Development of a Mobile Application for at-Home Analysis of Retinal Fundus Images

2025-09-20

AI Summary

Current machine learning–based analysis of retinal fundus images relies heavily on clinical expert validation, hindering scalable, at-home ocular self-monitoring. To address this, we propose a mobile-based, longitudinal monitoring framework that operates without specialist involvement. Our approach integrates three core components: (1) the DeepSeeNet glaucoma classifier, (2) a diabetic retinopathy and macular edema detection model trained on Messidor and MAPLES-DR datasets, and (3) a novel, self-developed algorithm for quantitative assessment of vascular tortuosity. Leveraging multi-model ensemble inference and longitudinal trend modeling, the system dynamically tracks key biomarkers of age-related eye diseases. Users regularly upload fundus images via a mobile application, which automatically generates personalized health trajectory reports and early-warning alerts. Experimental evaluation demonstrates robust detection of subtle, preclinical pathological changes, significantly enhancing the feasibility, timeliness, and clinical utility of home-based screening—thereby establishing a deployable technical pathway for proactive, chronic ophthalmic disease management.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Machine learning is gaining significant attention as a diagnostic tool in medical imaging, particularly in the analysis of retinal fundus images. However, this approach is not yet clinically applicable, as it still depends on human validation from a professional. Therefore, we present the design for a mobile application that monitors metrics related to retinal fundus images correlating to age-related conditions. The purpose of this platform is to observe for a change in these metrics over time, offering early insights into potential ocular diseases without explicitly delivering diagnostics. Metrics analysed include vessel tortuosity, as well as signs of glaucoma, retinopathy and macular edema. To evaluate retinopathy grade and risk of macular edema, a model was trained on the Messidor dataset and compared to a similar model trained on the MAPLES-DR dataset. Information from the DeepSeeNet glaucoma detection model, as well as tortuosity calculations, is additionally incorporated to ultimately present a retinal fundus image monitoring platform. As a result, the mobile application permits monitoring of trends or changes in ocular metrics correlated to age-related conditions with regularly uploaded photographs.

Problem

• Developing a mobile app for at-home retinal fundus image analysis
• Monitoring ocular metrics over time for age-related conditions
• Providing early insights without explicit diagnostic capabilities

Innovation

• Mobile app monitors retinal fundus image metrics
• Combines multiple trained models for disease analysis
• Tracks metric changes over time for early insights