Cargando…

Enhancing Electroretinogram Classification with Multi-Wavelet Analysis and Visual Transformer

The electroretinogram (ERG) is a clinical test that records the retina’s electrical response to light. Analysis of the ERG signal offers a promising way to study different retinal diseases and disorders. Machine learning-based methods are expected to play a pivotal role in achieving the goals of ret...

Descripción completa

Detalles Bibliográficos
Autores principales: Kulyabin, Mikhail, Zhdanov, Aleksei, Dolganov, Anton, Ronkin, Mikhail, Borisov, Vasilii, Maier, Andreas
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10648817/
https://www.ncbi.nlm.nih.gov/pubmed/37960427
http://dx.doi.org/10.3390/s23218727
_version_ 1785135428656955392
author Kulyabin, Mikhail
Zhdanov, Aleksei
Dolganov, Anton
Ronkin, Mikhail
Borisov, Vasilii
Maier, Andreas
author_facet Kulyabin, Mikhail
Zhdanov, Aleksei
Dolganov, Anton
Ronkin, Mikhail
Borisov, Vasilii
Maier, Andreas
author_sort Kulyabin, Mikhail
collection PubMed
description The electroretinogram (ERG) is a clinical test that records the retina’s electrical response to light. Analysis of the ERG signal offers a promising way to study different retinal diseases and disorders. Machine learning-based methods are expected to play a pivotal role in achieving the goals of retinal diagnostics and treatment control. This study aims to improve the classification accuracy of the previous work using the combination of three optimal mother wavelet functions. We apply Continuous Wavelet Transform (CWT) on a dataset of mixed pediatric and adult ERG signals and show the possibility of simultaneous analysis of the signals. The modern Visual Transformer-based architectures are tested on a time-frequency representation of the signals. The method provides 88% classification accuracy for Maximum 2.0 ERG, 85% for Scotopic 2.0, and 91% for Photopic 2.0 protocols, which on average improves the result by 7.6% compared to previous work.
format Online
Article
Text
id pubmed-10648817
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106488172023-10-26 Enhancing Electroretinogram Classification with Multi-Wavelet Analysis and Visual Transformer Kulyabin, Mikhail Zhdanov, Aleksei Dolganov, Anton Ronkin, Mikhail Borisov, Vasilii Maier, Andreas Sensors (Basel) Article The electroretinogram (ERG) is a clinical test that records the retina’s electrical response to light. Analysis of the ERG signal offers a promising way to study different retinal diseases and disorders. Machine learning-based methods are expected to play a pivotal role in achieving the goals of retinal diagnostics and treatment control. This study aims to improve the classification accuracy of the previous work using the combination of three optimal mother wavelet functions. We apply Continuous Wavelet Transform (CWT) on a dataset of mixed pediatric and adult ERG signals and show the possibility of simultaneous analysis of the signals. The modern Visual Transformer-based architectures are tested on a time-frequency representation of the signals. The method provides 88% classification accuracy for Maximum 2.0 ERG, 85% for Scotopic 2.0, and 91% for Photopic 2.0 protocols, which on average improves the result by 7.6% compared to previous work. MDPI 2023-10-26 /pmc/articles/PMC10648817/ /pubmed/37960427 http://dx.doi.org/10.3390/s23218727 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kulyabin, Mikhail
Zhdanov, Aleksei
Dolganov, Anton
Ronkin, Mikhail
Borisov, Vasilii
Maier, Andreas
Enhancing Electroretinogram Classification with Multi-Wavelet Analysis and Visual Transformer
title Enhancing Electroretinogram Classification with Multi-Wavelet Analysis and Visual Transformer
title_full Enhancing Electroretinogram Classification with Multi-Wavelet Analysis and Visual Transformer
title_fullStr Enhancing Electroretinogram Classification with Multi-Wavelet Analysis and Visual Transformer
title_full_unstemmed Enhancing Electroretinogram Classification with Multi-Wavelet Analysis and Visual Transformer
title_short Enhancing Electroretinogram Classification with Multi-Wavelet Analysis and Visual Transformer
title_sort enhancing electroretinogram classification with multi-wavelet analysis and visual transformer
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10648817/
https://www.ncbi.nlm.nih.gov/pubmed/37960427
http://dx.doi.org/10.3390/s23218727
work_keys_str_mv AT kulyabinmikhail enhancingelectroretinogramclassificationwithmultiwaveletanalysisandvisualtransformer
AT zhdanovaleksei enhancingelectroretinogramclassificationwithmultiwaveletanalysisandvisualtransformer
AT dolganovanton enhancingelectroretinogramclassificationwithmultiwaveletanalysisandvisualtransformer
AT ronkinmikhail enhancingelectroretinogramclassificationwithmultiwaveletanalysisandvisualtransformer
AT borisovvasilii enhancingelectroretinogramclassificationwithmultiwaveletanalysisandvisualtransformer
AT maierandreas enhancingelectroretinogramclassificationwithmultiwaveletanalysisandvisualtransformer