A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs
Abstract Fluorescein angiography (FA) is a procedure used to image the vascular structure of the retina and requires the insertion of an exogenous dye with potential adverse side effects. Currently, there is only one alternative non-invasive system based on Optical coherence tomography (OCT) technol...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2020
|
Materias: | |
Acceso en línea: | https://doaj.org/article/ec6869771f0945e7be893d40e0077b27 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:ec6869771f0945e7be893d40e0077b27 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:ec6869771f0945e7be893d40e0077b272021-12-02T11:43:35ZA novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs10.1038/s41598-020-78696-22045-2322https://doaj.org/article/ec6869771f0945e7be893d40e0077b272020-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-78696-2https://doaj.org/toc/2045-2322Abstract Fluorescein angiography (FA) is a procedure used to image the vascular structure of the retina and requires the insertion of an exogenous dye with potential adverse side effects. Currently, there is only one alternative non-invasive system based on Optical coherence tomography (OCT) technology, called OCT angiography (OCTA), capable of visualizing retina vasculature. However, due to its cost and limited view, OCTA technology is not widely used. Retinal fundus photography is a safe imaging technique used for capturing the overall structure of the retina. In order to visualize retinal vasculature without the need for FA and in a cost-effective, non-invasive, and accurate manner, we propose a deep learning conditional generative adversarial network (GAN) capable of producing FA images from fundus photographs. The proposed GAN produces anatomically accurate angiograms, with similar fidelity to FA images, and significantly outperforms two other state-of-the-art generative algorithms ( $$p<.001$$ p < . 001 and $$p<.0001$$ p < . 0001 ). Furthermore, evaluations by experts shows that our proposed model produces such high quality FA images that are indistinguishable from real angiograms. Our model as the first application of artificial intelligence and deep learning to medical image translation, by employing a theoretical framework capable of establishing a shared feature-space between two domains (i.e. funduscopy and fluorescein angiography) provides an unrivaled way for the translation of images from one domain to the other.Alireza TavakkoliSharif Amit KamranKhondker Fariha HossainStewart Lee ZuckerbrodNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-15 (2020) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Alireza Tavakkoli Sharif Amit Kamran Khondker Fariha Hossain Stewart Lee Zuckerbrod A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs |
description |
Abstract Fluorescein angiography (FA) is a procedure used to image the vascular structure of the retina and requires the insertion of an exogenous dye with potential adverse side effects. Currently, there is only one alternative non-invasive system based on Optical coherence tomography (OCT) technology, called OCT angiography (OCTA), capable of visualizing retina vasculature. However, due to its cost and limited view, OCTA technology is not widely used. Retinal fundus photography is a safe imaging technique used for capturing the overall structure of the retina. In order to visualize retinal vasculature without the need for FA and in a cost-effective, non-invasive, and accurate manner, we propose a deep learning conditional generative adversarial network (GAN) capable of producing FA images from fundus photographs. The proposed GAN produces anatomically accurate angiograms, with similar fidelity to FA images, and significantly outperforms two other state-of-the-art generative algorithms ( $$p<.001$$ p < . 001 and $$p<.0001$$ p < . 0001 ). Furthermore, evaluations by experts shows that our proposed model produces such high quality FA images that are indistinguishable from real angiograms. Our model as the first application of artificial intelligence and deep learning to medical image translation, by employing a theoretical framework capable of establishing a shared feature-space between two domains (i.e. funduscopy and fluorescein angiography) provides an unrivaled way for the translation of images from one domain to the other. |
format |
article |
author |
Alireza Tavakkoli Sharif Amit Kamran Khondker Fariha Hossain Stewart Lee Zuckerbrod |
author_facet |
Alireza Tavakkoli Sharif Amit Kamran Khondker Fariha Hossain Stewart Lee Zuckerbrod |
author_sort |
Alireza Tavakkoli |
title |
A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs |
title_short |
A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs |
title_full |
A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs |
title_fullStr |
A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs |
title_full_unstemmed |
A novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs |
title_sort |
novel deep learning conditional generative adversarial network for producing angiography images from retinal fundus photographs |
publisher |
Nature Portfolio |
publishDate |
2020 |
url |
https://doaj.org/article/ec6869771f0945e7be893d40e0077b27 |
work_keys_str_mv |
AT alirezatavakkoli anoveldeeplearningconditionalgenerativeadversarialnetworkforproducingangiographyimagesfromretinalfundusphotographs AT sharifamitkamran anoveldeeplearningconditionalgenerativeadversarialnetworkforproducingangiographyimagesfromretinalfundusphotographs AT khondkerfarihahossain anoveldeeplearningconditionalgenerativeadversarialnetworkforproducingangiographyimagesfromretinalfundusphotographs AT stewartleezuckerbrod anoveldeeplearningconditionalgenerativeadversarialnetworkforproducingangiographyimagesfromretinalfundusphotographs AT alirezatavakkoli noveldeeplearningconditionalgenerativeadversarialnetworkforproducingangiographyimagesfromretinalfundusphotographs AT sharifamitkamran noveldeeplearningconditionalgenerativeadversarialnetworkforproducingangiographyimagesfromretinalfundusphotographs AT khondkerfarihahossain noveldeeplearningconditionalgenerativeadversarialnetworkforproducingangiographyimagesfromretinalfundusphotographs AT stewartleezuckerbrod noveldeeplearningconditionalgenerativeadversarialnetworkforproducingangiographyimagesfromretinalfundusphotographs |
_version_ |
1718395376313040896 |