RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure

Abstract Glaucoma is the leading cause of irreversible blindness in the world, affecting over 70 million people. The cumbersome Standard Automated Perimetry (SAP) test is most frequently used to detect visual loss due to glaucoma. Due to the SAP test’s innate difficulty and its high test-retest vari...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shounak Datta, Eduardo B. Mariottoni, David Dov, Alessandro A. Jammal, Lawrence Carin, Felipe A. Medeiros
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c941d8aad29d42f58a89fbd61fdda5ca
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c941d8aad29d42f58a89fbd61fdda5ca
record_format	dspace
spelling	oai:doaj.org-article:c941d8aad29d42f58a89fbd61fdda5ca2021-12-02T16:04:13ZRetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure10.1038/s41598-021-91493-92045-2322https://doaj.org/article/c941d8aad29d42f58a89fbd61fdda5ca2021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-91493-9https://doaj.org/toc/2045-2322Abstract Glaucoma is the leading cause of irreversible blindness in the world, affecting over 70 million people. The cumbersome Standard Automated Perimetry (SAP) test is most frequently used to detect visual loss due to glaucoma. Due to the SAP test’s innate difficulty and its high test-retest variability, we propose the RetiNerveNet, a deep convolutional recursive neural network for obtaining estimates of the SAP visual field. RetiNerveNet uses information from the more objective Spectral-Domain Optical Coherence Tomography (SDOCT). RetiNerveNet attempts to trace-back the arcuate convergence of the retinal nerve fibers, starting from the Retinal Nerve Fiber Layer (RNFL) thickness around the optic disc, to estimate individual age-corrected 24-2 SAP values. Recursive passes through the proposed network sequentially yield estimates of the visual locations progressively farther from the optic disc. While all the methods used for our experiments exhibit lower performance for the advanced disease group (possibly due to the “floor effect” for the SDOCT test), the proposed network is observed to be more accurate than all the baselines for estimating the individual visual field values. We further augment the proposed network to additionally predict the SAP Mean Deviation values and also facilitate the assignment of higher weightage to the underrepresented groups in the data. We then study the resulting performance trade-offs of the RetiNerveNet on the early, moderate and severe disease groups.Shounak DattaEduardo B. MariottoniDavid DovAlessandro A. JammalLawrence CarinFelipe A. MedeirosNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Shounak Datta Eduardo B. Mariottoni David Dov Alessandro A. Jammal Lawrence Carin Felipe A. Medeiros RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure
description	Abstract Glaucoma is the leading cause of irreversible blindness in the world, affecting over 70 million people. The cumbersome Standard Automated Perimetry (SAP) test is most frequently used to detect visual loss due to glaucoma. Due to the SAP test’s innate difficulty and its high test-retest variability, we propose the RetiNerveNet, a deep convolutional recursive neural network for obtaining estimates of the SAP visual field. RetiNerveNet uses information from the more objective Spectral-Domain Optical Coherence Tomography (SDOCT). RetiNerveNet attempts to trace-back the arcuate convergence of the retinal nerve fibers, starting from the Retinal Nerve Fiber Layer (RNFL) thickness around the optic disc, to estimate individual age-corrected 24-2 SAP values. Recursive passes through the proposed network sequentially yield estimates of the visual locations progressively farther from the optic disc. While all the methods used for our experiments exhibit lower performance for the advanced disease group (possibly due to the “floor effect” for the SDOCT test), the proposed network is observed to be more accurate than all the baselines for estimating the individual visual field values. We further augment the proposed network to additionally predict the SAP Mean Deviation values and also facilitate the assignment of higher weightage to the underrepresented groups in the data. We then study the resulting performance trade-offs of the RetiNerveNet on the early, moderate and severe disease groups.
format	article
author	Shounak Datta Eduardo B. Mariottoni David Dov Alessandro A. Jammal Lawrence Carin Felipe A. Medeiros
author_facet	Shounak Datta Eduardo B. Mariottoni David Dov Alessandro A. Jammal Lawrence Carin Felipe A. Medeiros
author_sort	Shounak Datta
title	RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure
title_short	RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure
title_full	RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure
title_fullStr	RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure
title_full_unstemmed	RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure
title_sort	retinervenet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/c941d8aad29d42f58a89fbd61fdda5ca
work_keys_str_mv	AT shounakdatta retinervenetusingrecursivedeeplearningtoestimatepointwise242visualfielddatabasedonretinalstructure AT eduardobmariottoni retinervenetusingrecursivedeeplearningtoestimatepointwise242visualfielddatabasedonretinalstructure AT daviddov retinervenetusingrecursivedeeplearningtoestimatepointwise242visualfielddatabasedonretinalstructure AT alessandroajammal retinervenetusingrecursivedeeplearningtoestimatepointwise242visualfielddatabasedonretinalstructure AT lawrencecarin retinervenetusingrecursivedeeplearningtoestimatepointwise242visualfielddatabasedonretinalstructure AT felipeamedeiros retinervenetusingrecursivedeeplearningtoestimatepointwise242visualfielddatabasedonretinalstructure
_version_	1718385298989121536

RetiNerveNet: using recursive deep learning to estimate pointwise 24-2 visual field data based on retinal structure

Ejemplares similares