A portable diagnosis model for Keratoconus using a smartphone

2025-05-13

AI Summary

Keratoconus (KC) screening relies on specialized Placido disk devices, limiting accessibility in resource-constrained settings. Method: We propose the first smartphone-based portable KC diagnostic system: a mobile screen projects Placido rings onto the cornea, and the resulting reflection images are captured and analyzed via a hardware-free end-to-end framework. Our method innovatively integrates corneal reflection geometric features (height/width) with a weighted support vector machine (WSVM) for automated three-stage KC grading; additionally, we introduce a disc-spacing–based pseudo-color mapping technique to visualize pathological regions. Contribution/Results: Validated across multiple smartphone models, the system achieves 92.93% classification accuracy and >90% cross-device stability. ANOVA and omega-squared (ω²) tests confirm statistical significance (p < 10⁻⁶) and large effect size (ω² up to 0.8398), demonstrating robust discriminative power and clinical applicability.

Technology Category

• Machine Learning: Kernel Methods
• Computer Vision: Motion & Tracking
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Keratoconus (KC) is a progressive corneal disorder characterized by localized thinning and protrusion, leading to visual distortion. While Placido disc-based topography remains a standard in clinical diagnostics, its dependence on specialized equipment limits accessibility. In this paper, we propose a portable, smartphone-based diagnostic framework that captures corneal reflections of a Placido disc displayed on a phone screen and applies a two-stage detection pipeline, then validate on 3D-printed emulated eyeball models that simulate normal, moderate, and severe KC stages based on anterior chamber depth (ACD). The first step of the two-stage detection pipeline is classifying different stages of KC with features including height and width of extracted reflections using weighted support vector machine (WSVM). It achieves a maximum accuracy of 92.93%, and maintains over 90% accuracy across multiple smartphone models, including the Galaxy Z Flip 3, iPhone 15 Pro, and iPhone 16 Pro. For the second step, we visualize the KC-affected protrusion regions on the corneas with color maps based on inter-disc distance, that provides an intuitive representation of disease severity and localization. Moreover, we validate the ability of the extracted features to differentiate between KC stages with ANOVA and Omega Squared, with significant p-values (e.g., $p<10^{-6}$) and large effect sizes ($\omega^2$ up to 0.8398) among classes.

Problem

• Develops smartphone-based portable Keratoconus diagnosis model
• Uses corneal reflections for two-stage KC detection pipeline
• Validates accuracy on 3D-printed eyeball models simulating KC stages

Innovation

• Smartphone-based portable KC diagnosis framework
• Two-stage detection with WSVM classification
• Color maps visualize KC severity and location