USC-InfoLab/NeuroGNN

NeuroGNN is a state-of-the-art framework for precise seizure detection and classification from EEG data. It employs dynamic Graph Neural Networks (GNNs) to capture intricate spatial, temporal, semantic, and taxonomic correlations between EEG electrode locations and brain regions, resulting in improved accuracy. Presented at PAKDD '24.

34
/ 100
Emerging

This project helps medical professionals, specifically neurologists and clinical neurophysiologists, more accurately detect and classify epileptic seizures from EEG data. You provide raw or preprocessed EEG recordings, and it outputs precise indications of seizure presence and their specific types. It's designed for practitioners who interpret EEG results for diagnosis and treatment planning.

No commits in the last 6 months.

Use this if you need an advanced, high-precision tool to analyze complex EEG patterns for identifying and categorizing seizures.

Not ideal if you are looking for a simple, off-the-shelf EEG visualization or basic anomaly detection tool without specific seizure analysis capabilities.

epilepsy-diagnosis clinical-neurophysiology EEG-interpretation neurological-disorders seizure-monitoring
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

52

Forks

5

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/USC-InfoLab/NeuroGNN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.