Smartphones are great. They’re portable, always connected and most have excellent cameras. But new research finds they’re not necessarily so good at diagnosing diseases of the eye.
The problem, researchers at Anglia Ruskin University say, is that smartphone cameras aren’t calibrated and can give misleading results, even though eye doctors are increasingly using the devices because of their mobility and the ease of sharing results to the cloud.
But though convenient, the devices may not be accurate, they cautioned. For example, eye examinations to look for redness in the eye can indicate a variety of conditions including conjunctivitis, dry-eye disease and tear-gland dysfunction. However, camera color sensors vary and as a result, images of the same eye may appear different depending on the model of smartphone used, the researchers said in a study published this week in the Nature journal Scientific Reports.
The researchers took 192 images of eyes using three smartphone cameras, two different lighting levels and two zoom levels (x10 and x6). The images were duplicated and one set was white balanced and color corrected (calibrated) and the other left unaltered.
Cameras aren’t calibrated
They took photographs in autofocus mode with the iPhone 6s, the Google Nexus 6p and the Bq Aquaris U Lite, and found that the iPhone results were significantly different from the other two devices, when computing relative redness of each eye, and when compared to a clinician’s diagnosis. However, when the images were calibrated, the differences between lighting levels and camera types were significantly minimized — with differences between smartphones reduced by approximately 30%.
“This is the first time that the performance of three different smartphone cameras were evaluated in the context of a clinical application,” said lead author Carles Otero, of Anglia Ruskin’s Vision and Eye Institute.
“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,” he said.