Classification of Unhealthy and Healthy Neonates in Neonatal Intensive Care Units Using Medical Thermography Processing and Artificial Neural Network

Abstract

Tracking temperature changes of neonatals in the neonatal intensive care unit is quite important in the prediagnosis of diseases or the evaluation of follow-up treatment. The purpose of this study is to develop an analysis system based on thermal imaging, which is the contact-free, nonionized and noninvasive method for the neonatal. For this purpose, 190 images taken from 19 healthy and 19 unhealthy neonates were used. In general, this study consists of three steps. First, the temperature map of the images was segmented. Then, discrete wavelet transform (DWT), curvelet transform and contourlet transform as multiresolution methods were applied to them, and feature vectors were extracted by using their approximation coefficients. After that, all feature vectors were given as an input to the artificial neural networks (ANN) and support vector machines. According to the obtained results, the best accuracy rate was 98.42% when using DWT+ANN. © 2019 Elsevier Inc. All rights reserved.