Back to articles
Regular Articles
Volume: 65 | Article ID: jist1218
Image
Smartphones’ Skin Colour Reproduction Analysis for Neonatal Jaundice Detection
  DOI :  10.2352/J.ImagingSci.Technol.2021.65.6.060407  Published OnlineNovember 2021
Abstract
Abstract

In recent years, smartphone-based colour imaging systems are being increasingly used for Neonatal jaundice detection applications. These systems are based on the estimation of bilirubin concentration levels that correlates with newborns’ skin colour images corresponding to total serum bilirubin (TSB) and transcutaneous bilirubinometry (TcB) measurements. However, the colour reproduction capacity of smartphone cameras are known to be influenced by various factors including the technological and acquisition process variabilities. To make an accurate bilirubin estimation, irrespective of the type of smartphone and illumination conditions used to capture the newborns’ skin images, an inclusive and complete model, or data set, which can represent all the possible real world acquisitions scenarios needs to be utilized. Due to various challenges in generating such a model or a data set, some solutions tend towards the application of reduced data set (designed for reference conditions and devices only) and colour correction systems (for the transformation of other smartphone skin images to the reference space). Such approaches will make the bilirubin estimation methods highly dependent on the accuracy of their employed colour correction systems, and the capability of reducing device-to-device colour reproduction variability. However, the state-of-the-art methods with similar methodologies were only evaluated and validated on a single smartphone camera. The vulnerability of the systems in making an incorrect jaundice diagnosis can only be shown with a thorough investigation of the colour reproduction variability for extended number of smartphones and illumination conditions. Accordingly, this work presents and discuss the results of such broad investigation, including the evaluation of seven smartphone cameras, ten light sources, and three different colour correction approaches. The overall results show statistically significant colour differences among devices, even after colour correction applications, and that further analysis on clinically significance of such differences is required for skin colour based jaundice diagnosis.

Subject Areas :
Views 125
Downloads 16
 articleview.views 125
 articleview.downloads 16
  Cite this article 

Mekides Assefa Abebe, Jon Yngve Hardeberg, Gunnar Vartdal, "Smartphones’ Skin Colour Reproduction Analysis for Neonatal Jaundice Detectionin Journal of Imaging Science and Technology,  2021,  pp 060407-1 - 060407-15,  https://doi.org/10.2352/J.ImagingSci.Technol.2021.65.6.060407

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2021
  Article timeline 
  • received August 2021
  • accepted November 2021
  • PublishedNovember 2021

Preprint submitted to:
  Login or subscribe to view the content