Search Our Scientific Publications & Authors

Publications
find publications by category +
Translate page:

Deep-learning-based seizure detection and prediction from electroencephalography signals.

Authors:
Fatma E Ibrahim Heba M Emara Walid El-Shafai Mohamed Elwekeil Mohamed Rihan Ibrahim M Eldokany Taha E Taha Adel S El-Fishawy El-Sayed M El-Rabaie Essam Abdellatef Fathi E Abd El-Samie

Int J Numer Method Biomed Eng 2022 Jan 25:e3573. Epub 2022 Jan 25.

Department of Electronics and Electrical Communications Engineering, Faculty of Electronic Engineering, Menoufia University, Menouf, Egypt.

Electroencephalography (EEG) is among the main tools used for analyzing and diagnosing epilepsy. The manual analysis of EEG must be conducted by highly trained clinicians or neuro-physiologists; a process that is considered to have a comparatively low inter-rater agreement. Furthermore, the new data interpretation consumes an excessive amount of time and resources. Hence, an automatic seizure detection and prediction system can improve the quality of patient care in terms of shortening the diagnosis period, reducing manual errors, and automatically detecting debilitating events. Moreover, for patient treatment, it is important to alert the patients of epilepsy seizures prior to seizure occurrence. Various distinguished studies presented good solutions for two-class seizure detection problems with binary classification scenarios. To deal with these challenges, this paper puts forward effective approaches for EEG signal classification for normal, pre-ictal, and ictal activities. Three models are presented for the classification task. Two of them are patient-specific, while the third one is patient non-specific, which makes it better for the general classification tasks. The two-class classification is implemented between normal and pre-ictal activities for seizure prediction and between normal and ictal activities for seizure detection. A more generalized three-class classification framework is considered to identify all EEG signal activities. The first model depends on a Convolutional Neural Network (CNN) with residual blocks. It contains thirteen layers with four residual learning blocks. It works on spectrograms of EEG signal segments. The second model depends on a CNN with three layers. It also works on spectrograms. On the other hand, the third model depends on Phase Space Reconstruction (PSR) to eliminate the limitations of the spectrograms used in the first models. A five-layer CNN is used with this strategy. The advantage of the PSR is the direct projection from the time domain, which keeps the main trend of different signal activities. The third model deals with all signal activities, and it was tested for all patients of the CHB-MIT dataset. It has a superior performance compared to the first models and the state-of-the-art models.

Download full-text PDF

 Source
http://dx.doi.org/10.1002/cnm.3573DOI Listing
January 2022

Publication Analysis

Top Keywords

seizure detection
16
model depends
12
eeg signal
12
signal activities
12
activities seizure
8
detection prediction
8
works spectrograms
8
third model
8
ictal activities
8
normal pre-ictal
8
classification
6
activities
6
seizure
5
signal
5
eeg
5
seizure prediction
4
general classification
4
classification tasks
4
tasks two-class
4
two-class classification
4

Keyword Occurance

Similar Publications

Vagus nerve stimulation for conservative therapy-refractive epilepsy and depression.

Authors:
H Möbius H J Welkoborsky

Laryngorhinootologie 2022 May 23;101(S 01):S114-S143. Epub 2022 May 23.

Klinik für HNO-Heilkunde, Kopf- und Halschirurgie, KRH Klinikum Nordstadt, Hannover.

Numerous studies confirm that the vagus nerve stimulation (VNS) is an efficient, indirect neuromodulatory therapy with electrically induced current for epilepsy that cannot be treated by epilepsy surgery and is therapy-refractory and for drug therapy-refractory depression. VNS is an established, evidence-based and in the long-term cost-effective therapy in an interdisciplinary overall concept.Long-term data on the safety and tolerance of the method are available despite the heterogeneity of the patient populations. Read More

View Article and Full-Text PDF
May 2022
Similar Publications

Virtual Epileptic Patient brain modeling: relationships with seizure onset and surgical outcome.

Authors:
Julia Makhalova Samuel Medina Villalon Huifang Wang Bernard Giusiano Marmaduke Woodman Christian Bénar Maxime Guye Viktor Jirsa Fabrice Bartolomei

Epilepsia 2022 May 23. Epub 2022 May 23.

APHM, Timone Hospital, Epileptology and Cerebral Rhythmology, Marseille, France.

Objective: The virtual epileptic patient (VEP) is a large-scale brain modelling method based on the virtual brain technology, using StereoElectroEncephalography (SEEG), anatomical data (MRI and connectivity) and a computational neuronal model to provide computer simulations of a patient's seizures. VEP has potential interest in the pre-surgical evaluation of drug-resistant epilepsy by identifying regions most likely to generate seizures. We aimed to assess the performance of VEP approach in estimating the epileptogenic zone and in predicting surgical outcome. Read More

View Article and Full-Text PDF
May 2022
Similar Publications

Clinical and imaging features of nonmotor onset seizure in poststroke epilepsy.

Authors:
Kazuki Fukuma Shuhei Ikeda Tomotaka Tanaka Naruhiko Kamogawa Hiroyuki Ishiyama Soichiro Abe Maya Tojima Katsuya Kobayashi Akihiro Shimotake Yuriko Nakaoku Kunihiro Nishimura Masatoshi Koga Kazunori Toyoda Riki Matsumoto Akio Ikeda Masafumi Ihara

Epilepsia 2022 May 20. Epub 2022 May 20.

Department of Neurology, National Cerebral and Cardiovascular Center, Osaka, Japan.

Objective: Motivated by the challenges raised by diagnosing poststroke epilepsy (PSE), especially in nonmotor onset seizure (non-MOS), we aimed to investigate features of non-MOS, including seizure sequences, patient characteristics, and electrophysiological and imaging findings in PSE.

Methods: This observational cohort study enrolled patients with PSE whose seizure onset was witnessed. According to the International League Against Epilepsy 2017 seizure classification, we classified seizure onset symptoms into the non-MOS and MOS groups. Read More

View Article and Full-Text PDF
May 2022
Similar Publications

Intra- and Inter-Subject Perspectives on the Detection of Focal Onset Motor Seizures in Epilepsy Patients.

Authors:
Sebastian Böttcher Elisa Bruno Nino Epitashvili Matthias Dümpelmann Nicolas Zabler Martin Glasstetter Valentina Ticcinelli Sarah Thorpe Simon Lees Kristof Van Laerhoven Mark P Richardson Andreas Schulze-Bonhage

Sensors (Basel) 2022 Apr 26;22(9). Epub 2022 Apr 26.

Epilepsy Center, Department of Neurosurgery, Medical Center-University of Freiburg, 79106 Freiburg im Breisgau, Germany.

Focal onset epileptic seizures are highly heterogeneous in their clinical manifestations, and a robust seizure detection across patient cohorts has to date not been achieved. Here, we assess and discuss the potential of supervised machine learning models for the detection of focal onset motor seizures by means of a wrist-worn wearable device, both in a personalized context as well as across patients. Wearable data were recorded in-hospital from patients with epilepsy at two epilepsy centers. Read More

View Article and Full-Text PDF
April 2022
Similar Publications

Epileptic-seizure onset detection using PARAFAC model with cross-wavelet transformation on multi-channel EEG.

Authors:
Arijit Ghosh Purbanka Pahari Piyali Basak Ujjwal Maulik Anasua Sarkar

Phys Eng Sci Med 2022 May 16. Epub 2022 May 16.

Jadavpur University, Kolkata, West Bengal, India.

Finding components from multi-channel EEG signal for localizing and detection of onset of seizure, is a new approach in biomedical signal analysis. Tensor-based approaches are utilized to fit the components into multi-dimensional arrays in recent works. We initially decompose EEG signals into Beta band using discrete wavelet transform (DWT). Read More

View Article and Full-Text PDF
May 2022
Similar Publications
}