Fundus image quality assessment: survey, challenges, and future scope

Abstract

Various ocular diseases, such as cataract, diabetic retinopathy, and glaucoma have affected a large proportion of the population worldwide. In ophthalmology, fundus photography is used for the diagnosis of such retinal disorders. Nowadays, the setup of fundus image acquisition has changed from a fixed position to portable devices, making acquisition more vulnerable to distortions. However, a trustworthy diagnosis solely relies upon the quality of the fundus image. In recent years, fundus image quality assessment (IQA) has drawn much attention from researchers. This paper presents a detailed survey of the fundus IQA research. The survey covers a comprehensive discussion on the factors affecting the fundus image quality and the real-time distortions. The fundus IQA algorithms have been analyzed on the basis of the methodologies used and divided into three classes, namely: (i) Similarity-based, (ii) Segmentation-based, and (iii) Machine learning based. In addition, limitations of state of the art in this research field are also presented with the possible solutions. The objective of this paper is to provide a detailed information about the fundus IQA research with its significance, present status, limitations, and future scope. To the best of our knowledge, this is the first survey paper on the fundus IQA research.

A Comprehensive Survey on Computational Aesthetic Evaluation of Visual Art Images: Metrics and Challenges

“…Joshi et al [26] discussed key aspects of computational inference of aesthetics and emotion from images, but the deep learning based methods are not considered. Some reviews focused on image quality assessment [27]- [29], however, the image quality usually relates to distortions caused by lossy compression, noises, transmission channel attenuation, and distinguishes noisy images from clean images in terms of different quality measures such as structural similarity index [30], visual signal-tonoise ratio [31], and visual information fidelity [32], rather than photographic or artistic aesthetics. Deng et al [33] systematically reviewed approaches based on visual feature types, dataset characteristics, evaluation metrics, and also conducted experiments to compare the predictive performances of various deep learning settings.…”

Classification of Multiple Retinal Disorders from Enhanced Fundus Images Using Semi-supervised GAN

“…Often, the fundus image quality is degraded due to the illumination inhomogeneity and low contrast issues. Some of the fundus image quality assessment standards are discussed in [5]. Low-quality fundus images can hinder the examination procedure by masking the abnormalities, such as drusen and hemorrhages.…”

Multivariate Regression-Based Convolutional Neural Network Model for Fundus Image Quality Assessment

“…The next subsection contains an overview of the previous fundus IQA works with theirs limitations. For further details, the reader can refer to [11].…”