🏠 Home 📁 File Manager

🧠 EEG Analysis Platform

Advanced EEG automated labeling for seizure detection

About the Platform

The EEG Analysis Platform is a web-based tool designed to showcase EEG labeling system. This platform enables researchers and clinicians to visualize electroencephalography signals in bilateral montage and leverage machine learning models for automated event detection and classification.

📌 Browser Compatibility: This application is optimized for Chrome and Edge browsers for the best performance and compatibility.

Key Features

📁 Directory-Based Loading

Load entire directories containing EDF (European Data Format) files for batch processing and analysis.

🏷️ CSV Label Integration

Import labels via CSV files with the same name as EDF files. Columns: channel, start_time, stop_time, label, confidence.

📊 Bilateral Montage Visualization

View EEG signals in standard bilateral montage with clear, interactive visualization of all channels.

🤖 AI-Powered Prediction

Utilize trained machine learning models to automatically predict and label events in unlabeled EEG segments.

📈 Label Overlay Display

Seamlessly visualize predicted and manual labels alongside the raw EEG signal for easy comparison and validation.

⚡ Caching

Results are cached to improve performance and reduce redundant computations.

Platform Goal

This platform serves as a demonstration tool for EEG labeling system. It showcases the integration of signal processing techniques with machine learning models trained on large-scale clinical datasets, aiming to improve the accuracy and efficiency of seizure detection and EEG event classification.

🤝 Collaborate With Us

We welcome collaboration opportunities, feedback, and discussions about EEG analysis and machine learning applications in neurophysiology.

📧 Contact us at: info@palmaf.com

Acknowledgments

The machine learning models implemented in this platform were trained using data from the following datasets. We gratefully acknowledge the contributions of these research teams:

Dataset Citations:

TUSZ - Temple University Seizure Detection Corpus

Shah, V., von Weltin, E., Lopez. S., McHugh, J., Veloso, L., Golmohammadi, M., Obeid, I., and Picone, J. (2018). The Temple University Hospital Seizure Detection Corpus. Frontiers in Neuroinformatics. 12:83. doi: 10.3389/fninf.2018.00083

TUEV - Temple University EEG Events Corpus

Harati, A., Golmohammadi, M., Lopez, S., Obeid, I., & Picone, J. (2015). Improved EEG Event Classification Using Differential Energy. Proceedings of the IEEE Signal Processing in Medicine and Biology Symposium (pp. 1-4). Philadelphia, Pennsylvania, USA.

TUAR - Temple University Artifact Corpus

Buckwalter, G., Chhin, S., Rahman, S., Obeid, I., & Picone, J. (2021). Recent Advances in the TUH EEG Corpus: Improving the Interrater Agreement for Artifacts and Epileptiform Events. In I. Obeid, I. Selesnick, & J. Picone (Eds.), Proceedings of the IEEE Signal Processing in Medicine and Biology Symposium (SPMB) (pp. 1–3). IEEE. https://doi.org/10.1109/SPMB52430.2021.9672302