Cargando…

Deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs

OBJECTIVE: To assess the ability of a deep learning model to distinguish between diabetic retinopathy (DR), sickle cell retinopathy (SCR), retinal vein occlusions (RVOs) and healthy eyes using ultra-widefield colour fundus photography (UWF-CFP). METHODS AND ANALYSIS: In this retrospective study, UWF...

Descripción completa

Detalles Bibliográficos
Autores principales: Abitbol, Elie, Miere, Alexandra, Excoffier, Jean-Baptiste, Mehanna, Carl-Joe, Amoroso, Francesca, Kerr, Samuel, Ortala, Matthieu, Souied, Eric H
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BMJ Publishing Group 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8819815/
https://www.ncbi.nlm.nih.gov/pubmed/35141420
http://dx.doi.org/10.1136/bmjophth-2021-000924
_version_ 1784646128287875072
author Abitbol, Elie
Miere, Alexandra
Excoffier, Jean-Baptiste
Mehanna, Carl-Joe
Amoroso, Francesca
Kerr, Samuel
Ortala, Matthieu
Souied, Eric H
author_facet Abitbol, Elie
Miere, Alexandra
Excoffier, Jean-Baptiste
Mehanna, Carl-Joe
Amoroso, Francesca
Kerr, Samuel
Ortala, Matthieu
Souied, Eric H
author_sort Abitbol, Elie
collection PubMed
description OBJECTIVE: To assess the ability of a deep learning model to distinguish between diabetic retinopathy (DR), sickle cell retinopathy (SCR), retinal vein occlusions (RVOs) and healthy eyes using ultra-widefield colour fundus photography (UWF-CFP). METHODS AND ANALYSIS: In this retrospective study, UWF-CFP images of patients with retinal vascular disease (DR, RVO, and SCR) and healthy controls were included. The images were used to train a multilayer deep convolutional neural network to differentiate on UWF-CFP between different vascular diseases and healthy controls. A total of 224 UWF-CFP images were included, of which 169 images were of retinal vascular diseases and 55 were healthy controls. A cross-validation technique was used to ensure that every image from the dataset was tested once. Established augmentation techniques were applied to enhance performances, along with an Adam optimiser for training. The visualisation method was integrated gradient visualisation. RESULTS: The best performance of the model was obtained using 10 epochs, with an overall accuracy of 88.4%. For DR, the area under the receiver operating characteristics (ROC) curve (AUC) was 90.5% and the accuracy was 85.2%. For RVO, the AUC was 91.2% and the accuracy 88.4%. For SCR, the AUC was 96.7% and the accuracy 93.8%. For healthy controls, the ROC was 88.5% with an accuracy that reached 86.2%. CONCLUSION: Deep learning algorithms can classify several retinal vascular diseases on UWF-CPF with good accuracy. This technology may be a useful tool for telemedicine and areas with a shortage of ophthalmic care.
format Online
Article
Text
id pubmed-8819815
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher BMJ Publishing Group
record_format MEDLINE/PubMed
spelling pubmed-88198152022-02-08 Deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs Abitbol, Elie Miere, Alexandra Excoffier, Jean-Baptiste Mehanna, Carl-Joe Amoroso, Francesca Kerr, Samuel Ortala, Matthieu Souied, Eric H BMJ Open Ophthalmol Retina OBJECTIVE: To assess the ability of a deep learning model to distinguish between diabetic retinopathy (DR), sickle cell retinopathy (SCR), retinal vein occlusions (RVOs) and healthy eyes using ultra-widefield colour fundus photography (UWF-CFP). METHODS AND ANALYSIS: In this retrospective study, UWF-CFP images of patients with retinal vascular disease (DR, RVO, and SCR) and healthy controls were included. The images were used to train a multilayer deep convolutional neural network to differentiate on UWF-CFP between different vascular diseases and healthy controls. A total of 224 UWF-CFP images were included, of which 169 images were of retinal vascular diseases and 55 were healthy controls. A cross-validation technique was used to ensure that every image from the dataset was tested once. Established augmentation techniques were applied to enhance performances, along with an Adam optimiser for training. The visualisation method was integrated gradient visualisation. RESULTS: The best performance of the model was obtained using 10 epochs, with an overall accuracy of 88.4%. For DR, the area under the receiver operating characteristics (ROC) curve (AUC) was 90.5% and the accuracy was 85.2%. For RVO, the AUC was 91.2% and the accuracy 88.4%. For SCR, the AUC was 96.7% and the accuracy 93.8%. For healthy controls, the ROC was 88.5% with an accuracy that reached 86.2%. CONCLUSION: Deep learning algorithms can classify several retinal vascular diseases on UWF-CPF with good accuracy. This technology may be a useful tool for telemedicine and areas with a shortage of ophthalmic care. BMJ Publishing Group 2022-02-04 /pmc/articles/PMC8819815/ /pubmed/35141420 http://dx.doi.org/10.1136/bmjophth-2021-000924 Text en © Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. https://creativecommons.org/licenses/by-nc/4.0/This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/ (https://creativecommons.org/licenses/by-nc/4.0/) .
spellingShingle Retina
Abitbol, Elie
Miere, Alexandra
Excoffier, Jean-Baptiste
Mehanna, Carl-Joe
Amoroso, Francesca
Kerr, Samuel
Ortala, Matthieu
Souied, Eric H
Deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs
title Deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs
title_full Deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs
title_fullStr Deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs
title_full_unstemmed Deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs
title_short Deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs
title_sort deep learning-based classification of retinal vascular diseases using ultra-widefield colour fundus photographs
topic Retina
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8819815/
https://www.ncbi.nlm.nih.gov/pubmed/35141420
http://dx.doi.org/10.1136/bmjophth-2021-000924
work_keys_str_mv AT abitbolelie deeplearningbasedclassificationofretinalvasculardiseasesusingultrawidefieldcolourfundusphotographs
AT mierealexandra deeplearningbasedclassificationofretinalvasculardiseasesusingultrawidefieldcolourfundusphotographs
AT excoffierjeanbaptiste deeplearningbasedclassificationofretinalvasculardiseasesusingultrawidefieldcolourfundusphotographs
AT mehannacarljoe deeplearningbasedclassificationofretinalvasculardiseasesusingultrawidefieldcolourfundusphotographs
AT amorosofrancesca deeplearningbasedclassificationofretinalvasculardiseasesusingultrawidefieldcolourfundusphotographs
AT kerrsamuel deeplearningbasedclassificationofretinalvasculardiseasesusingultrawidefieldcolourfundusphotographs
AT ortalamatthieu deeplearningbasedclassificationofretinalvasculardiseasesusingultrawidefieldcolourfundusphotographs
AT souiederich deeplearningbasedclassificationofretinalvasculardiseasesusingultrawidefieldcolourfundusphotographs