Lack of Consensus for Manual Mouse Sleep Scoring Limits Implementation of Automatic Deep Learning Models
Laura Rose, Alexander Neergaard Zahid, Javier García Ciudad, Christine Egebjerg, Louise Piilgaard, Frederikke Lynge Sørensen, Mie Maar Andersen, Tessa Radovanovic, Anastasia Tsopanidou, Maiken Nedergaard, Sébastien Arthaud, Renato Marciano Maciel, Christelle Peyron, Chiara Berteotti, Viviana Lo Martire, , Birgitte Rahbek Kornum
This study shows that automatic deep learning models for mouse sleep scoring struggle to generalize across labs due to signal variability and label noise, and proposes four robust models trained on diverse data.
bioRxiv · Mar 30, 2026 · PreprintNeuroscience