Learning Robust Features using Deep Learning for Automatic Seizure Detection
By Pierre Thodoroff, Joelle Pineau, Andrew Lim. Machine Learning in Health Care, 2016
321 citations recorded by the source corpus.
We present and evaluate the capacity of a deep neural network to learn robust features from EEG to automatically detect seizures. This is a challenging problem because seizure manifestations on EEG are extremely variable both inter- and intra-patient. By simultaneously capturing spectral, temporal and spatial information our recurrent convolutional neural network learns a general spatially invariant representation of a seizure. The proposed approach exceeds significantly previous results obtained on cross-patient classifiers both in terms of sensitivity and false positive rate. Furthermore, our model proves to be robust to missing channel and variable electrode montage.
Subfields: Artificial Intelligence, Cognitive Neuroscience, Neurology
View Paper: https://www.semanticscholar.org/paper/6622bdc1aed1f4d5719ca6cab80927e373c4f183
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Cao Xiao
- Jimeng Sun
- Abbas Khosravi
- Isabela Albuquerque
- Amir F. Atiya
- Dimitrios I. Fotiadis
- Saeid Nahavandi
- Alexandre Gramfort
In Cognitive Neuroscience
- Abbas Khosravi
- Cao Xiao
- Dimitrios I. Fotiadis
- Jimeng Sun
- Saeid Nahavandi
- Alexandre Gramfort
- Dehua Liang
- M. Brandon Westover
Citations in the corpus
- Data Augmentation for Deep-Learning-Based Electroencephalography. (2020, background): “Cost-sensitive learning [45], oversampling of the minority class [92, 94, 107], and subsampling the majority class [98, 108] are common techniques to address imbalanced classes.”
- EEGtoText: Learning to Write Medical Reports from EEG Recordings (2019, methodology): “Deep neural networks have been applied to both raw EEG signals and spectrogram representations (Bashivan et al., 2015; Tibor Schirrmeister et al., 2017; Schirrmeister et al., 2017; Biswal et al., 2017; Thodoroff et al., 2016) or on clinical texts (Maldonado”
- Deep learning-based electroencephalography analysis: a systematic review (2019, background): “Conversely, in [172, 194], the majority class was subsampled.”
- Epileptic Seizures Detection Using Deep Learning Techniques: A Review (2020, methodology): “[107] Clinical Theano Normalization, Feature Extraction, Standardization DBN NA LR NA SVM KNN [110] CHB-MIT NA Image Based Representation 2D CNN-LSTM NA NA NA”
- A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals (2018, methodology): “[53], consisting of a 4-layer CNN that inputs the spectral information of each EEG channel and an LSTM network with a single layer to perform the final classification of ictal EEG segments.”