A Deep Retinal Image Quality Assessment Network with Salient Structure Priors

TL;DR

This paper introduces a deep learning approach for retinal image quality assessment that incorporates salient structure priors, mimicking ophthalmologists' focus on key anatomical features to improve accuracy and efficiency.

Contribution

It proposes two CNN architectures guided by salient structure priors, enhancing focus on important retinal features for quality assessment, and demonstrates superior performance on a benchmark dataset.

Findings

Dual-branch SalStructIQA outperforms state-of-the-art methods.

Single-branch SalStructIQA is more lightweight with competitive accuracy.

Salient structure priors improve CNN focus and assessment accuracy.

Abstract

Retinal image quality assessment is an essential prerequisite for diagnosis of retinal diseases. Its goal is to identify retinal images in which anatomic structures and lesions attracting ophthalmologists' attention most are exhibited clearly and definitely while reject poor quality fundus images. Motivated by this, we mimic the way that ophthalmologists assess the quality of retinal images and propose a method termed SalStructuIQA. First, two salient structures for automated retinal quality assessment. One is the large-size salient structures including optic disc region and exudates in large-size. The other is the tiny-size salient structures which mainly include vessels. Then we incorporate the proposed two salient structure priors with deep convolutional neural network (CNN) to shift the focus of CNN to salient structures. Accordingly, we develop two CNN architectures: Dual-branch SalStructIQA and Single-branch SalStructIQA. Dual-branch SalStructIQA contains two CNN branches and one is guided by large-size salient structures while the other is guided by tiny-size salient structures. Single-branch SalStructIQA contains one CNN branch, which is guided by the concatenation of salient structures in both large-size and tiny-size. Experimental results on Eye-Quality dataset show that our proposed Dual-branch SalStructIQA outperforms the state-of-the-art methods for retinal image quality assessment and Single-branch SalStructIQA is much light-weight comparing with state-of-the-art deep retinal image quality assessment methods and still achieves competitive performances.