New smartphone app can diagnose eye cancer in kids: Study

Scientists have developed a new smartphone app that parents can use to scan family photographs to detect early signs of various eye diseases in their children such as retinoblastoma -- a rare and aggressive form of eye cancer.

The study, published in the journal Science Advances, noted that the app named CRADLE -- ComputeR Assisted Detector LEukocoia -- searched for traces of abnormal reflections from the retina called leukocoria (white eye) which is a primary symptom of many eye diseases including retinoblastoma.

The researchers from Baylor University in the US found the app to be an effective tool to screen for clinical leukocoria, enabling parents to efficiently screen their children more often as they grew up.

Using the app, the researchers analysed more than 50,000 photographs of children taken prior to their diagnosis, and those diagnosed with eye disorders, CRADLE was able to detect leukocoria for 80 per cent of them.

The study noted that the app detected leukocoria in photos that were taken on average of 1.3 years before the children got their clinical diagnosis.

According to the study's first author Micheal Munson of Baylor University, general physical exams are successful in diagnosing for retinoblastoma via the detection of leukocoria in only 8 per cent of the cases.

However, Munson added that CRADLE's sensitivity for children of age two years and younger surpassed 80 per cent -- the threshold regarded by ophthalmologists as the ''gold standard" of sensitivity for similar devices.

According to the researchers, the CRADLE app was more effective because of the breadth and frequency of sample it can analyse such as everyday family photos.

There is a variety of opportunities for light to reflect off the ocular lesions regardless of its location in the eye, given the number of photos family and friends take in a range of environments, the researchers said.

"We wanted to be able to detect all hues and intensities of leukocoria. As a parent of a child with retinoblastoma, I am especially interested in detecting the traces of leukocoria that appear as a 'gray' pupil and are difficult to detect with the naked eye," said Bryan F Shaw, co-author of the study from Baylor University.

The app's algorithm, the researchers said, had become more sophisticated with improvements in its ability to detect even slight instances of leukocoria.

The study noted that the app could also detect leukocoria associated with other more common eye diseases and also some rare ones.

"So far, parents and some doctors, have used it to detect cataract, myelin retinal nerve fiber layer, refractive error, Coats' disease, and of course retinoblastoma," Shaw said.