Evaluation of Retinal Image Quality Assessment Networks in Different Color-spaces
This work addresses the need for reliable RIQA to improve automated diagnostic systems in ophthalmology, but it is incremental as it builds on existing methods with a new dataset and color-space integration.
The authors tackled the problem of retinal image quality assessment (RIQA) by re-annotating a large-scale dataset with multi-level quality grades and proposing a deep network that integrates multiple color-spaces, achieving state-of-the-art performance on their dataset. They also showed that diabetic retinopathy detection methods are highly dependent on image quality.
Retinal image quality assessment (RIQA) is essential for controlling the quality of retinal imaging and guaranteeing the reliability of diagnoses by ophthalmologists or automated analysis systems. Existing RIQA methods focus on the RGB color-space and are developed based on small datasets with binary quality labels (i.e., `Accept' and `Reject'). In this paper, we first re-annotate an Eye-Quality (EyeQ) dataset with 28,792 retinal images from the EyePACS dataset, based on a three-level quality grading system (i.e., `Good', `Usable' and `Reject') for evaluating RIQA methods. Our RIQA dataset is characterized by its large-scale size, multi-level grading, and multi-modality. Then, we analyze the influences on RIQA of different color-spaces, and propose a simple yet efficient deep network, named Multiple Color-space Fusion Network (MCF-Net), which integrates the different color-space representations at both a feature-level and prediction-level to predict image quality grades. Experiments on our EyeQ dataset show that our MCF-Net obtains a state-of-the-art performance, outperforming the other deep learning methods. Furthermore, we also evaluate diabetic retinopathy (DR) detection methods on images of different quality, and demonstrate that the performances of automated diagnostic systems are highly dependent on image quality.