Glorbit: A Modular, Web-Based Platform for AI Based Periorbital Measurement in Low-Resource Settings (Preprint)

George R. Nahass , Jacob van der Ende , Sasha Hubschman , Benjamin Beltran , Bhavana Kolli , Caitlin Berek , James D. Edmonds , R.V. Paul Chan , Pete Setabutr , James W. Larrick , Darvin Yi , Ann Q. Tran ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.2196/preprints.82859

BACKGROUND Periorbital measurements such as margin reflex distances (MRD1/2), palpebral fissure height, and scleral show are critical in diagnosing and managing conditions like ptosis and disorders of the eyelid. OBJECTIVE We developed and evaluated Glorbit, a lightweight, browser-based application for automated periorbital distance measurement using artificial intelligence (AI), designed for deployment in low-resource clinical environments. The goal was to assess its usability, cross-platform functionality, and readiness for real-world field deployment. METHODS The application integrates a DeepLabV3 segmentation model into a modular image processing pipeline with secure, site-specific Google Cloud storage. Glorbit supports offline mode, local preprocessing, and cloud upload through Firebase-authenticated logins. The full workflow—metadata entry, facial image capture, segmentation, and upload—was tested. Post-session, participants completed a Likert-style usability survey. RESULTS Glorbit successfully ran on all tested platforms, including laptops, tablets, and mobile phones across major browsers. A total of 15 volunteers were enrolled in this study where the app completed the full workflow without error on 100% of patients. The segmentation model succeeded on all images, and average session duration was 101.7 ± 17.5 seconds. Usability scores on a 5-point Likert scale were uniformly high: intuitiveness and efficiency (5.0 ± 0.0), workflow clarity (4.8 ± 0.4), output confidence (4.9 ± 0.3), and clinical usability (4.9 ± 0.3). CONCLUSIONS Glorbit is a functional, cross-platform solution for standardized periorbital measurement in clinical and low-resource settings. By combining a local image processing with secure, modular data storage and offline compatibility, the tool enables scalable deployment and secure data collection. These features support broader efforts in AI-driven oculoplastics including future development of real-time triage tools and multimodal datasets for personalized ophthalmic care. CLINICALTRIAL STUDY2025-0731