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

Automatic classification of epliptic seizure types in EEG datacould enable more precise diagnosis and efficient manage-ment of the disease. Automatic seizure type classificationusing clinical electroencephalograms (EEGs) is challengingdue to factors such as low signal to noise ratios, signal arte-facts, high variance in the seizure semiology among individ-ual epileptic patients, and limited availability of clinical data.To overcome these challenges, in this paper, we present adeep learning based framework which learns multi-spectralfeature embeddings using multiple CNN models in an ensem-ble architecture for accurate cross-patient seizure type clas-sification. Experiments on the recently released TUH EEGSeizure Corpus show that our multi-spectral dense featurelearning produces a weighted f1 score of 0.98 for seizure typeclassification setting new benchmarks on the dataset.