Cargando…
Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning
Center-involved diabetic macular edema (ci-DME) is a major cause of vision loss. Although the gold standard for diagnosis involves 3D imaging, 2D imaging by fundus photography is usually used in screening settings, resulting in high false-positive and false-negative calls. To address this, we train...
Autores principales: | , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6949287/ https://www.ncbi.nlm.nih.gov/pubmed/31913272 http://dx.doi.org/10.1038/s41467-019-13922-8 |
_version_ | 1783485892354113536 |
---|---|
author | Varadarajan, Avinash V. Bavishi, Pinal Ruamviboonsuk, Paisan Chotcomwongse, Peranut Venugopalan, Subhashini Narayanaswamy, Arunachalam Cuadros, Jorge Kanai, Kuniyoshi Bresnick, George Tadarati, Mongkol Silpa-archa, Sukhum Limwattanayingyong, Jirawut Nganthavee, Variya Ledsam, Joseph R. Keane, Pearse A. Corrado, Greg S. Peng, Lily Webster, Dale R. |
author_facet | Varadarajan, Avinash V. Bavishi, Pinal Ruamviboonsuk, Paisan Chotcomwongse, Peranut Venugopalan, Subhashini Narayanaswamy, Arunachalam Cuadros, Jorge Kanai, Kuniyoshi Bresnick, George Tadarati, Mongkol Silpa-archa, Sukhum Limwattanayingyong, Jirawut Nganthavee, Variya Ledsam, Joseph R. Keane, Pearse A. Corrado, Greg S. Peng, Lily Webster, Dale R. |
author_sort | Varadarajan, Avinash V. |
collection | PubMed |
description | Center-involved diabetic macular edema (ci-DME) is a major cause of vision loss. Although the gold standard for diagnosis involves 3D imaging, 2D imaging by fundus photography is usually used in screening settings, resulting in high false-positive and false-negative calls. To address this, we train a deep learning model to predict ci-DME from fundus photographs, with an ROC–AUC of 0.89 (95% CI: 0.87–0.91), corresponding to 85% sensitivity at 80% specificity. In comparison, retinal specialists have similar sensitivities (82–85%), but only half the specificity (45–50%, p < 0.001). Our model can also detect the presence of intraretinal fluid (AUC: 0.81; 95% CI: 0.81–0.86) and subretinal fluid (AUC 0.88; 95% CI: 0.85–0.91). Using deep learning to make predictions via simple 2D images without sophisticated 3D-imaging equipment and with better than specialist performance, has broad relevance to many other applications in medical imaging. |
format | Online Article Text |
id | pubmed-6949287 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-69492872020-01-10 Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning Varadarajan, Avinash V. Bavishi, Pinal Ruamviboonsuk, Paisan Chotcomwongse, Peranut Venugopalan, Subhashini Narayanaswamy, Arunachalam Cuadros, Jorge Kanai, Kuniyoshi Bresnick, George Tadarati, Mongkol Silpa-archa, Sukhum Limwattanayingyong, Jirawut Nganthavee, Variya Ledsam, Joseph R. Keane, Pearse A. Corrado, Greg S. Peng, Lily Webster, Dale R. Nat Commun Article Center-involved diabetic macular edema (ci-DME) is a major cause of vision loss. Although the gold standard for diagnosis involves 3D imaging, 2D imaging by fundus photography is usually used in screening settings, resulting in high false-positive and false-negative calls. To address this, we train a deep learning model to predict ci-DME from fundus photographs, with an ROC–AUC of 0.89 (95% CI: 0.87–0.91), corresponding to 85% sensitivity at 80% specificity. In comparison, retinal specialists have similar sensitivities (82–85%), but only half the specificity (45–50%, p < 0.001). Our model can also detect the presence of intraretinal fluid (AUC: 0.81; 95% CI: 0.81–0.86) and subretinal fluid (AUC 0.88; 95% CI: 0.85–0.91). Using deep learning to make predictions via simple 2D images without sophisticated 3D-imaging equipment and with better than specialist performance, has broad relevance to many other applications in medical imaging. Nature Publishing Group UK 2020-01-08 /pmc/articles/PMC6949287/ /pubmed/31913272 http://dx.doi.org/10.1038/s41467-019-13922-8 Text en © The Author(s) 2020 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/. |
spellingShingle | Article Varadarajan, Avinash V. Bavishi, Pinal Ruamviboonsuk, Paisan Chotcomwongse, Peranut Venugopalan, Subhashini Narayanaswamy, Arunachalam Cuadros, Jorge Kanai, Kuniyoshi Bresnick, George Tadarati, Mongkol Silpa-archa, Sukhum Limwattanayingyong, Jirawut Nganthavee, Variya Ledsam, Joseph R. Keane, Pearse A. Corrado, Greg S. Peng, Lily Webster, Dale R. Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning |
title | Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning |
title_full | Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning |
title_fullStr | Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning |
title_full_unstemmed | Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning |
title_short | Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning |
title_sort | predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6949287/ https://www.ncbi.nlm.nih.gov/pubmed/31913272 http://dx.doi.org/10.1038/s41467-019-13922-8 |
work_keys_str_mv | AT varadarajanavinashv predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT bavishipinal predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT ruamviboonsukpaisan predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT chotcomwongseperanut predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT venugopalansubhashini predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT narayanaswamyarunachalam predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT cuadrosjorge predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT kanaikuniyoshi predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT bresnickgeorge predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT tadaratimongkol predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT silpaarchasukhum predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT limwattanayingyongjirawut predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT nganthaveevariya predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT ledsamjosephr predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT keanepearsea predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT corradogregs predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT penglily predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning AT websterdaler predictingopticalcoherencetomographyderiveddiabeticmacularedemagradesfromfundusphotographsusingdeeplearning |