Removing Noise from Extracellular Neural Recordings Using Fully Convolutional Denoising Autoencoders

TL;DR

This paper introduces a deep learning method using Fully Convolutional Denoising Autoencoders to effectively remove noise from extracellular neural recordings, enhancing spike sorting accuracy.

Contribution

It presents a novel end-to-end deep learning approach that outperforms traditional wavelet denoising techniques for neural signal noise reduction.

Findings

Significantly improves neural signal quality

Outperforms wavelet denoising methods

Effective on simulated data

Abstract

Extracellular recordings are severely contaminated by a considerable amount of noise sources, rendering the denoising process an extremely challenging task that should be tackled for efficient spike sorting. To this end, we propose an end-to-end deep learning approach to the problem, utilizing a Fully Convolutional Denoising Autoencoder, which learns to produce a clean neuronal activity signal from a noisy multichannel input. The experimental results on simulated data show that our proposed method can improve significantly the quality of noise-corrupted neural signals, outperforming widely-used wavelet denoising techniques.