Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     

Australia's Leading Ophthalmic Magazine Since 1975

     Free Sign Up     

Warnings about using smartphones in eye examinations

13/02/2019By Callum Glennen
Researches have cautioned clinicians who use smartphone cameras to diagnose eye disease to check their settings or else risk misdiagnosis.

According to research published in Scientific Reports, the colours in images captured by smartphone cameras may be inaccurate if the camera is not correctly calibrated. This has the potential to lead to misdiagnosis, particularly if the images are used in telemedicine or artificial intelligence applications.

Researchers from Anglia Ruskin University’s Vision and Eye Research Institute took almost 200 images of eyes using two different lighting levels, two zoom settings and three different smartphones. Images were then split into two sets: one unaltered from the smartphone’s default settings, and the other white balanced and colour corrected.

“Different cameras can produce different results for the same scene.”
Carles Otero, Anglia Ruskin University

When comparing relative eye-redness across uncorrected photographs taken by the iPhone 6s, the Google Nexus 6p and the Bq Aquaris U Lite, researchers found that iPhone photographs were significantly different. However, images were far more similar once corrected.

The colour variations may be an issue in artificial intelligence applications that use machine-learning algorithms to scan images and learn the signs of particular diseases.

Lead author on the study Mr Carles Otero said this research is the first time the performance of three different smartphone cameras has been evaluated in the context of a clinical application.

“Camera manufacturers have their own autofocus algorithms and hardware specifications, and this means different cameras can produce different results for the same scene. It is important that clinicians bear this in mind,” Otero said.

"Our results show that while the clinician's subjective evaluation was not affected by different cameras, lighting conditions or optical magnifications, calibration of a smartphone's camera is essential when extracting objective data from images. This can affect both telemedicine and artificial intelligence applications."


More reading:

Telehealth: an eyecare access breakthrough or dangerous gamble?


large leaderboard

Face A Face
Editor's Suggestion
Hot Stories

Designs for Vision


Subscribe for Insight in your Inbox

Get Insight with the latest in industry news, trends, new products, services and equipment!