Smartphone-based artificial intelligence system for oculofacial measurements and automatic comparison against a newly developed age and ethnicity-matched normative database of oculofacial anthropometric measurements
Author: Jeremy T. Moreau
Base Hospital / Institution: University of Calgary
Rapid fire oral presentation
Abstract ID: 24-475
Purpose
In this presentation we discuss our development of OphthoRuler, a free smartphone application powered by AI and image processing techniques to automatically detect eyelid margins and calculate margin to reflex distance 1 (MRD1), margin to reflex distance 2 (MRD2), palpebral fissure height/width, inter-pupillary distance, inner/outer canthal distances, and canthal angle. We additionally discuss a newly created literature-sourced age and ethnicity-matched normative database of oculofacial anthropometric measurements including over 27 000 individuals and its implementation in OphthoRuler.
Methods
We validated the app against 120 healthy control images from the Chicago Face Database. App measurements were compared against manual photographic measurements obtained using an image analysis tool (ImageJ). Agreement was assessed using Bland-Altman difference plots. Subgroups of controls were compared to assess for equal reliability of measurements across Male, Female as well as Asian, Black, Latino, and White participants.
Results
Using the current model, mean difference was 0.75mm [1.96SD: -0.39-1.89] for MRD1, -0.58 for MRD2 [1.96SD: -2.02-0.87], 0.16 [1.96SD: -1.50- 1.83] for palpebral fissure height, and -0.37 for palpebral fissure width [1.96SD: -3.00-2.26]. There were no significant differences in reliability of measurements across Male, Female or Asian, Black, Latino, and White participants.
Conclusion
We developed a novel app for automated oculofacial anthropometric measurements and present case examples to illustrate functionality as well as data assessing the app’s reliability against manual photographic measurements. We also demonstrate applications of automated comparison against a novel age and ethnicity-matched normative database of oculofacial anthropometric measurements.
Additional Authors
| First name | Last name | Base Hospital / Institution |
|---|---|---|
| Étienne | Bénard-Séguin | University of Calgary |
| David | Plemel | University of Calgary |
| Michael | Ashenhurst | University of Calgary |
| Ezekiel | Weis | University of Calgary |
| Femida | Kherani | University of Calgary |
| Karim | Punja | University of Calgary |
| Andrew | Ting | University of Calgary |
| Fiona | Costello | University of Calgary |
