Generating Fundus Fluorescence Angiography Images from Structure Fundus Images Using Generative Adversarial Networks
This work addresses a domain-specific problem in medical imaging for ophthalmologists, offering an incremental improvement by enhancing feature accuracy in image translation.
The paper tackled the problem of generating fundus fluorescence angiography images from structure fundus images to reduce patient risks in ophthalmology diagnosis, achieving more accurate learning of small-vessel and fluorescein leakage features using a conditional GAN with a novel saliency loss.
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 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.