Motion Artifact Removal in Functional Near‐Infrared Spectroscopy Based on Long Short‐Term Memory‐Autoencoder Model

ABSTRACT Motion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily on expert‐based knowledge and optimal selection of model parameters within brain regions. In this paper, we propose a deep learning denoising...

Full description

Saved in:
Bibliographic Details
Published in:The European journal of neuroscience Vol. 61; no. 2
Main Authors: Yang, Pan, Wang, Junhong, Wang, Ting, Li, Lihua, Xu, Dongjuan, Xi, Xugang
Format: Journal Article
Language:English
Published: Chichester Wiley Subscription Services, Inc 01.01.2025
Subjects:
Algorithms
Deep learning
functional near‐infrared spectroscopy
Hemodynamics
Infrared spectroscopy
LSTM‐AE
Morphology
motion
Neural networks
reconstruct hemodynamic response
Spectrum analysis
Statistical analysis
ISSN:0953-816X, 1460-9568
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:ABSTRACT Motion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily on expert‐based knowledge and optimal selection of model parameters within brain regions. In this paper, we propose a deep learning denoising model based on long short‐term memory (LSTM)‐autoencoder (viz., LSTM‐AE) to reduce motion artifacts. By training a neural network to reconstruct hemodynamic response coupled with neuronal activity, LSTM‐AE achieves positive denoising results on both our synthesized noisy simulated dataset and the real dataset. The LSTM‐AE processes the raw fNIRS in three phases: (1) Morphological feature extraction of the raw fNIRS is conducted through the encoder module. (2) The LSTM module captures temporal correlations between individual samples to enhance features. (3) The decoder module recovers and reconstructs the morphological feature information of fNIRS from the latent space. Finally, clean reconstructed fNIRS is generated at the output layer. We compare our proposed method with existing calibration algorithms for hemodynamic response estimation using the following metrics: mean square error (MSE), Pearson's correlation (R2), signal‐to‐noise ratio (SNR), and percent deviation ratio (PDR). The proposed LSTM‐AE method outperforms conventional methods, demonstrating an improvement in all these metrics. Additionally, the proposed LSTM‐AE method shows statistically significant differences from other motion artifact algorithms in terms of effectiveness (p < 0.01, significance level α = 0.05). This study demonstrates the potential of deep network architectures to remove motion artifacts in fNIRS data. We propose a deep learning denoising model based on long short‐term memory (LSTM)‐autoencoder (viz., LSTM‐AE) to reduce motion artifacts. By training a neural network to reconstruct hemodynamic response coupled with neuronal activity, LSTM‐AE achieves positive denoising results on both our synthesized noisy simulated dataset and the real dataset. This study demonstrates the potential of deep network architectures to remove motion artifacts in fNIRS data.
Bibliography:Edited by
Funding
This work was supported by the National Natural Science Foundation of China (Nos. 62371178 and 62301197), Zhejiang Provincial Key Research and Development Program of China (No. 2024C03041), and Zhejiang Provincial Natural Science Foundation of China (No. LTGY23H180020).
John Foxe
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0953-816X
1460-9568
DOI:10.1111/ejn.16679