Deep learning for automated detection of neovascular leakage on ultra-widefield fluorescein angiography in diabetic retinopathy
Abstract Diabetic retinopathy is a leading cause of blindness in working-age adults worldwide. Neovascular leakage on fluorescein angiography indicates progression to the proliferative stage of diabetic retinopathy, which is an important distinction that requires timely ophthalmic intervention with...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-06-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-36327-6 |
| _version_ | 1827928730256801792 |
|---|---|
| author | Peter Y. Zhao Nikhil Bommakanti Gina Yu Michael T. Aaberg Tapan P. Patel Yannis M. Paulus |
| author_facet | Peter Y. Zhao Nikhil Bommakanti Gina Yu Michael T. Aaberg Tapan P. Patel Yannis M. Paulus |
| author_sort | Peter Y. Zhao |
| collection | DOAJ |
| description | Abstract Diabetic retinopathy is a leading cause of blindness in working-age adults worldwide. Neovascular leakage on fluorescein angiography indicates progression to the proliferative stage of diabetic retinopathy, which is an important distinction that requires timely ophthalmic intervention with laser or intravitreal injection treatment to reduce the risk of severe, permanent vision loss. In this study, we developed a deep learning algorithm to detect neovascular leakage on ultra-widefield fluorescein angiography images obtained from patients with diabetic retinopathy. The algorithm, an ensemble of three convolutional neural networks, was able to accurately classify neovascular leakage and distinguish this disease marker from other angiographic disease features. With additional real-world validation and testing, our algorithm could facilitate identification of neovascular leakage in the clinical setting, allowing timely intervention to reduce the burden of blinding diabetic eye disease. |
| first_indexed | 2024-03-13T06:12:53Z |
| format | Article |
| id | doaj.art-c13d93c990f2484695c4bcbf00df8b26 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-13T06:12:53Z |
| publishDate | 2023-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-c13d93c990f2484695c4bcbf00df8b262023-06-11T11:11:11ZengNature PortfolioScientific Reports2045-23222023-06-011311710.1038/s41598-023-36327-6Deep learning for automated detection of neovascular leakage on ultra-widefield fluorescein angiography in diabetic retinopathyPeter Y. Zhao0Nikhil Bommakanti1Gina Yu2Michael T. Aaberg3Tapan P. Patel4Yannis M. Paulus5Department of Ophthalmology and Visual Sciences, W.K. Kellogg Eye Center, University of MichiganDepartment of Ophthalmology and Visual Sciences, W.K. Kellogg Eye Center, University of MichiganDepartment of Ophthalmology and Visual Sciences, W.K. Kellogg Eye Center, University of MichiganDepartment of Ophthalmology and Visual Sciences, W.K. Kellogg Eye Center, University of MichiganDepartment of Ophthalmology and Visual Sciences, W.K. Kellogg Eye Center, University of MichiganDepartment of Ophthalmology and Visual Sciences, W.K. Kellogg Eye Center, University of MichiganAbstract Diabetic retinopathy is a leading cause of blindness in working-age adults worldwide. Neovascular leakage on fluorescein angiography indicates progression to the proliferative stage of diabetic retinopathy, which is an important distinction that requires timely ophthalmic intervention with laser or intravitreal injection treatment to reduce the risk of severe, permanent vision loss. In this study, we developed a deep learning algorithm to detect neovascular leakage on ultra-widefield fluorescein angiography images obtained from patients with diabetic retinopathy. The algorithm, an ensemble of three convolutional neural networks, was able to accurately classify neovascular leakage and distinguish this disease marker from other angiographic disease features. With additional real-world validation and testing, our algorithm could facilitate identification of neovascular leakage in the clinical setting, allowing timely intervention to reduce the burden of blinding diabetic eye disease.https://doi.org/10.1038/s41598-023-36327-6 |
| spellingShingle | Peter Y. Zhao Nikhil Bommakanti Gina Yu Michael T. Aaberg Tapan P. Patel Yannis M. Paulus Deep learning for automated detection of neovascular leakage on ultra-widefield fluorescein angiography in diabetic retinopathy Scientific Reports |
| title | Deep learning for automated detection of neovascular leakage on ultra-widefield fluorescein angiography in diabetic retinopathy |
| title_full | Deep learning for automated detection of neovascular leakage on ultra-widefield fluorescein angiography in diabetic retinopathy |
| title_fullStr | Deep learning for automated detection of neovascular leakage on ultra-widefield fluorescein angiography in diabetic retinopathy |
| title_full_unstemmed | Deep learning for automated detection of neovascular leakage on ultra-widefield fluorescein angiography in diabetic retinopathy |
| title_short | Deep learning for automated detection of neovascular leakage on ultra-widefield fluorescein angiography in diabetic retinopathy |
| title_sort | deep learning for automated detection of neovascular leakage on ultra widefield fluorescein angiography in diabetic retinopathy |
| url | https://doi.org/10.1038/s41598-023-36327-6 |
| work_keys_str_mv | AT peteryzhao deeplearningforautomateddetectionofneovascularleakageonultrawidefieldfluoresceinangiographyindiabeticretinopathy AT nikhilbommakanti deeplearningforautomateddetectionofneovascularleakageonultrawidefieldfluoresceinangiographyindiabeticretinopathy AT ginayu deeplearningforautomateddetectionofneovascularleakageonultrawidefieldfluoresceinangiographyindiabeticretinopathy AT michaeltaaberg deeplearningforautomateddetectionofneovascularleakageonultrawidefieldfluoresceinangiographyindiabeticretinopathy AT tapanppatel deeplearningforautomateddetectionofneovascularleakageonultrawidefieldfluoresceinangiographyindiabeticretinopathy AT yannismpaulus deeplearningforautomateddetectionofneovascularleakageonultrawidefieldfluoresceinangiographyindiabeticretinopathy |