Article
Engineering, Biomedical
Jingwei Zhang, Christos Chatzichristos, Kaat Vandecasteele, Lauren Swinnen, Victoria Broux, Evy Cleeren, Wim Van Paesschen, Maarten De Vos
Summary: This paper presents an automatic annotation correction approach for training seizure detection algorithms using wearable EEG data. The approach improves the sensitivity and reduces false-positive detections compared to visually corrected and original seizure annotations.
JOURNAL OF NEURAL ENGINEERING
(2022)
Article
Engineering, Multidisciplinary
Mohammed Diykh, Firas Sabar Miften, Shahab Abdulla, Ravinesh C. Deo, Siuly Siuly, Jonathan H. Green, Atheer Y. Oudahb
Summary: This paper proposes a new framework for the automated detection of neonatal seizures based on the Morse Wavelet approach, local binary pattern algorithm, and graph-based community detection algorithm. The experimental results demonstrate that the proposed model is more accurate in detecting seizures compared to traditional approaches.
Article
Computer Science, Information Systems
Said Agounad, Soukaina Hamou, Ousama Tarahi, Mustapha Moufassih, Md Kafiul Islam
Summary: This study proposes an automatic method and algorithm for handling EEG artifacts, which involves the use of statistical parameters, fuzzy inference system, and stationary wavelet transform. The method effectively identifies and removes artifacts to restore clean EEG signals. Evaluation in various scenarios demonstrates its superior performance and computational efficiency compared to existing methods.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Clinical Neurology
Lejla Elezi, Johannes P. Koren, Susanne Pirker, Christoph Baumgartner
Summary: This study investigates the impact of seizure pattern morphology on automatic seizure detection and finds significant correlations between seizure pattern morphology, seizure onset zone, and detection performance.
CLINICAL NEUROPHYSIOLOGY
(2022)
Article
Clinical Neurology
Johannes Koren, Sebastian Hafner, Moritz Feigl, Christoph Baumgartner
Summary: The study compared three commercially available seizure-detection software packages (Besa, Encevis, Persyst) in 81 epilepsy patients undergoing long-term video-EEG monitoring. While all three packages showed similar sensitivities in detecting seizures, they differed in false alarm rates and detection delays. Persyst 13 had the highest detection rate and false alarm rate with the shortest detection delay, while Encevis 1.7 had slightly lower sensitivity, the lowest false alarm rate, and longer detection delay.
Article
Biochemistry & Molecular Biology
Ramy Hussein, Soojin Lee, Rabab Ward
Summary: In this study, a Transformer-based approach called MViT is introduced for automated learning of spatio-temporal-spectral features in multi-channel EEG data. Extensive experiments demonstrate the superiority of MViT algorithm in seizure prediction.
Article
Clinical Neurology
Troels W. Kjaer, Line S. Remvig, Asbjoern W. Helge, Jonas Duun-Henriksen
Summary: This study combined EEG and movement-related modalities to define individual multimodal ictal fingerprints for epilepsy management. Features from acceleration, EMG activity, and EEG bands were used to establish these fingerprints, showing the benefits of integrating multiple modalities for understanding seizure semiology and manifestation.
FRONTIERS IN NEUROLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Ramy Hussein, Soojin Lee, Rabab Ward, Martin J. McKeown
Summary: This study introduces a novel semi-dilated convolutional neural network architecture that outperforms previous methods in predicting epileptic seizures, achieving an average prediction sensitivity of 98.90% for scalp EEG.
Article
Chemistry, Analytical
Gul Hameed Khan, Nadeem Ahmad Khan, Muhammad Awais Bin Altaf, Qammer Abbasi
Summary: This paper proposes a trainable hybrid approach for epileptic seizure detection using a shallow autoencoder (AE) and a conventional classifier. The encoded AE representation is used as a feature vector for classifying EEG signal segments as epileptic or non-epileptic. The algorithm has low computational complexity and can be used in body sensor networks and wearable devices. Experimental results show that the proposed method achieves high accuracy and sensitivity in detecting abnormal seizure activity.
Article
Computer Science, Interdisciplinary Applications
Sungmin You, Baek Hwan Cho, Young-Min Shon, Dae-Won Seo, In Young Kim
Summary: The study proposed a novel personalized deep learning-based anomaly detection algorithm for seizure monitoring using behind-the-ear EEG signals, achieving improved detection accuracy for seizures with high sensitivity and a lower false alarm rate.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Chemistry, Multidisciplinary
Marcin Kolodziej, Andrzej Majkowski, Andrzej Rysz
Summary: This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. It presents standard approaches for analyzing iEEG signals and discusses modern deep learning algorithms. The study shows that CNN and LSTM networks yield significantly better results, and the gradient-weighted class activation mapping algorithm can identify important iEEG signal fragments for seizure detection.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Biomedical
Jiale Zeng, Xiao-dan Tan, Chang'an A. Zhan
Summary: This study utilized prior knowledge to improve seizure detection algorithm, achieving high performance and robustness exceeding other methods in the literature. The levels of EWT and direct use of time-frequency features had the greatest impact on the final seizure detection performance, and KNN and SVM classifiers outperformed RF.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2021)
Article
Engineering, Biomedical
Xuyang Zhao, Noboru Yoshida, Tetsuya Ueda, Hidenori Sugano, Toshihisa Tanaka
Summary: This study applies commonly used models such as LeNet, VGG, ResNet, and ViT to the EEG image classification task, and solves the problems of data imbalance and model interpretation through data augmentation and model explanation methods. The models achieve good performance in seizure detection and provide visual and quantitative information for clinical experts in diagnosis.
JOURNAL OF NEURAL ENGINEERING
(2023)
Article
Chemistry, Multidisciplinary
Zakareya Lasefr, Khaled Elleithy, Ramasani Rakesh Reddy, Eman Abdelfattah, Miad Faezipour
Summary: This paper studied epileptic seizure detection methods based on EEG signals and proposed an enhanced technique with a mobile application for monitoring the classification of EEG signals. The proposed method achieved high accuracy and outperformed previous studies. It will have significant impacts in the medical field and Human-Computer Interaction fields.
APPLIED SCIENCES-BASEL
(2023)
Article
Biology
Asghar Zarei, Babak Mohammadzadeh Asl
Summary: A novel algorithm was developed for automatic seizure detection from EEG signals using DWT and OMP techniques, which improved detection accuracy by extracting signal coefficients, calculating nonlinear features, and statistical features. The proposed OMP-based technique with SVM classifier showed good performance in different classification tasks according to the experimental results.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)