A review of epilepsy detection and prediction methods based on EEG signal processing and deep learning DOI Creative Commons
Xizhen Zhang,

Xiaoli Zhang,

Qiong Huang

et al.

Frontiers in Neuroscience, Journal Year: 2024, Volume and Issue: 18

Published: Nov. 15, 2024

Epilepsy is a chronic neurological disorder that poses significant challenges to patients and their families. Effective detection prediction of epilepsy can facilitate patient recovery, reduce family burden, streamline healthcare processes. Therefore, it essential propose deep learning method for efficient epileptic electroencephalography (EEG) signals. This paper reviews several key aspects EEG signal processing, focusing on prediction. It covers publicly available datasets, preprocessing techniques, feature extraction methods, learning-based networks used in these tasks. The literature categorized based independence, distinguishing between patient-independent non-patient-independent studies. Additionally, the evaluation methods are classified into general classification indicators specific criteria, with findings organized according cycles reported various review reveals important insights. Despite availability public they often lack diversity types collected under controlled conditions may not reflect real-world scenarios. As result, tend be limited fully represent practical conditions. Feature network designs frequently emphasize fusion mechanisms, recent advances Convolutional Neural Networks (CNNs) Recurrent (RNNs) showing promising results, suggesting new models warrant further exploration. Studies using data generally produce better results than those relying data. Metrics typically perform though future research should focus latter more accurate evaluation. kept 1 h, most studies concentrating intervals 30 min or less.

Language: Английский

Natural Language Processing in medicine and ophthalmology: A review for the 21st-century clinician DOI Creative Commons
William Rojas‐Carabali,

Rajdeep Agrawal,

Laura Gutiérrez-Sinisterra

et al.

Asia-Pacific Journal of Ophthalmology, Journal Year: 2024, Volume and Issue: 13(4), P. 100084 - 100084

Published: July 1, 2024

Natural Language Processing (NLP) is a subfield of artificial intelligence that focuses on the interaction between computers and human language, enabling to understand, generate, derive meaning from language. NLP's potential applications in medical field are extensive vary extracting data Electronic Health Records -one its most well-known frequently exploited uses- investigating relationships among genetics, biomarkers, drugs, diseases for proposal new medications. NLP can be useful clinical decision support, patient monitoring, or image analysis. Despite vast potential, real-world application still limited due various challenges constraints, evolution predominantly continues within research domain. However, with increasingly widespread use NLP, particularly availability large language models, such as ChatGPT, it crucial professionals aware status, uses, limitations these technologies.

Language: Английский

Citations

5
EEG Sinyallerini Kullanarak 2D Konvolüsyonel Sinir Ağları ile Epilepsi Hastalığının Çok Sınıflı Tespiti DOI Open Access

Yiğithan Geniş,

Eda Akman Aydın

Journal of Polytechnic, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 1

Published: April 12, 2025

Elektroensefalogram (EEG) epilepsi hastalığının teşhisi için önemli bir sinyaldir. Transfer öğrenme, veri boyutlarının model eğitimi yeterli olmadığı durumlarda, önceden eğitilmiş ağırlıklarının yeni problemlerde kullanılmasını sağlayan tekniktir. Bu çalışmada, transfer öğrenme modelleri sağlıklı gözü açık, kapalı, nöbet anında olmayan hastadan epileptojenik bölgenin karşısından kaydedilmiş, bölgeden kaydedilmiş ve anındaki EEG sinyal örneklerinin sınıflandırılması amacıyla kullanılmıştır. Sinyallerin, 2D CNN modelinde kullanılmak üzere zaman-frekans gösterimini elde edebilmek Sürekli Dalgacık Dönüşümü (CWT) ile skalogram görüntüleri edilerek konvolüsyonel sinir ağı (CNN) giriş olarak Çalışmanın sonuçları GoogleNet modelinin CWT gösterimi kullanılarak teşhisinde en başarılı olduğunu, önerilen yöntemin beş duruma ait sinyallerini %95.33 doğrulukla ayırt edebildiğini göstermektedir.

Citations

0
Multi-scale convolutional transformer network for motor imagery brain-computer interface DOI Creative Commons
Wei Zhao, Baocan Zhang, Haifeng Zhou

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 15, 2025

Abstract Brain-computer interface (BCI) systems allow users to communicate with external devices by translating neural signals into real-time commands. Convolutional networks (CNNs) have been effectively utilized for decoding motor imagery electroencephalography (MI-EEG) in BCIs. However, traditional CNN-based methods face challenges such as individual variability EEG and the limited receptive fields of CNNs. This study presents Multi-Scale Transformer (MSCFormer) model that integrates multiple CNN branches multi-scale feature extraction a module capture global dependencies, followed fully connected layer classification. The multi-branch structure addresses signals, enhancing model’s generalization capabilities, while encoder strengthens integration improves performance. Extensive experiments on BCI IV-2a IV-2b datasets show MSCFormer achieves average accuracies 82.95% (BCI IV-2a) 88.00% IV-2b), kappa values 0.7726 0.7599 five-fold cross-validation, surpassing several state-of-the-art methods. These results highlight MSCFormer’s robustness accuracy, underscoring its potential EEG-based applications. code has released https://github.com/snailpt/MSCFormer .

Language: Английский

Citations

0
Electroencephalogram (EEG) classification using a bio-inspired deep oscillatory neural network DOI
Sayan Ghosh,

Vigneswaran Chandrasekaran,

NR Rohan

et al.

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 103, P. 107379 - 107379

Published: Dec. 26, 2024

Language: Английский

Citations

2
A review of epilepsy detection and prediction methods based on EEG signal processing and deep learning DOI Creative Commons
Xizhen Zhang,

Xiaoli Zhang,

Qiong Huang

et al.

Frontiers in Neuroscience, Journal Year: 2024, Volume and Issue: 18

Published: Nov. 15, 2024

Epilepsy is a chronic neurological disorder that poses significant challenges to patients and their families. Effective detection prediction of epilepsy can facilitate patient recovery, reduce family burden, streamline healthcare processes. Therefore, it essential propose deep learning method for efficient epileptic electroencephalography (EEG) signals. This paper reviews several key aspects EEG signal processing, focusing on prediction. It covers publicly available datasets, preprocessing techniques, feature extraction methods, learning-based networks used in these tasks. The literature categorized based independence, distinguishing between patient-independent non-patient-independent studies. Additionally, the evaluation methods are classified into general classification indicators specific criteria, with findings organized according cycles reported various review reveals important insights. Despite availability public they often lack diversity types collected under controlled conditions may not reflect real-world scenarios. As result, tend be limited fully represent practical conditions. Feature network designs frequently emphasize fusion mechanisms, recent advances Convolutional Neural Networks (CNNs) Recurrent (RNNs) showing promising results, suggesting new models warrant further exploration. Studies using data generally produce better results than those relying data. Metrics typically perform though future research should focus latter more accurate evaluation. kept 1 h, most studies concentrating intervals 30 min or less.

Language: Английский

Citations

0