E-Sort: Empowering End-to-end Neural Network for Multi-channel Spike Sorting with Transfer Learning and Fast Post-processing

TL;DR

E-Sort is an end-to-end neural network-based spike sorting framework that leverages transfer learning and fast post-processing to improve accuracy and speed in decoding extracellular neural recordings, especially for multi-channel data.

Contribution

It introduces a novel transfer learning approach and a compatible post-processing algorithm, significantly reducing training data needs and increasing processing speed for spike sorting.

Findings

Reduces training data by 44%

Achieves up to 25.68% higher accuracy

Sorts 50 seconds of data in 1.32 seconds

Abstract

Decoding extracellular recordings is a crucial task in electrophysiology and brain-computer interfaces. Spike sorting, which distinguishes spikes and their putative neurons from extracellular recordings, becomes computationally demanding with the increasing number of channels in modern neural probes. To address the intensive workload and complex neuron interactions, we propose E-Sort, an end-to-end neural network-based spike sorter with transfer learning and parallelizable post-processing. Our framework reduces the required number of annotated spikes for training by 44% compared to training from scratch, achieving up to 25.68% higher accuracy. Additionally, our novel post-processing algorithm is compatible with deep learning frameworks, making E-Sort significantly faster than state-of-the-art spike sorters. On synthesized Neuropixels recordings, E-Sort achieves comparable accuracy with Kilosort4 while sorting 50 seconds of data in only 1.32 seconds. Our method demonstrates robustness across various probe geometries, noise levels, and drift conditions, offering a substantial improvement in both accuracy and runtime efficiency compared to existing spike sorters.