Cargando…

A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders

The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, and tested a DLS, using...

Descripción completa

Detalles Bibliográficos
Autores principales: Chan, Ebenezer, Tang, Zhiqun, Najjar, Raymond P., Narayanaswamy, Arun, Sathianvichitr, Kanchalika, Newman, Nancy J., Biousse, Valérie, Milea, Dan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9818957/
https://www.ncbi.nlm.nih.gov/pubmed/36611452
http://dx.doi.org/10.3390/diagnostics13010160
_version_ 1784865113057001472
author Chan, Ebenezer
Tang, Zhiqun
Najjar, Raymond P.
Narayanaswamy, Arun
Sathianvichitr, Kanchalika
Newman, Nancy J.
Biousse, Valérie
Milea, Dan
author_facet Chan, Ebenezer
Tang, Zhiqun
Najjar, Raymond P.
Narayanaswamy, Arun
Sathianvichitr, Kanchalika
Newman, Nancy J.
Biousse, Valérie
Milea, Dan
author_sort Chan, Ebenezer
collection PubMed
description The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, and tested a DLS, using an international, multicentre, multi-ethnic dataset of 5015 ocular fundus photographs from 31 centres in 20 countries participating to the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI). The reference standard in image quality was established by three experts who independently classified photographs as of “good”, “borderline”, or “poor” quality. The DLS was trained on 4208 fundus photographs and tested on an independent external dataset of 807 photographs, using a multi-class model, evaluated with a one-vs-rest classification strategy. In the external-testing dataset, the DLS could identify with excellent performance “good” quality photographs (AUC = 0.93 (95% CI, 0.91–0.95), accuracy = 91.4% (95% CI, 90.0–92.9%), sensitivity = 93.8% (95% CI, 92.5–95.2%), specificity = 75.9% (95% CI, 69.7–82.1%) and “poor” quality photographs (AUC = 1.00 (95% CI, 0.99–1.00), accuracy = 99.1% (95% CI, 98.6–99.6%), sensitivity = 81.5% (95% CI, 70.6–93.8%), specificity = 99.7% (95% CI, 99.6–100.0%). “Borderline” quality images were also accurately classified (AUC = 0.90 (95% CI, 0.88–0.93), accuracy = 90.6% (95% CI, 89.1–92.2%), sensitivity = 65.4% (95% CI, 56.6–72.9%), specificity = 93.4% (95% CI, 92.1–94.8%). The overall accuracy to distinguish among the three classes was 90.6% (95% CI, 89.1–92.1%), suggesting that this DLS could select optimal quality fundus photographs in patients with neuro-ophthalmic and neurological disorders affecting the ONH.
format Online
Article
Text
id pubmed-9818957
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-98189572023-01-07 A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders Chan, Ebenezer Tang, Zhiqun Najjar, Raymond P. Narayanaswamy, Arun Sathianvichitr, Kanchalika Newman, Nancy J. Biousse, Valérie Milea, Dan Diagnostics (Basel) Article The quality of ocular fundus photographs can affect the accuracy of the morphologic assessment of the optic nerve head (ONH), either by humans or by deep learning systems (DLS). In order to automatically identify ONH photographs of optimal quality, we have developed, trained, and tested a DLS, using an international, multicentre, multi-ethnic dataset of 5015 ocular fundus photographs from 31 centres in 20 countries participating to the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI). The reference standard in image quality was established by three experts who independently classified photographs as of “good”, “borderline”, or “poor” quality. The DLS was trained on 4208 fundus photographs and tested on an independent external dataset of 807 photographs, using a multi-class model, evaluated with a one-vs-rest classification strategy. In the external-testing dataset, the DLS could identify with excellent performance “good” quality photographs (AUC = 0.93 (95% CI, 0.91–0.95), accuracy = 91.4% (95% CI, 90.0–92.9%), sensitivity = 93.8% (95% CI, 92.5–95.2%), specificity = 75.9% (95% CI, 69.7–82.1%) and “poor” quality photographs (AUC = 1.00 (95% CI, 0.99–1.00), accuracy = 99.1% (95% CI, 98.6–99.6%), sensitivity = 81.5% (95% CI, 70.6–93.8%), specificity = 99.7% (95% CI, 99.6–100.0%). “Borderline” quality images were also accurately classified (AUC = 0.90 (95% CI, 0.88–0.93), accuracy = 90.6% (95% CI, 89.1–92.2%), sensitivity = 65.4% (95% CI, 56.6–72.9%), specificity = 93.4% (95% CI, 92.1–94.8%). The overall accuracy to distinguish among the three classes was 90.6% (95% CI, 89.1–92.1%), suggesting that this DLS could select optimal quality fundus photographs in patients with neuro-ophthalmic and neurological disorders affecting the ONH. MDPI 2023-01-03 /pmc/articles/PMC9818957/ /pubmed/36611452 http://dx.doi.org/10.3390/diagnostics13010160 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
Chan, Ebenezer
Tang, Zhiqun
Najjar, Raymond P.
Narayanaswamy, Arun
Sathianvichitr, Kanchalika
Newman, Nancy J.
Biousse, Valérie
Milea, Dan
A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders
title A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders
title_full A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders
title_fullStr A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders
title_full_unstemmed A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders
title_short A Deep Learning System for Automated Quality Evaluation of Optic Disc Photographs in Neuro-Ophthalmic Disorders
title_sort deep learning system for automated quality evaluation of optic disc photographs in neuro-ophthalmic disorders
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9818957/
https://www.ncbi.nlm.nih.gov/pubmed/36611452
http://dx.doi.org/10.3390/diagnostics13010160
work_keys_str_mv AT chanebenezer adeeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT tangzhiqun adeeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT najjarraymondp adeeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT narayanaswamyarun adeeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT sathianvichitrkanchalika adeeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT newmannancyj adeeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT bioussevalerie adeeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT mileadan adeeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT adeeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT chanebenezer deeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT tangzhiqun deeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT najjarraymondp deeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT narayanaswamyarun deeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT sathianvichitrkanchalika deeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT newmannancyj deeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT bioussevalerie deeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT mileadan deeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders
AT deeplearningsystemforautomatedqualityevaluationofopticdiscphotographsinneuroophthalmicdisorders