Non-Invasive Bilirubin Level Quantification and Jaundice Detection by Sclera Image Processing

• Published in: 2019 IEEE Global Humanitarian Technology Conference (GHTC) pp. 1 - 7
• Main Authors: Miah, Md. Messal Monem, Tazim, Rafat Jamal, Johora, Fatema Tuj, Al Imran, Md. Ibrahim, Surma, Sanzida Sayedul, Islam, Fariba, Shabab, Rashid, Shahnaz, Celia, Subhana, Arik
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-10-2019
• Subjects: bilirubin; hyperbilirubinemia; invasive; jaundice; neonatal; non-invasive; sclera; skin; yellowness
• DOI: 10.1109/GHTC46095.2019.9033059

The yellow discoloration of the skin and sclera are the symptoms of excessive bilirubin in the blood. Bilirubin level in human body is increased when the blood system is not capable of removing the sufficient amount of bilirubin from the blood. Jaundice is only recognizable to the naked eye in severe stages, but a ubiquitous test using computer vision and machine learning can detect milder forms of jaundice. The conventional processes of measuring bilirubin level are time consuming, costly and invasive in nature. In this paper, an image processing based non-invasive technique for determining the bilirubin level in blood of human body is presented where the degree of yellowness of the sclera is used to quantify the level of bilirubin. The non-invasive technique can efficiently and quickly detect jaundice problem while reducing the pain compared to the conventional technique. However, the process presented in this paper is applicable mostly for adults. The total system is designed for a community clinic where the number of patients is large and the report of the bilirubin test as well as the treatment for the patients is to be provided at a very low cost within shortest possible time.