Zhu Wenhui, Qiu Peijie, Farazi Mohammad, Nandakumar Keshav, Dumitrascu Oana M, Wang Yalin
School of Computing and Augmented Intelligence, Arizona State University, AZ 85281, USA.
McKeley School of Engineering, Washington University in St. Louis, St. Louis, MO 63130, USA.
Proc IEEE Int Symp Biomed Imaging. 2023 Apr;2023. doi: 10.1109/isbi53787.2023.10230719. Epub 2023 Sep 1.
Real-world non-mydriatic retinal fundus photography is prone to artifacts, imperfections, and low-quality when certain ocular or systemic co-morbidities exist. Artifacts may result in inaccuracy or ambiguity in clinical diagnoses. In this paper, we proposed a simple but effective end-to-end framework for enhancing poor-quality retinal fundus images. Leveraging the optimal transport theory, we proposed an unpaired image-to-image translation scheme for transporting low-quality images to their high-quality counterparts. We theoretically proved that a Generative Adversarial Networks (GAN) model with a generator and discriminator is sufficient for this task. Furthermore, to mitigate the inconsistency of information between the low-quality images and their enhancements, an information consistency mechanism was proposed to maximally maintain structural consistency (optical discs, blood vessels, lesions) between the source and enhanced domains. Extensive experiments were conducted on the EyeQ dataset to demonstrate the superiority of our proposed method perceptually and quantitatively.
在存在某些眼部或全身合并症的情况下，现实世界中的免散瞳视网膜眼底摄影容易出现伪像、瑕疵和低质量问题。伪像可能导致临床诊断的不准确或模糊。在本文中，我们提出了一个简单但有效的端到端框架，用于增强质量较差的视网膜眼底图像。利用最优传输理论，我们提出了一种非配对图像到图像的转换方案，用于将低质量图像转换为高质量图像。我们从理论上证明，具有生成器和判别器的生成对抗网络（GAN）模型足以完成此任务。此外，为了减轻低质量图像与其增强图像之间信息的不一致性，我们提出了一种信息一致性机制，以最大程度地保持源域和增强域之间的结构一致性（视盘、血管、病变）。我们在EyeQ数据集上进行了广泛的实验，以从感知和定量方面证明我们提出的方法的优越性。
