FundaQ-8: A Clinically-Inspired Scoring Framework for Automated Fundus Image Quality Assessment

TL;DR

FundaQ-8 is a clinically-inspired, expert-validated scoring framework for automated fundus image quality assessment, improving the robustness of diabetic retinopathy diagnosis by integrating quality evaluation into deep learning models.

Contribution

We developed FundaQ-8, a novel structured scoring system for fundus image quality, and trained a ResNet18-based model to predict quality scores, enhancing diagnostic robustness.

Findings

FundaQ-8 reliably assesses fundus image quality.

Incorporating FundaQ-8 improves diabetic retinopathy grading accuracy.

The framework is validated on clinical and public datasets.

Abstract

Automated fundus image quality assessment (FIQA) remains a challenge due to variations in image acquisition and subjective expert evaluations. We introduce FundaQ-8, a novel expert-validated framework for systematically assessing fundus image quality using eight critical parameters, including field coverage, anatomical visibility, illumination, and image artifacts. Using FundaQ-8 as a structured scoring reference, we develop a ResNet18-based regression model to predict continuous quality scores in the 0 to 1 range. The model is trained on 1800 fundus images from real-world clinical sources and Kaggle datasets, using transfer learning, mean squared error optimization, and standardized preprocessing. Validation against the EyeQ dataset and statistical analyses confirm the framework's reliability and clinical interpretability. Incorporating FundaQ-8 into deep learning models for diabetic retinopathy grading also improves diagnostic robustness, highlighting the value of quality-aware training in real-world screening applications.