Classification of patterns of EEG synchronization for seizure prediction.

By Piotr Wojciech Mirowski, Deepak Madhavan, Yann LeCun, Ruben Kuzniecky. Clinical Neurophysiology, 2009

405 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Neurology

View Paper: https://www.semanticscholar.org/paper/f94ed69179beb00b7d759b75f37e3b7f8d0fc937

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Neurology

Citations in the corpus

Focal Onset Seizure Prediction Using Convolutional Networks (2018, methodology): “The closest work to this one applies convolutional neural networks (CNN) to selected frequency bands on intracranial EEG [27], [30].”
Seizure prediction with spectral power of EEG using cost‐sensitive support vector machines (2011, background): “Prediction may be also improved by adding and testing more features, including other univariate features such as autoregressive coefficients (Chisci et al., 2010) or bivariate features such as cross-correlation or wavelet synchrony (Mirowski et al., 2009).”
A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series (2017, background): “data [21]–[24] and some of these contributions use a first layer that boils down to a spatial filter [25]–[30].”
Deep learning in bioinformatics (2016, methodology): “Raw EEG signals have been analyzed in brain decoding [164–167] and anomaly classification [176] via CNNs, which perform one-dimensional convolutions.”
Application of Machine Learning To Epileptic Seizure Detection (2010, background): “In (Mirowski et al., 2009), high specificity was achieved because test non-seizure feature vectors (33% of data) were not separated in time from training non-seizure feature vectors (66% of data).”
Deep Learning Human Mind for Automated Visual Classification (2016, background): “, in [5] for P300 detection or in [14] for seizure detection.”
Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks (2015, methodology): “In other works, convolutional and recurrent neural networks have been used to extract representations from EEG time series (Mirowski et al., 2009; Cecotti & Gr¨aser, 2011; Guler et al., 2005).”
Deep Learning and Its Applications in Biomedicine (2018, methodology): “RNN EEG-based prediction of epileptic seizures propagation using t e-delayed NN [141] Classification of patterns of EEG synchronization for seizure p ediction [142] EEG-based lapse detection [143] Prediction of epileptic seizures [144]”
A review of channel selection algorithms for EEG signal processing (2015, methodology): “Chang et al. [22] proposed a channel selection method to reduce the feature pattern size produced from Mirowski et al. work [20] for seizure prediction.”
An Automated System for Epilepsy Detection using EEG Brain Signals based on Deep Learning Approach (2018, background): “Recently, a lot of research work have been carried out to detect the epileptic and non-epileptic signals as a classification problem (Gardner et al., 2006; Meier et al., 2008; Mirowski et al., 2009; Sheb et al., 2010).”
Deep Feature Learning for EEG Recordings (2015, methodology): “Mirowski et al. (2009) applied convolutional neural networks (CNNs) for epileptic seizure prediction in EEG and intercranial EEG. Wulsin et al. (2011) used deep belief nets (DBNs) to detect anomalies related to epilepsy in EEG recordings by classifying individual “channel-seconds”, i.e., one-second…”
Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy. (2014, methodology): “Mirowski, 2009 [17] EEG/PS Variable feature extraction methods used followed by patient-specific”
A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals (2018, methodology): “Bivariate features that measure EEG synchronization in intracranial recordings from the Freiburg database were also used to evaluate the seizure prediction performance of 5-layer CNN and showed that it was able to predict all testing seizures with no false alarms in 15 of 21 patients [49].”