Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A Deep Learning Architecture for Epileptic Seizure Classification Based on Object and Action Recognition

Abstract: 

Epilepsy affects approximately 1% of the world’s population. Semiology of epileptic seizures contain major clinical signs to classify epilepsy syndromes currently evaluated by epileptologists by simple visual inspection of video. There is a necessity to create automatic and semiautomatic methods for seizure detection and classification to better support patient monitoring management and diagnostic decisions. One of the current promising approaches are the marker-less computer-vision techniques. In this paper an end-to-end deep learning approach is proposed for binary classification of Frontal vs. Temporal Lobe Epilepsies based solely on seizure videos. The system utilizes infrared (IR) videos of the seizures as it is used 24/7 in hospitals’ epilepsy monitoring units. The architecture employs transfer learning from large object detection "static" and human action recognition "dynamic" datasets such as ImageNet and Kinectics-400, to extract and classify the clinically known spatiotemporal features of seizures. The developed classification architecture achieves a 5-fold cross-validation f1-score of 0.844±0.042. This architecture has the potential to support physicians with diagnostic decisions and might be applied for online applications in epilepsy monitoring units. Furthermore, it may be jointly used in the near future with synchronized scene depth 3D information and EEG from the seizures.

up
0 users have voted:

Paper Details

Authors:
Tamás Karácsony ; Anna Mira Loesch-Biffar ; Christian Vollmar ; Soheyl Noachtar ; João Paulo Silva Cunha
Submitted On:
14 May 2020 - 8:20am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Tamás Karácsony
Paper Code:
MLSP-P13.4
Document Year:
2020
Cite

Document Files

ICASSP2020 slides

(43)

Subscribe

[1] Tamás Karácsony ; Anna Mira Loesch-Biffar ; Christian Vollmar ; Soheyl Noachtar ; João Paulo Silva Cunha, "A Deep Learning Architecture for Epileptic Seizure Classification Based on Object and Action Recognition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5295. Accessed: Sep. 26, 2020.
@article{5295-20,
url = {http://sigport.org/5295},
author = {Tamás Karácsony ; Anna Mira Loesch-Biffar ; Christian Vollmar ; Soheyl Noachtar ; João Paulo Silva Cunha },
publisher = {IEEE SigPort},
title = {A Deep Learning Architecture for Epileptic Seizure Classification Based on Object and Action Recognition},
year = {2020} }
TY - EJOUR
T1 - A Deep Learning Architecture for Epileptic Seizure Classification Based on Object and Action Recognition
AU - Tamás Karácsony ; Anna Mira Loesch-Biffar ; Christian Vollmar ; Soheyl Noachtar ; João Paulo Silva Cunha
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5295
ER -
Tamás Karácsony ; Anna Mira Loesch-Biffar ; Christian Vollmar ; Soheyl Noachtar ; João Paulo Silva Cunha. (2020). A Deep Learning Architecture for Epileptic Seizure Classification Based on Object and Action Recognition. IEEE SigPort. http://sigport.org/5295
Tamás Karácsony ; Anna Mira Loesch-Biffar ; Christian Vollmar ; Soheyl Noachtar ; João Paulo Silva Cunha, 2020. A Deep Learning Architecture for Epileptic Seizure Classification Based on Object and Action Recognition. Available at: http://sigport.org/5295.
Tamás Karácsony ; Anna Mira Loesch-Biffar ; Christian Vollmar ; Soheyl Noachtar ; João Paulo Silva Cunha. (2020). "A Deep Learning Architecture for Epileptic Seizure Classification Based on Object and Action Recognition." Web.
1. Tamás Karácsony ; Anna Mira Loesch-Biffar ; Christian Vollmar ; Soheyl Noachtar ; João Paulo Silva Cunha. A Deep Learning Architecture for Epileptic Seizure Classification Based on Object and Action Recognition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5295