Cargando…

Non-stationary neural signal to image conversion framework for image-based deep learning algorithms

This paper presents a time-efficient preprocessing framework that converts any given 1D physiological signal recordings into a 2D image representation for training image-based deep learning models. The non-stationary signal is rasterized into the 2D image using Bresenham’s line algorithm with time c...

Descripción completa

Detalles Bibliográficos
Autores principales: Patel, Sahaj Anilbhai, Yildirim, Abidin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10079945/
https://www.ncbi.nlm.nih.gov/pubmed/37035716
http://dx.doi.org/10.3389/fninf.2023.1081160
_version_ 1785020815418327040
author Patel, Sahaj Anilbhai
Yildirim, Abidin
author_facet Patel, Sahaj Anilbhai
Yildirim, Abidin
author_sort Patel, Sahaj Anilbhai
collection PubMed
description This paper presents a time-efficient preprocessing framework that converts any given 1D physiological signal recordings into a 2D image representation for training image-based deep learning models. The non-stationary signal is rasterized into the 2D image using Bresenham’s line algorithm with time complexity O(n). The robustness of the proposed approach is evaluated based on two publicly available datasets. This study classified three different neural spikes (multi-class) and EEG epileptic seizure and non-seizure (binary class) based on shapes using a modified 2D Convolution Neural Network (2D CNN). The multi-class dataset consists of artificially simulated neural recordings with different Signal-to-Noise Ratios (SNR). The 2D CNN architecture showed significant performance for all individual SNRs scores with (SNR/ACC): 0.5/99.69, 0.75/99.69, 1.0/99.49, 1.25/98.85, 1.5/97.43, 1.75/95.20 and 2.0/91.98. Additionally, the binary class dataset also achieved 97.52% accuracy by outperforming several others proposed algorithms. Likewise, this approach could be employed on other biomedical signals such as Electrocardiograph (EKG) and Electromyography (EMG).
format Online
Article
Text
id pubmed-10079945
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-100799452023-04-08 Non-stationary neural signal to image conversion framework for image-based deep learning algorithms Patel, Sahaj Anilbhai Yildirim, Abidin Front Neuroinform Neuroscience This paper presents a time-efficient preprocessing framework that converts any given 1D physiological signal recordings into a 2D image representation for training image-based deep learning models. The non-stationary signal is rasterized into the 2D image using Bresenham’s line algorithm with time complexity O(n). The robustness of the proposed approach is evaluated based on two publicly available datasets. This study classified three different neural spikes (multi-class) and EEG epileptic seizure and non-seizure (binary class) based on shapes using a modified 2D Convolution Neural Network (2D CNN). The multi-class dataset consists of artificially simulated neural recordings with different Signal-to-Noise Ratios (SNR). The 2D CNN architecture showed significant performance for all individual SNRs scores with (SNR/ACC): 0.5/99.69, 0.75/99.69, 1.0/99.49, 1.25/98.85, 1.5/97.43, 1.75/95.20 and 2.0/91.98. Additionally, the binary class dataset also achieved 97.52% accuracy by outperforming several others proposed algorithms. Likewise, this approach could be employed on other biomedical signals such as Electrocardiograph (EKG) and Electromyography (EMG). Frontiers Media S.A. 2023-03-24 /pmc/articles/PMC10079945/ /pubmed/37035716 http://dx.doi.org/10.3389/fninf.2023.1081160 Text en Copyright © 2023 Patel and Yildirim. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Patel, Sahaj Anilbhai
Yildirim, Abidin
Non-stationary neural signal to image conversion framework for image-based deep learning algorithms
title Non-stationary neural signal to image conversion framework for image-based deep learning algorithms
title_full Non-stationary neural signal to image conversion framework for image-based deep learning algorithms
title_fullStr Non-stationary neural signal to image conversion framework for image-based deep learning algorithms
title_full_unstemmed Non-stationary neural signal to image conversion framework for image-based deep learning algorithms
title_short Non-stationary neural signal to image conversion framework for image-based deep learning algorithms
title_sort non-stationary neural signal to image conversion framework for image-based deep learning algorithms
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10079945/
https://www.ncbi.nlm.nih.gov/pubmed/37035716
http://dx.doi.org/10.3389/fninf.2023.1081160
work_keys_str_mv AT patelsahajanilbhai nonstationaryneuralsignaltoimageconversionframeworkforimagebaseddeeplearningalgorithms
AT yildirimabidin nonstationaryneuralsignaltoimageconversionframeworkforimagebaseddeeplearningalgorithms