Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks

Wanyue Li, Wen Kong, Yiwei Chen, Jing Wang, Yi He, Guohua Shi, Guohua Deng
Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:424-439, 2020.

Abstract

Fluorescein angiography can provide a map of retinal vascular structure and function, which is commonly used in ophthalmology diagnosis, however, this imaging modality may pose risks of harm to the patients. To help physicians reduce the potential risks of diagnosis, an image translation method is adopted. In this work, we proposed a conditional generative adversarial network (GAN)-based method to directly learn the mapping relationship between structure fundus images and fundus fluorescence angiography (FFA) images. Moreover, local saliency maps, which define each pixel�s importance, are used to define a novel saliency loss in the GAN cost function. This facilitates more accurate learning of small-vessel and fluorescein leakage features. The proposed method was validated on our dataset and the publicly available Isfahan MISP dataset with the metrics of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The experimental results indicate that the proposed method can accurately generate both retinal vascular and fluorescein leakage structures, which has great practical significance for clinical diagnosis and analysis.

Cite this Paper

BibTeX
@InProceedings{pmlr-v121-li20b, title = {Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks}, author = {Li, Wanyue and Kong, Wen and Chen, Yiwei and Wang, Jing and He, Yi and Shi, Guohua and Deng, Guohua}, booktitle = {Proceedings of the Third Conference on Medical Imaging with Deep Learning}, pages = {424--439}, year = {2020}, editor = {Arbel, Tal and Ben Ayed, Ismail and de Bruijne, Marleen and Descoteaux, Maxime and Lombaert, Herve and Pal, Christopher}, volume = {121}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/li20b/li20b.pdf}, url = {https://proceedings.mlr.press/v121/li20b.html}, abstract = {Fluorescein angiography can provide a map of retinal vascular structure and function, which is commonly used in ophthalmology diagnosis, however, this imaging modality may pose risks of harm to the patients. To help physicians reduce the potential risks of diagnosis, an image translation method is adopted. In this work, we proposed a conditional generative adversarial network (GAN)-based method to directly learn the mapping relationship between structure fundus images and fundus fluorescence angiography (FFA) images. Moreover, local saliency maps, which define each pixel�s importance, are used to define a novel saliency loss in the GAN cost function. This facilitates more accurate learning of small-vessel and fluorescein leakage features. The proposed method was validated on our dataset and the publicly available Isfahan MISP dataset with the metrics of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The experimental results indicate that the proposed method can accurately generate both retinal vascular and fluorescein leakage structures, which has great practical significance for clinical diagnosis and analysis.} }
Endnote
%0 Conference Paper %T Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks %A Wanyue Li %A Wen Kong %A Yiwei Chen %A Jing Wang %A Yi He %A Guohua Shi %A Guohua Deng %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-li20b %I PMLR %P 424--439 %U https://proceedings.mlr.press/v121/li20b.html %V 121 %X Fluorescein angiography can provide a map of retinal vascular structure and function, which is commonly used in ophthalmology diagnosis, however, this imaging modality may pose risks of harm to the patients. To help physicians reduce the potential risks of diagnosis, an image translation method is adopted. In this work, we proposed a conditional generative adversarial network (GAN)-based method to directly learn the mapping relationship between structure fundus images and fundus fluorescence angiography (FFA) images. Moreover, local saliency maps, which define each pixel�s importance, are used to define a novel saliency loss in the GAN cost function. This facilitates more accurate learning of small-vessel and fluorescein leakage features. The proposed method was validated on our dataset and the publicly available Isfahan MISP dataset with the metrics of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The experimental results indicate that the proposed method can accurately generate both retinal vascular and fluorescein leakage structures, which has great practical significance for clinical diagnosis and analysis.
APA
Li, W., Kong, W., Chen, Y., Wang, J., He, Y., Shi, G. & Deng, G.. (2020). Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 121:424-439 Available from https://proceedings.mlr.press/v121/li20b.html.

Related Material