UWAFA-GAN: Ultra-Wide-Angle Fluorescein Angiography Transformation via Multi-scale Generation and Registration Enhancement

TL;DR

UWAFA-GAN is a novel deep learning model that synthesizes ultra-wide-angle fluorescein angiography images from scanning laser ophthalmoscopy images, improving resolution and clinical utility while reducing invasive procedures.

Contribution

The paper introduces UWAFA-GAN, a multi-scale, attention-enhanced GAN with registration modules for high-quality UWF-FA image synthesis from UWF-SLO images, addressing resolution and alignment issues.

Findings

Outperforms existing methods in inception scores and detail generation

Clinically comparable to real images in diagnostic reliability

Effective in extracting global structures and local lesions

Abstract

Fundus photography, in combination with the ultra-wide-angle fundus (UWF) techniques, becomes an indispensable diagnostic tool in clinical settings by offering a more comprehensive view of the retina. Nonetheless, UWF fluorescein angiography (UWF-FA) necessitates the administration of a fluorescent dye via injection into the patient's hand or elbow unlike UWF scanning laser ophthalmoscopy (UWF-SLO). To mitigate potential adverse effects associated with injections, researchers have proposed the development of cross-modality medical image generation algorithms capable of converting UWF-SLO images into their UWF-FA counterparts. Current image generation techniques applied to fundus photography encounter difficulties in producing high-resolution retinal images, particularly in capturing minute vascular lesions. To address these issues, we introduce a novel conditional generative adversarial network (UWAFA-GAN) to synthesize UWF-FA from UWF-SLO. This approach employs multi-scale generators and an attention transmit module to efficiently extract both global structures and local lesions. Additionally, to counteract the image blurriness issue that arises from training with misaligned data, a registration module is integrated within this framework. Our method performs non-trivially on inception scores and details generation. Clinical user studies further indicate that the UWF-FA images generated by UWAFA-GAN are clinically comparable to authentic images in terms of diagnostic reliability. Empirical evaluations on our proprietary UWF image datasets elucidate that UWAFA-GAN outperforms extant methodologies. The code is accessible at https://github.com/Tinysqua/UWAFA-GAN.