Image analysis and machine learning-based malaria assessment system
Kyle Manning, Xiaojun Zhai, Wangyang Yu
Abstract
Malaria is an important and worldwide fatal disease that has been widely reported by the World Health Organization (WHO), and it has about 219 million cases worldwide, with 435,000 of those mortal. The common malaria diagnosis approach is heavily reliant on highly trained experts, who use a microscope to examine the samples. Therefore, there is a need to create an automated solution for the diagnosis of malaria. One of the main objectives of this work is to create a design tool that could be used to diagnose malaria from the image of a blood sample. In this paper, we firstly developed a graphical user interface that could be used to help segment red blood cells and infected cells and allow the users to analyze the blood samples. Secondly, a Feed-forward Neural Network (FNN) is designed to classify the cells into two classes. The achieved results show that the proposed techniques can be used to detect malaria, as it has achieved 92% accuracy with a database that contains 27,560 benchmark images.