Learning Robust Features using Deep Learning for Automatic Seizure Detection

Pierre Thodoroff, Joelle Pineau, Andrew Lim
; Proceedings of the 1st Machine Learning for Healthcare Conference, PMLR 56:178-190, 2016.

Abstract

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v56-Thodoroff16, title = {Learning Robust Features using Deep Learning for Automatic Seizure Detection}, author = {Pierre Thodoroff and Joelle Pineau and Andrew Lim}, booktitle = {Proceedings of the 1st Machine Learning for Healthcare Conference}, pages = {178--190}, year = {2016}, editor = {Finale Doshi-Velez and Jim Fackler and David Kale and Byron Wallace and Jenna Wiens}, volume = {56}, series = {Proceedings of Machine Learning Research}, address = {Northeastern University, Boston, MA, USA}, month = {18--19 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v56/Thodoroff16.pdf}, url = {http://proceedings.mlr.press/v56/Thodoroff16.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Learning Robust Features using Deep Learning for Automatic Seizure Detection %A Pierre Thodoroff %A Joelle Pineau %A Andrew Lim %B Proceedings of the 1st Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2016 %E Finale Doshi-Velez %E Jim Fackler %E David Kale %E Byron Wallace %E Jenna Wiens %F pmlr-v56-Thodoroff16 %I PMLR %J Proceedings of Machine Learning Research %P 178--190 %U http://proceedings.mlr.press %V 56 %W PMLR %X 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.
RIS
TY - CPAPER TI - Learning Robust Features using Deep Learning for Automatic Seizure Detection AU - Pierre Thodoroff AU - Joelle Pineau AU - Andrew Lim BT - Proceedings of the 1st Machine Learning for Healthcare Conference PY - 2016/12/10 DA - 2016/12/10 ED - Finale Doshi-Velez ED - Jim Fackler ED - David Kale ED - Byron Wallace ED - Jenna Wiens ID - pmlr-v56-Thodoroff16 PB - PMLR SP - 178 DP - PMLR EP - 190 L1 - http://proceedings.mlr.press/v56/Thodoroff16.pdf UR - http://proceedings.mlr.press/v56/Thodoroff16.html AB - 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. ER -
APA
Thodoroff, P., Pineau, J. & Lim, A.. (2016). Learning Robust Features using Deep Learning for Automatic Seizure Detection. Proceedings of the 1st Machine Learning for Healthcare Conference, in PMLR 56:178-190

Related Material