Cargando…
The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation
We compared the performance of deep learning (DL) in the classification of optical coherence tomography (OCT) images of macular diseases between automated classification alone and in combination with automated segmentation. OCT images were collected from patients with neovascular age-related macular...
Autores principales: | , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9858554/ https://www.ncbi.nlm.nih.gov/pubmed/36672999 http://dx.doi.org/10.3390/diagnostics13020189 |
_version_ | 1784874130547408896 |
---|---|
author | Kaothanthong, Natsuda Limwattanayingyong, Jirawut Silpa-archa, Sukhum Tadarati, Mongkol Amphornphruet, Atchara Singhanetr, Panisa Lalitwongsa, Pawas Chantangphol, Pantid Amornpetchsathaporn, Anyarak Chainakul, Methaphon Ruamviboonsuk, Paisan |
author_facet | Kaothanthong, Natsuda Limwattanayingyong, Jirawut Silpa-archa, Sukhum Tadarati, Mongkol Amphornphruet, Atchara Singhanetr, Panisa Lalitwongsa, Pawas Chantangphol, Pantid Amornpetchsathaporn, Anyarak Chainakul, Methaphon Ruamviboonsuk, Paisan |
author_sort | Kaothanthong, Natsuda |
collection | PubMed |
description | We compared the performance of deep learning (DL) in the classification of optical coherence tomography (OCT) images of macular diseases between automated classification alone and in combination with automated segmentation. OCT images were collected from patients with neovascular age-related macular degeneration, polypoidal choroidal vasculopathy, diabetic macular edema, retinal vein occlusion, cystoid macular edema in Irvine-Gass syndrome, and other macular diseases, along with the normal fellow eyes. A total of 14,327 OCT images were used to train DL models. Three experiments were conducted: classification alone (CA), use of automated segmentation of the OCT images by RelayNet, and the graph-cut technique before the classification (combination method 1 (CM1) and 2 (CM2), respectively). For validation of classification of the macular diseases, the sensitivity, specificity, and accuracy of CA were found at 62.55%, 95.16%, and 93.14%, respectively, whereas the sensitivity, specificity, and accuracy of CM1 were found at 72.90%, 96.20%, and 93.92%, respectively, and of CM2 at 71.36%, 96.42%, and 94.80%, respectively. The accuracy of CM2 was statistically higher than that of CA (p = 0.05878). All three methods achieved AUC at 97%. Applying DL for segmentation of OCT images prior to classification of the images by another DL model may improve the performance of the classification. |
format | Online Article Text |
id | pubmed-9858554 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-98585542023-01-21 The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation Kaothanthong, Natsuda Limwattanayingyong, Jirawut Silpa-archa, Sukhum Tadarati, Mongkol Amphornphruet, Atchara Singhanetr, Panisa Lalitwongsa, Pawas Chantangphol, Pantid Amornpetchsathaporn, Anyarak Chainakul, Methaphon Ruamviboonsuk, Paisan Diagnostics (Basel) Article We compared the performance of deep learning (DL) in the classification of optical coherence tomography (OCT) images of macular diseases between automated classification alone and in combination with automated segmentation. OCT images were collected from patients with neovascular age-related macular degeneration, polypoidal choroidal vasculopathy, diabetic macular edema, retinal vein occlusion, cystoid macular edema in Irvine-Gass syndrome, and other macular diseases, along with the normal fellow eyes. A total of 14,327 OCT images were used to train DL models. Three experiments were conducted: classification alone (CA), use of automated segmentation of the OCT images by RelayNet, and the graph-cut technique before the classification (combination method 1 (CM1) and 2 (CM2), respectively). For validation of classification of the macular diseases, the sensitivity, specificity, and accuracy of CA were found at 62.55%, 95.16%, and 93.14%, respectively, whereas the sensitivity, specificity, and accuracy of CM1 were found at 72.90%, 96.20%, and 93.92%, respectively, and of CM2 at 71.36%, 96.42%, and 94.80%, respectively. The accuracy of CM2 was statistically higher than that of CA (p = 0.05878). All three methods achieved AUC at 97%. Applying DL for segmentation of OCT images prior to classification of the images by another DL model may improve the performance of the classification. MDPI 2023-01-04 /pmc/articles/PMC9858554/ /pubmed/36672999 http://dx.doi.org/10.3390/diagnostics13020189 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 Kaothanthong, Natsuda Limwattanayingyong, Jirawut Silpa-archa, Sukhum Tadarati, Mongkol Amphornphruet, Atchara Singhanetr, Panisa Lalitwongsa, Pawas Chantangphol, Pantid Amornpetchsathaporn, Anyarak Chainakul, Methaphon Ruamviboonsuk, Paisan The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation |
title | The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation |
title_full | The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation |
title_fullStr | The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation |
title_full_unstemmed | The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation |
title_short | The Classification of Common Macular Diseases Using Deep Learning on Optical Coherence Tomography Images with and without Prior Automated Segmentation |
title_sort | classification of common macular diseases using deep learning on optical coherence tomography images with and without prior automated segmentation |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9858554/ https://www.ncbi.nlm.nih.gov/pubmed/36672999 http://dx.doi.org/10.3390/diagnostics13020189 |
work_keys_str_mv | AT kaothanthongnatsuda theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT limwattanayingyongjirawut theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT silpaarchasukhum theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT tadaratimongkol theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT amphornphruetatchara theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT singhanetrpanisa theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT lalitwongsapawas theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT chantangpholpantid theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT amornpetchsathapornanyarak theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT chainakulmethaphon theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT ruamviboonsukpaisan theclassificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT kaothanthongnatsuda classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT limwattanayingyongjirawut classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT silpaarchasukhum classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT tadaratimongkol classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT amphornphruetatchara classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT singhanetrpanisa classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT lalitwongsapawas classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT chantangpholpantid classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT amornpetchsathapornanyarak classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT chainakulmethaphon classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation AT ruamviboonsukpaisan classificationofcommonmaculardiseasesusingdeeplearningonopticalcoherencetomographyimageswithandwithoutpriorautomatedsegmentation |