InSight: AI Mobile Screening Tool for Multiple Eye Disease Detection using Multimodal Fusion

TL;DR

InSight is an AI-powered mobile screening tool that combines clinical metadata and fundus images through multimodal fusion to accurately detect five common eye diseases, improving accessibility especially in resource-limited settings.

Contribution

The paper introduces a novel multimodal fusion technique, MetaFusion, and a multitask pretrained model for simultaneous detection of multiple eye diseases, enhancing accuracy and efficiency.

Findings

Near-100% accuracy in image quality assessment

Multimodal model outperforms image-only models by 6% in accuracy

Pipeline is five times more computationally efficient than separate models for each disease

Abstract

Background/Objectives: Age-related macular degeneration, glaucoma, diabetic retinopathy (DR), diabetic macular edema, and pathological myopia affect hundreds of millions of people worldwide. Early screening for these diseases is essential, yet access to medical care remains limited in low- and middle-income countries as well as in resource-limited settings. We develop InSight, an AI-based app that combines patient metadata with fundus images for accurate diagnosis of five common eye diseases to improve accessibility of screenings. Methods: InSight features a three-stage pipeline: real-time image quality assessment, disease diagnosis model, and a DR grading model to assess severity. Our disease diagnosis model incorporates three key innovations: (a) Multimodal fusion technique (MetaFusion) combining clinical metadata and images; (b) Pretraining method leveraging supervised and self-supervised loss functions; and (c) Multitask model to simultaneously predict 5 diseases. We make use of BRSET (lab-captured images) and mBRSET (smartphone-captured images) datasets, both of which also contain clinical metadata for model training/evaluation. Results: Trained on a dataset of BRSET and mBRSET images, the image quality checker achieves near-100% accuracy in filtering out low-quality fundus images. The multimodal pretrained disease diagnosis model outperforms models using only images by 6% in balanced accuracy for BRSET and 4% for mBRSET. Conclusions: The InSight pipeline demonstrates robustness across varied image conditions and has high diagnostic accuracy across all five diseases, generalizing to both smartphone and lab captured images. The multitask model contributes to the lightweight nature of the pipeline, making it five times computationally efficient compared to having five individual models corresponding to each disease.