Cargando…

Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture

PURPOSE: In this study, an algorithm based on deep learning was presented to reduce the retinal nerve fiber layer (RNFL) segmentation errors in spectral domain optical coherence tomography (SD-OCT) scans using ophthalmologists' manual segmentation as a reference standard. METHODS: In this study...

Descripción completa

Detalles Bibliográficos
Autores principales: Razaghi, Ghazale, Aghsaei Fard, Masoud, Hejazi, Marjaneh
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PUBLISHED BY KNOWLEDGE E 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10020786/
https://www.ncbi.nlm.nih.gov/pubmed/36937200
http://dx.doi.org/10.18502/jovr.v18i1.12724
_version_ 1784908342805659648
author Razaghi, Ghazale
Aghsaei Fard, Masoud
Hejazi, Marjaneh
author_facet Razaghi, Ghazale
Aghsaei Fard, Masoud
Hejazi, Marjaneh
author_sort Razaghi, Ghazale
collection PubMed
description PURPOSE: In this study, an algorithm based on deep learning was presented to reduce the retinal nerve fiber layer (RNFL) segmentation errors in spectral domain optical coherence tomography (SD-OCT) scans using ophthalmologists' manual segmentation as a reference standard. METHODS: In this study, we developed an image segmentation network based on deep learning to automatically identify the RNFL thickness from B-scans obtained with SD-OCT. The scans were collected from Farabi Eye Hospital (500 B-scans were used for training, while 50 were used for testing). To remove the speckle noise from the images, preprocessing was applied before training, and postprocessing was performed to fill any discontinuities that might exist. Afterward, output masks were analyzed for their average thickness. Finally, the calculation of mean absolute error between predicted and ground truth RNFL thickness was performed. RESULTS: Based on the testing database, SD-OCT segmentation had an average dice similarity coefficient of 0.91, and thickness estimation had a mean absolute error of 2.23 [Formula: see text] 2.1 μm. As compared to conventional OCT software algorithms, deep learning predictions were better correlated with the best available estimate during the test period (r(2) = 0.99 vs r(2) = 0.88, respectively; P [Formula: see text] 0.001). CONCLUSION: Our experimental results demonstrate effective and precise segmentation of the RNFL layer with the coefficient of 0.91 and reliable thickness prediction with MAE 2.23 [Formula: see text] 2.1 μm in SD-OCT B-scans. Performance is comparable with human annotation of the RNFL layer and other algorithms according to the correlation coefficient of 0.99 and 0.88, respectively, while artifacts and errors are evident.
format Online
Article
Text
id pubmed-10020786
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher PUBLISHED BY KNOWLEDGE E
record_format MEDLINE/PubMed
spelling pubmed-100207862023-03-18 Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture Razaghi, Ghazale Aghsaei Fard, Masoud Hejazi, Marjaneh J Ophthalmic Vis Res Original Article PURPOSE: In this study, an algorithm based on deep learning was presented to reduce the retinal nerve fiber layer (RNFL) segmentation errors in spectral domain optical coherence tomography (SD-OCT) scans using ophthalmologists' manual segmentation as a reference standard. METHODS: In this study, we developed an image segmentation network based on deep learning to automatically identify the RNFL thickness from B-scans obtained with SD-OCT. The scans were collected from Farabi Eye Hospital (500 B-scans were used for training, while 50 were used for testing). To remove the speckle noise from the images, preprocessing was applied before training, and postprocessing was performed to fill any discontinuities that might exist. Afterward, output masks were analyzed for their average thickness. Finally, the calculation of mean absolute error between predicted and ground truth RNFL thickness was performed. RESULTS: Based on the testing database, SD-OCT segmentation had an average dice similarity coefficient of 0.91, and thickness estimation had a mean absolute error of 2.23 [Formula: see text] 2.1 μm. As compared to conventional OCT software algorithms, deep learning predictions were better correlated with the best available estimate during the test period (r(2) = 0.99 vs r(2) = 0.88, respectively; P [Formula: see text] 0.001). CONCLUSION: Our experimental results demonstrate effective and precise segmentation of the RNFL layer with the coefficient of 0.91 and reliable thickness prediction with MAE 2.23 [Formula: see text] 2.1 μm in SD-OCT B-scans. Performance is comparable with human annotation of the RNFL layer and other algorithms according to the correlation coefficient of 0.99 and 0.88, respectively, while artifacts and errors are evident. PUBLISHED BY KNOWLEDGE E 2023-02-21 /pmc/articles/PMC10020786/ /pubmed/36937200 http://dx.doi.org/10.18502/jovr.v18i1.12724 Text en Copyright © 2023 Razaghi et al . https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Article
Razaghi, Ghazale
Aghsaei Fard, Masoud
Hejazi, Marjaneh
Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture
title Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture
title_full Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture
title_fullStr Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture
title_full_unstemmed Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture
title_short Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture
title_sort correction of retinal nerve fiber layer thickness measurement on spectral-domain optical coherence tomographic images using u-net architecture
topic Original Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10020786/
https://www.ncbi.nlm.nih.gov/pubmed/36937200
http://dx.doi.org/10.18502/jovr.v18i1.12724
work_keys_str_mv AT razaghighazale correctionofretinalnervefiberlayerthicknessmeasurementonspectraldomainopticalcoherencetomographicimagesusingunetarchitecture
AT aghsaeifardmasoud correctionofretinalnervefiberlayerthicknessmeasurementonspectraldomainopticalcoherencetomographicimagesusingunetarchitecture
AT hejazimarjaneh correctionofretinalnervefiberlayerthicknessmeasurementonspectraldomainopticalcoherencetomographicimagesusingunetarchitecture