NED-Net: an annotation-training loop for rodent EEG event detection
- 1Epilepsy Center, Lund University
Abstract
Long-term EEG monitoring is central to rodent epilepsy research, and manual review is laborious because recordings span hundreds to tens of thousands of animal-hours. Published automated detectors perform well on their development datasets but are typically fixed models that may not adapt to another laboratory's electrodes, animals, or noise conditions. We introduce NED-Net, open-source software for training and maintaining seizure detectors. It uses reviewed candidate events as training labels, runs detection live during recording, and retrains as annotations accumulate. A detector trained on one mouse cohort (867 annotated seizures) achieved 93.6% precision in human review of 171 detections. Applied unchanged to a second cohort on the same acquisition system, its detections were mostly seizures (12 of 13 reviewed), but per-animal recall varied substantially (median 10%), with no convulsive reference seizure detected in four of 11 animals. Retraining with annotations from the second cohort raised convulsive recall from 15% to 64%, with at least one reference seizure detected in every animal. On recordings withheld from training, 75% of detections were seizures and 14 of 22 reference seizures were detected, whereas the source model and a model trained without these animals detected none. NED-Net supports evaluating and adapting detectors to local recordings.
Related
- Development of Loop-Mediated Isothermal Amplification Assays for Rapid and Sensitive Detection of Three Viruses Infecting Areca catechu L.
- MillionTrees: A global benchmark for tree detection across geography, sensor, and annotation geometry
- Goal directed closed-loop training of network bursts in cortical cultures produces improved performance and error correction over days
- Millisecond-scale detection of mouse ultrasonic vocalizations enables closed-loop experiments
- Diagnostic utility of colourimetric readout loop-mediated isothermal amplification assay for rapid detection of Babesia gibsoni at the clinical point-of-care (POC)
BibTeX
@misc{y2026nednet,
title = {{NED-Net: an annotation-training loop for rodent EEG event detection}},
author = {M. Y. MIR and M. Ledri},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.15.759362},
url = {https://www.biorxiv.org/content/10.64898/2026.10.15.759362v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - NED-Net: an annotation-training loop for rodent EEG event detection
AU - M. Y. MIR
AU - M. Ledri
PY - 2026
DA - 2026/10/15
PB - bioRxiv
DO - 10.64898/2026.10.15.759362
UR - https://www.biorxiv.org/content/10.64898/2026.10.15.759362v1
AB - Long-term EEG monitoring is central to rodent epilepsy research, and manual review is laborious because recordings span hundreds to tens of thousands of animal-hours. Published automated detectors perform well on their development datasets but are typically fixed models that may not adapt to another laboratory's electrodes, animals, or noise conditions. We introduce NED-Net, open-source software for training and maintaining seizure detectors. It uses reviewed candidate events as training labels, runs detection live during recording, and retrains as annotations accumulate. A detector trained on one mouse cohort (867 annotated seizures) achieved 93.6% precision in human review of 171 detections. Applied unchanged to a second cohort on the same acquisition system, its detections were mostly seizures (12 of 13 reviewed), but per-animal recall varied substantially (median 10%), with no convulsive reference seizure detected in four of 11 animals. Retraining with annotations from the second cohort raised convulsive recall from 15% to 64%, with at least one reference seizure detected in every animal. On recordings withheld from training, 75% of detections were seizures and 14 of 22 reference seizures were detected, whereas the source model and a model trained without these animals detected none. NED-Net supports evaluating and adapting detectors to local recordings.
ER -