Unsupervised neural spike sorting for high-density microelectrode arrays with convolutive independent component analysis

- We propose an unsupervised spike sorting algorithm that accounts for spike overlaps and performed comparable to a supervised algorithm.
- Spike sorting performance was assessed with ground-truth data on 4365 electrodes - generated from experimentally derived templates.
- We show how ICA based spike sorting has to be extended in order to retrieve a larger number of accurately sorted neural spike trains.
- Our new algorithm constitutes a fast solution for spike sorting data from thousands of electrodes.

BackgroundUnsupervised identification of action potentials in multi-channel extracellular recordings, in particular from high-density microelectrode arrays with thousands of sensors, is an unresolved problem. While independent component analysis (ICA) achieves rapid unsupervised sorting, it ignores the convolutive structure of extracellular data, thus limiting the unmixing to a subset of neurons.New methodHere we present a spike sorting algorithm based on convolutive ICA (cICA) to retrieve a larger number of accurately sorted neurons than with instantaneous ICA while accounting for signal overlaps. Spike sorting was applied to datasets with varying signal-to-noise ratios (SNR: 3-12) and 27% spike overlaps, sampled at either 11.5 or 23 kHz on 4365 electrodes.ResultsWe demonstrate how the instantaneity assumption in ICA-based algorithms has to be relaxed in order to improve the spike sorting performance for high-density microelectrode array recordings. Reformulating the convolutive mixture as an instantaneous mixture by modeling several delayed samples jointly is necessary to increase signal-to-noise ratio. Our results emphasize that different cICA algorithms are not equivalent.Comparison with existing methodsSpike sorting performance was assessed with ground-truth data generated from experimentally derived templates. The presented spike sorter was able to extract ≈90% of the true spike trains with an error rate below 2%. It was superior to two alternative (c)ICA methods (≈80% accurately sorted neurons) and comparable to a supervised sorting.ConclusionOur new algorithm represents a fast solution to overcome the current bottleneck in spike sorting of large datasets generated by simultaneous recording with thousands of electrodes.