Classification of Red Blood Cells Randomly Selected from Dataset of National Institutes of Health

Abstract

Millions of people worldwide suffer from malaria, a potentially fatal disease. Early and precise diagnosis is essential for the medical condition to be successfully treated and managed. This paper employs three computer aided methods to determine percentages of red blood cells that are either parasitic or uninfected given test set(s) randomly obtained from National Institutes of Health (NIH) dataset. The three methods employed are traditional image processing, Support Vector Machine (SVM), and Convolutional Neural Networks based Deep Learning (CNN-DL). The simulations were performed using a dataset that had 27,558 images of red blood cells. The traditional image processing method achieves an accuracy of 91.97%. SVM classifier using Histogram of Oriented Gradients (HOG) features had accuracy of 88.6% and with features extracted using Local Binary Patterns (LBP) accuracy had improved to 92.5%. The two previous methods were proved to be inferior when compared with the CNN- DL classification that gave an accuracy of 95.7%.