Abstract Body

AIMS: Sharp-wave ripples (SWR) are high frequency events recorded in the local field potential (LFP) of the hippocampus of rodents and humans. During SWR, the sequential firing of ensembles of neurons acts to reactivate memory traces of previously encoded experience. SWR-related interventions can influence hippocampal-dependent cognitive function, making their real-time detection crucial to understand underlying mechanisms. Moreover, with the advent of ultra-dense recordings the need to automatic detection is pressing.

METHODS: Here, we introduce a 1D convolutional neural network (CNN) operating over high-density LFP recordings to detect hippocampal SWR both offline and on-line. The adapted architecture included seven convolutional deep layers composed of different filters to process 8-channel LFP inputs in increasing hierarchical complexity and one output layer delivering the probability of an occurring SWR.

RESULTS: We report offline performance on several types of recordings (e.g. linear arrays, high-density probes, ultradense Neuropixels) as well as on open databases that were not used for training. By saturating the operation of different filters, we examine and interpret their optimal behaviour associated to the ground truth versus a random selection. We then use dimensionality reduction techniques to visualize how the network evolve across learning. Finally, we show how by building a plug-in for a widely used open system such Open Ephys, our method detects SWRs in real time.

CONCLUSIONS: We conclude this approach can be used as a discovery tool for better understanding the dynamics of SWR.