Institutional Repository of Vilnius University
Taikomoji programa skirta epilepsijos priepuolių paieškai dirbtinio intelekto metodais /
Abstract
dc:descriptionThe aim of this bachelor thesis is to develop an application for neurologists and neurophysiologists to speed up their work with electroencephalography (EEG) test results. The application uses EfficientNetV2, a convolutional neural network (CNN) architecture that automatically flags possible epileptic seizures in the EEG. The model was trained using the Siena Scalp EEG database, which consists of EEG recordings from 14 patients. The application reduces the analysis time for neurologists: instead of evaluating the entire EEG study, neurologists review only selected segments. The model achieved 79.01% accuracy, 89.09% sensitivity and 78.94% specificity. A different version of the model (seizure duration must be at least 15 seconds) is also available in the application and achieves 92.43% accuracy, 72.73% sensitivity and 92.57% specificity. The application could be used in the internal infrastructure of medical institutions.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Vidžiūnas, Arnas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD229556294&prefLang=en_US