vix.ing · top · new · best · stats · spec

SeizureNet: Multi-Spectral Deep Feature Learning for Seizure Type\n Classification

2019/03/07 by Umar Asif, Asif, Umar, Subhrajit Roy +5
Medicine · Neuroscience · #Brain Tumor Detection and Classification #EEG and Brain-Computer Interfaces #Epilepsy research and treatment #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neurons and Cognition (q-bio.NC)

paper · pdf · doi:10.48550/arxiv.1903.03232

openalex publication_date 2019/03/07 · openalex created_date 2022/07/29 · openalex updated_date 2026/07/28

Abstract

Automatic classification of epileptic seizure types in electroencephalograms\n(EEGs) data can enable more precise diagnosis and efficient management of the\ndisease. This task is challenging due to factors such as low signal-to-noise\nratios, signal artefacts, high variance in seizure semiology among epileptic\npatients, and limited availability of clinical data. To overcome these\nchallenges, in this paper, we present SeizureNet, a deep learning framework\nwhich learns multi-spectral feature embeddings using an ensemble architecture\nfor cross-patient seizure type classification. We used the recently released\nTUH EEG Seizure Corpus (V1.4.0 and V1.5.2) to evaluate the performance of\nSeizureNet. Experiments show that SeizureNet can reach a weighted F1 score of\nup to 0.94 for seizure-wise cross validation and 0.59 for patient-wise cross\nvalidation for scalp EEG based multi-class seizure type classification. We also\nshow that the high-level feature embeddings learnt by SeizureNet considerably\nimprove the accuracy of smaller networks through knowledge distillation for\napplications with low-memory constraints.\n

Related