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

2024-09-19

AI Summary

To address key challenges in extracellular spike sorting from high-channel-count neural probes—including low sorting accuracy, high computational cost, strong dependence on manual annotations, and poor robustness—this paper proposes an end-to-end convolutional-recurrent neural network architecture, integrated with cross-dataset transfer learning and a graph-optimization-based parallel post-processing algorithm. We introduce the first lightweight, framework-agnostic post-processing module compatible with mainstream deep learning platforms, reducing annotation effort by 44% and improving sorting accuracy by up to 25.68%. On Neuropixels synthetic data, our method achieves accuracy comparable to Kilosort4 while processing 50 seconds of data in just 1.32 seconds. The approach demonstrates strong generalization across probe configurations, noise conditions, and signal drift, simultaneously achieving high accuracy, real-time efficiency, and minimal annotation overhead.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Hardware-aware ML
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Data transparency and provenance

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.

Problem

• Neuronal Signal Decoding
• High-Density Electrodes
• Spike Sorting

Innovation

• E-Sort
• Advanced Neural Networks
• High Precision and Speed