Domain-invariant interpretable fundus image quality assessment

•A framework for fundus image quality assessment filters the image with quality defects and provides visual feedback for real-time image reacquisition.•The proposed semi-tied adversarial discriminative domain adaptation model improves the generalization performance across different datasets with various distributions.•An efficient coarse-to-fine landmark detection (e.g. OD, fovea) is integrated into the architecture for robust quality assessment.•The DR grading task is improved with the proposed quality assessment preprocessing. [Display omitted] Objective and quantitative assessment of fundus image quality is essential for the diagnosis of retinal diseases. The major factors in fundus image quality assessment are image artifact, clarity, and field definition. Unfortunately, most of existing quality assessment methods focus on the quality of overall image, without interpretable quality feedback for real-time adjustment. Furthermore, these models are often sensitive to the specific imaging devices, and cannot generalize well under different imaging conditions. This paper presents a new multi-task domain adaptation framework to automatically assess fundus image quality. The proposed framework provides interpretable quality assessment with both quantitative scores and quality visualization for potential real-time image recapture with proper adjustment. In particular, the present approach can detect optic disc and fovea structures as landmarks, to assist the assessment through coarse-to-fine feature encoding. The framework also exploit semi-tied adversarial discriminative domain adaptation to make the model generalizable across different data sources. Experimental results demonstrated that the proposed algorithm outperforms different state-of-the-art approaches and achieves an area under the ROC curve of 0.9455 for the overall quality classification.