New Smartphone App Developed Screens For Pancreatic Cancer

Highlights

A new smartphone app developed can detect the early signs of pancreatic cancer from a selfie
BiliScreen, the new smartphone app uses a smartphone camera, computer vision algorithms and machine learning tools to detect increased bilirubin levels in the sclera
Further research needs to be done on more number of people who are at risk of pancreatic cancer to improve their survival rates

Pancreatic cancer has a five-year survival rate of nine percent and is one of the worst prognoses, as there are no signs or symptoms or non-invasive screening tools that can diagnose the tumor before it spreads.

The research team from the University of Washington has developed a new app that allows individuals to screen for pancreatic cancer and other diseases quickly by snapping a smartphone selfie.

Pancreatic Cancer - All About the Disease, its Diagnosis and Management
Pancreatic cancer often involves its exocrine part. It grows aggressively, and often detected late. Treatment options include surgery, radiation and chemotherapy.

‘BiliScreen uses a smartphone's built-in camera and as they snap a selfie the pictures of a person's eye are collected.’

Tweet it Now

Biliscreen, The New Smartphone App

BiliScreen is the new smartphone app. It uses a smartphone camera, computer vision algorithms and machine learning tools, which helps in detecting increased bilirubin levels in the sclera (the white part of the eye).

The paper on new app is being presented on September 13th at Ubicomp 2017, the Association for Computing Machinery's International Joint Conference on Pervasive and Ubiquitous Computing.

Jaundice is one of the earliest symptoms of pancreatic cancer and as well as for other diseases. Jaundice is a yellow discoloration of the skin and eyes. It is caused by a buildup of bilirubin in the blood.

The signs of jaundice when bilirubin levels are minimally elevated can be detected with an entirely new screening program that has been developed for at-risk individuals.

Promising Pancreatic Cancer Target Identified
Pancreatic cancer can be treated by promising treatments that could suppress the GRP78 protein.

In this clinical study, about 70 participants took part in the study and the BiliScreen app was used along with a 3-D printed box that controls the eye's exposure to light. The app had identified the cases 89.7 percent of the time correctly when compared to the blood test which is being currently used.

Early Detection of Symptoms

Role of Radiotherapy in Pancreatic Cancer
A higher dose of radiotherapy can improve survival in pancreatic cancer patients, finds a new study.

Alex Mariakakis, lead author and a doctoral student at the Paul G. Allen School of Computer Science & Engineering said that the problem with pancreatic cancer is that by the symptoms are noticed it is too late.

The research team hopes that this simple test can be done once a month at their home, which helps in diagnosing the disease early and starting treatment immediately can save their lives.

BiliScreen has been built on earlier work that is taken from the UW's Ubiquitous Computing Lab. Previously it was developed as BiliCam, which is a smartphone app that helps in screening newborns for jaundice by taking a picture of the baby's skin.

In a recent study published in the journal Pediatrics, it showed that BiliCam estimated the levels of bilirubin in 530 infants accurately.

The present research team collaborated with UW Medicine doctors, as the UbiComp lab specializes in using cameras, microphones and other common consumer devices like smartphones and tablets to screen for disease.

Currently, the blood test that the doctors use to measure bilirubin levels is inconvenient for frequent screening and requires access to a health care professional. The blood test is not suggested to adults unless there is a reason for concern.

BiliScreen is an easy-to-use, non-invasive tool that helps determine whether someone has to consult a doctor for further testing. This tool can also reduce the burden on patients with pancreatic cancer, especially those who require frequent bilirubin monitoring.

Detecting the color of bilirubin levels

In adults, the sclera or the white of the eye is more sensitive than skin to changes in bilirubin levels and can be an early warning sign for pancreatic cancer, hepatitis or Gilbert's syndrome.

The changes that occur in the sclera are more consistent across all races and ethnicities, unlike the skin color. By the time the yellowish discoloration in the sclera is noticed, the bilirubin levels have already passed cause for concern.

The UW research team wondered whether computer vision and machine learning tools could help detect these color changes that occur in the eye before humans could see them.

Shwetak Patel, senior author, the Washington Research Foundation Entrepreneurship Endowed Professor in Computer Science & Engineering and Electrical Engineering said, "The eyes are an attractive gateway into the body. Tears can tell you how much glucose you have, sclera can tell you how much bilirubin is in your blood. Our question was: Could we capture some of these changes that might lead to earlier detection with a selfie?"

The research team has developed a computer vision system which automatically and efficiently isolates the sclera or the white parts of the eye, that remains a valuable tool for medical diagnostics.

The smartphone app then calculates the color information from the sclera or the white of the eye based on the wavelengths of light that are being reflected and absorbed and thereby correlates it with the levels of bilirubin using machine learning algorithms.

The research team tested BiliScreen with two separate accessories to account for different lighting conditions; paper glasses were printed with colored squares, which can help calibrate the color and a 3-D printed box that blocks out ambient light.

Using the smartphone app with the box accessory, which is reminiscent of a Google Cardboard headset has led to better results.

Need for further research

Further, the research team needs to test the app on a wider range of people, who are at risk for jaundice and underlying conditions, and as well as to continually improve the usability like removing the need for accessories such as the box and glasses.

Dr. Jim Taylor, co-author, a professor in the UW Medicine Department of Pediatrics whose father died of pancreatic cancer at age 70 said that this relatively small initial clinical study shows that the technology has a promising future.

Taylor said that pancreatic cancer is a terrible disease that has no effective screening techniques right now.

"Our goal is to have more people who are unfortunate enough to get pancreatic cancer to be fortunate enough to catch it in time to have surgery that gives them a better chance of survival," said Taylor.

Source-Medindia