10.3233\/IDT-228040_ref7","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.jneumeth.2016.10.008","article-title":"Interpretable deep neural networks for single-trial EEG classification","volume":"274","author":"Sturm","year":"2016","journal-title":"Journal of Neuroscience Methods"},{"issue":"6","key":"10.3233\/IDT-228040_ref8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF02309007","article-title":"Use of some sensitivity criteria for choosing networks with good generalization ability","volume":"2","author":"Dimopoulos","year":"1995","journal-title":"Neural Processing Letters"},{"issue":"2-3","key":"10.3233\/IDT-228040_ref9","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/S0304-3800(99)00099-X","article-title":"Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city (Greece)","volume":"120","author":"Dimopoulos","year":"1999","journal-title":"Ecological Modelling"},{"key":"10.3233\/IDT-228040_ref14","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.compbiomed.2019.04.031","article-title":"Classification of epileptic EEG recordings using signal transforms and convolutional neural networks","volume":"109","author":"San-Segundo","year":"2019","journal-title":"Computers in Biology and Medicine"},{"issue":"1","key":"10.3233\/IDT-228040_ref15","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.clinph.2019.09.031","article-title":"Detection of mesial temporal lobe epileptiform discharges on intracranial electrodes using deep learning","volume":"131","author":"Abou Jaoude","year":"2020","journal-title":"Clinical Neurophysiology"},{"issue":"2","key":"10.3233\/IDT-228040_ref16","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1002\/ana.22548","article-title":"High-frequency oscillations as a new biomarker in epilepsy","volume":"71","author":"Zijlmans","year":"2012","journal-title":"Annals of Neurology"},{"issue":"3","key":"10.3233\/IDT-228040_ref17","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.pneurobio.2012.03.001","article-title":"High-frequency oscillations (HFOs) in clinical epilepsy","volume":"98","author":"Jacobs","year":"2012","journal-title":"Progress in Neurobiology"},{"key":"10.3233\/IDT-228040_ref22","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.neucom.2021.06.048","article-title":"One dimensional convolutional neural networks for seizure onset detection using long-term scalp and intracranial EEG","volume":"459","author":"Wang","year":"2021","journal-title":"Neurocomputing"},{"issue":"1s","key":"10.3233\/IDT-228040_ref23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3241056","article-title":"Applying deep learning for epilepsy seizure detection and brain mapping visualization","volume":"15","author":"Hossain","year":"2019","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"}],"container-title":["Intelligent Decision Technologies"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDT-228040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:23:28Z","timestamp":1777454608000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDT-228040"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,20]]},"references-count":14,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/idt-228040","relation":{},"ISSN":["1872-4981","1875-8843"],"issn-type":[{"value":"1872-4981","type":"print"},{"value":"1875-8843","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,20]]}}}