FRONT PAGE: Diagnosing Jaundice In The Blink Of An Eye From A Digital Camera

dWeb.News Article from Daniel Webster dWeb.News

Newswise — Imagine a system that can detect within one second whether a newborn baby has jaundice, a condition affecting 60 per cent of infants, and in severe cases leading to brain damage and hearing loss.

Visualize that system to immediately start a treatment program and notify a nurse via text message.

Thanks in part to researchers from Iraq, Adelaide and other countries, these three scenarios are possible.

Engineers at the University of South Australia, Middle Technical University created imaging software that can diagnose jaundice within a blink of an eye. It also automatically turns on a blue LED to counteract it. The software then sends the carer an SMS with the diagnosis.

Jaundice, a condition that occurs in premature babies and newborns is caused by an excess of an orange-yellow pigment called Bilirubin. The condition usually resolves when the baby’s liver matures enough to eliminate it from their bodies.

In severe cases of jaundice caused by sickle cells anaemia blood disorders or a lack of certain enzymes, phototherapy can be used to treat the condition. This uses fluorescent blue light to reduce the bilirubin found in the baby’s skin. Professor Javaan Chahl, a remote sensing engineer at UniSA, says that jaundice is more common in developing countries. This is because there is often not enough medical staff or the equipment to treat it.

” Using image processing techniques derived from the camera’s data, we can quickly and inexpensively screen newborns for jaundice before performing a blood test.

“A microcontroller activates blue LED phototherapy when the bilirubin levels exceed a threshold and sends details to a smartphone.

“This can be done in one second, literally, which can make all the difference in severe cases, where brain damage and hearing loss can result if treatment is not administered quickly.”

Researchers tested the system in an intensive care unit in Mosul, Iraq, on 20 newborns diagnosed with jaundice. A second data set captured 16 images of newborns, five of whom were healthy, and the remainder jaundiced. Four other manikins were also tested with the system, including those with brown and white skins.

” Previous research using sensors to detect jaundice pigmentation has failed to produce a non-invasive method. Professor Chahl states that the methods tested were unreliable, expensive, inefficient, and sometimes caused skin allergies and infections.

” Our system detects jaundice immediately using a digital representation of colour that allows for high diagnostic accuracy and relatively low costs. It could be widely used in hospitals worldwide and medical centres where laboratory facilities and trained medical staff are not available.”

The study has been published in engineering journal Designs.

Notes for editors

Neonatal jaundice detection using a computer vision system” is authored by Prof Javaan Chahl, Joint Chair of Sensor Systems at UniSA and the Defence Science and Technology Group, and Iraqi researchers Ms Warqaa Hashim, Dr Ali Al-Naji, Dr Izzat A. Al-Rayahi, and Dr Makram Alkhaled.

Newborn jaundice occurs in up to 85 per cent of all live births, including premature babies. Although it usually disappears in 3-5 days, severe complications can cause thousands of infant deaths, especially in Africa and Southeast Asia where there are few options. A 2018 paper estimated that 75,000 children are living with brain dysfunction worldwide due to complications from jaundice.

For More dWeb.News Front Page News at

The post FRONT PAGE: Diagnosing Jaundice In The Blink Of An Eye From A Digital Camera appeared first on dWeb.News dWeb.News from Daniel Webster Publisher dWeb.News – dWeb Local Tech News and Business News

dWeb.NewsRead More

Similar Posts