A database and deep learning toolbox for noise-optimized, generalized spike inference from calcium imaging

Rupprecht et al. compiled a large database of simultaneous electrophysiological and calcium recordings from the same neurons. An algorithm (termed CASCADE) trained with this ground truth enables reliable spike inference without the need to tune parameters. Inference of action potentials ('spikes') from neuronal calcium signals is complicated by the scarcity of simultaneous measurements of action potentials and calcium signals ('ground truth'). In this study, we compiled a large, diverse ground truth database from publicly available and newly performed recordings in zebrafish and mice covering a broad range of calcium indicators, cell types and signal-to-noise ratios, comprising a total of more than 35 recording hours from 298 neurons. We developed an algorithm for spike inference (termed CASCADE) that is based on supervised deep networks, takes advantage of the ground truth database, infers absolute spike rates and outperforms existing model-based algorithms. To optimize performance for unseen imaging data, CASCADE retrains itself by resampling ground truth data to match the respective sampling rate and noise level; therefore, no parameters need to be adjusted by the user. In addition, we developed systematic performance assessments for unseen data, openly released a resource toolbox and provide a user-friendly cloud-based implementation.

Automated summary

Researchers developed an algorithm for spike inference (CASCADE) based on supervised deep networks, utilizing a large ground truth database to infer absolute spike rates and outperforming existing model-based algorithms. CASCADE optimizes performance for unseen data by resampling ground truth data, matching the respective sampling rate and noise level, without the need for user adjustment of any parameters.