Google Play icon

New App Uses In-Built Smartphone Camera to Screen for Pancreatic Cancer

Posted August 29, 2017

Pancreatic cancer has one of the worst prognoses of all medical conditions caused by malignant tumours, with only about 9 percent of patients surviving past the five-year mark post-diagnosis.

One of the main reasons for this has to do with there usually being no symptoms motivating people to pursue further testing, other than yellow discoloration of the skin and eyes, caused by a build-up of bilirubin in the blood.

However, once the sclera – or the white part of the eye – becomes noticeably discoloured, it is usually too late for effective medical intervention.

In the near future, people might be able to screen themselves for pancreatic cancer using nothing more than a garden-variety smartphone and a 3D-printed box worn much like a virtual reality headset. Image courtesy of Dennis Wise/University of Washington.

Given the unreliability of haematological testing for pancreatic cancer, the asymptomatic nature of the early stages of the disease, and the lack of other, non-invasive techniques, advancements in the field of diagnosis are sorely needed.

Enter BiliScreen – an app, developed by researchers at the University of Washington, that uses the built-in camera of a smartphone to snap a picture of the eye, calculates the colour information from the sclera based on the wavelengths of light that are being reflected and absorbed, and correlates it with bilirubin levels using machine learning algorithms.

Users of the app are also advised to wear a 3D-printed box (which resembles a Google Cardboard headset) that blocks out ambient lighting for more accurate results.

“The hope is that if people can do this simple test once a month – in the privacy of their own homes – some might catch the disease early enough to undergo treatment that could save their lives,” said lead author of the project Alex Mariakakis who’s a doctoral student at the Paul G. Allen School of Computer Science and Engineering.

BilliScreen is a younger cousin of BilliCam – an earlier app used for screening for new-born jaundice (also indicated by yellowish discoloration of the eye) by taking a picture of a baby’s skin.

An early clinical trial of the app showed it can correctly identify cases of concern an impressive 89.7 percent of the time.

The research team is now scheduled to conduct further testing on a wider range of people at risk of jaundice and related conditions, as well to continue making usability improvements, including removing the need for accessories such as the light-blocking box.


Featured news from related categories:

Technology Org App
Google Play icon
84,824 science & technology articles