Researchers have created a prototype smartphone app that can help parents detect early signs of eye disorders like retinoblastoma -- which is an aggressive kind of pediatric eye cancer.?
Rawpixel
The app is call CRADLE, which stands for ComputerR Assisted Detector LEukocoria. The app specifically looks out for traces of unusual reflections from the retina that are called Leukocoia or 'white-eye' -- the symptom of retinoblastoma. As per a study published in Science Advances (Reported by Science Daily), the app is perfect to simulate clinical leukocoria screenings that can allow parents to check their kid's eyes for any disorders more often, throughout their development.
The app is developed by Baylor University researchers Bryan F. Shaw and Greg Hamerly, both PhD professors at the university. They created the app called 'White Eye Detector' in 2014 for iOS and in 2015 for Android devices after Shaw's son Noah lost his right eye to retinoblastoma, but his left eye was able to be salvaged.
They perfected the sensitivity and accuracy of the prototype by deeply analysing more than 50,000 photographs of children taken before they were diagnosed. CRADLE was able to detect leukocoria for 80-per cent of these children.?
Rawpixel
What's more fascinating is the fact that the images that it made the detection in were actually captured almost a year and a half before their official diagnosis.?
The traditional screening on leukocoria has limited effectiveness where only 8-percent cases are actually detected. CRADLE's sensitivity for detecting eye disorders for kids ages 2 and below is over 80-percent, which is known as the 'gold standard' by ophthalmologists.?
The reason CRADLE is so effective is due to its wide sample size, which includes everyday family photos. With a wide variety of images captured by friends and relatives in different lighting conditions, there are various instances for the light to reflect off the ocular lesions, even if the eye isn't in direct contact.?
Baylor University
This makes the algorithm of the app more complex, making it capable of detecting even the slightest instances of leukocoria.
According to Shaw, "This is one of the most critical parts of building the app. 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."
He further added, "We suspected that the app would detect leukocoria associated with other more common disorders and some rare ones. We were right. 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."
They're currently working with undergrads at Baylor to perfect the detection (and limit false-positives) by adding over 100,000 more photographs.