Deep learning for gradability classification of handheld, non-mydriatic retinal images

Abstract Screening effectively identifies patients at risk of sight-threatening diabetic retinopathy (STDR) when retinal images are captured through dilated pupils. Pharmacological mydriasis is not logistically feasible in non-clinical, community DR screening, where acquiring gradable retinal images...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Paul Nderitu, Joan M. Nunez do Rio, Rajna Rasheed, Rajiv Raman, Ramachandran Rajalakshmi, Christos Bergeles, Sobha Sivaprasad, for the SMART India Study Group
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/594f097782804df78a12ee67fe218b74
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:594f097782804df78a12ee67fe218b74
record_format	dspace
spelling	oai:doaj.org-article:594f097782804df78a12ee67fe218b742021-12-02T14:49:43ZDeep learning for gradability classification of handheld, non-mydriatic retinal images10.1038/s41598-021-89027-42045-2322https://doaj.org/article/594f097782804df78a12ee67fe218b742021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-89027-4https://doaj.org/toc/2045-2322Abstract Screening effectively identifies patients at risk of sight-threatening diabetic retinopathy (STDR) when retinal images are captured through dilated pupils. Pharmacological mydriasis is not logistically feasible in non-clinical, community DR screening, where acquiring gradable retinal images using handheld devices exhibits high technical failure rates, reducing STDR detection. Deep learning (DL) based gradability predictions at acquisition could prompt device operators to recapture insufficient quality images, increasing gradable image proportions and consequently STDR detection. Non-mydriatic retinal images were captured as part of SMART India, a cross-sectional, multi-site, community-based, house-to-house DR screening study between August 2018 and December 2019 using the Zeiss Visuscout 100 handheld camera. From 18,277 patient eyes (40,126 images), 16,170 patient eyes (35,319 images) were eligible and 3261 retinal images (1490 patient eyes) were sampled then labelled by two ophthalmologists. Compact DL model area under the receiver operator characteristic curve was 0.93 (0.01) following five-fold cross-validation. Compact DL model agreement (Kappa) were 0.58, 0.69 and 0.69 for high specificity, balanced sensitivity/specificity and high sensitivity operating points compared to an inter-grader agreement of 0.59. Compact DL gradability model performance was favourable compared to ophthalmologists. Compact DL models can effectively classify non-mydriatic, handheld retinal image gradability with potential applications within community-based DR screening.Paul NderituJoan M. Nunez do RioRajna RasheedRajiv RamanRamachandran RajalakshmiChristos BergelesSobha Sivaprasadfor the SMART India Study GroupNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Paul Nderitu Joan M. Nunez do Rio Rajna Rasheed Rajiv Raman Ramachandran Rajalakshmi Christos Bergeles Sobha Sivaprasad for the SMART India Study Group Deep learning for gradability classification of handheld, non-mydriatic retinal images
description	Abstract Screening effectively identifies patients at risk of sight-threatening diabetic retinopathy (STDR) when retinal images are captured through dilated pupils. Pharmacological mydriasis is not logistically feasible in non-clinical, community DR screening, where acquiring gradable retinal images using handheld devices exhibits high technical failure rates, reducing STDR detection. Deep learning (DL) based gradability predictions at acquisition could prompt device operators to recapture insufficient quality images, increasing gradable image proportions and consequently STDR detection. Non-mydriatic retinal images were captured as part of SMART India, a cross-sectional, multi-site, community-based, house-to-house DR screening study between August 2018 and December 2019 using the Zeiss Visuscout 100 handheld camera. From 18,277 patient eyes (40,126 images), 16,170 patient eyes (35,319 images) were eligible and 3261 retinal images (1490 patient eyes) were sampled then labelled by two ophthalmologists. Compact DL model area under the receiver operator characteristic curve was 0.93 (0.01) following five-fold cross-validation. Compact DL model agreement (Kappa) were 0.58, 0.69 and 0.69 for high specificity, balanced sensitivity/specificity and high sensitivity operating points compared to an inter-grader agreement of 0.59. Compact DL gradability model performance was favourable compared to ophthalmologists. Compact DL models can effectively classify non-mydriatic, handheld retinal image gradability with potential applications within community-based DR screening.
format	article
author	Paul Nderitu Joan M. Nunez do Rio Rajna Rasheed Rajiv Raman Ramachandran Rajalakshmi Christos Bergeles Sobha Sivaprasad for the SMART India Study Group
author_facet	Paul Nderitu Joan M. Nunez do Rio Rajna Rasheed Rajiv Raman Ramachandran Rajalakshmi Christos Bergeles Sobha Sivaprasad for the SMART India Study Group
author_sort	Paul Nderitu
title	Deep learning for gradability classification of handheld, non-mydriatic retinal images
title_short	Deep learning for gradability classification of handheld, non-mydriatic retinal images
title_full	Deep learning for gradability classification of handheld, non-mydriatic retinal images
title_fullStr	Deep learning for gradability classification of handheld, non-mydriatic retinal images
title_full_unstemmed	Deep learning for gradability classification of handheld, non-mydriatic retinal images
title_sort	deep learning for gradability classification of handheld, non-mydriatic retinal images
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/594f097782804df78a12ee67fe218b74
work_keys_str_mv	AT paulnderitu deeplearningforgradabilityclassificationofhandheldnonmydriaticretinalimages AT joanmnunezdorio deeplearningforgradabilityclassificationofhandheldnonmydriaticretinalimages AT rajnarasheed deeplearningforgradabilityclassificationofhandheldnonmydriaticretinalimages AT rajivraman deeplearningforgradabilityclassificationofhandheldnonmydriaticretinalimages AT ramachandranrajalakshmi deeplearningforgradabilityclassificationofhandheldnonmydriaticretinalimages AT christosbergeles deeplearningforgradabilityclassificationofhandheldnonmydriaticretinalimages AT sobhasivaprasad deeplearningforgradabilityclassificationofhandheldnonmydriaticretinalimages AT forthesmartindiastudygroup deeplearningforgradabilityclassificationofhandheldnonmydriaticretinalimages
_version_	1718389447078182912

Deep learning for gradability classification of handheld, non-mydriatic retinal images

Ejemplares similares