Open Access

Malaria Blood Smear Classification Using Deep Learning and Best Features Selection

Talha Imran¹, Muhammad Attique Khan², Muhammad Sharif¹, Usman Tariq³, Yu-Dong Zhang⁴, Yunyoung Nam^5,*, Yunja Nam⁵, Byeong-Gwon Kang⁵

1 Department of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt, Pakistan
2 Department of Computer Science, HITEC University Taxila, Taxila, Pakistan
3 College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Khraj, Saudi Arabia
4 Department of Informatics, University of Leicester, Leicester, UK
5 Department of ICT Convergence, Soonchunhyang University, Asan, Korea

* Corresponding Author: Yunyoung Nam. Email:

(This article belongs to the Special Issue: Recent Advances in Deep Learning for Medical Image Analysis)

Computers, Materials & Continua 2022, 70(1), 1875-1891. https://doi.org/10.32604/cmc.2022.018946

Received 27 March 2021; Accepted 18 May 2021; Issue published 07 September 2021

Abstract

Malaria is a critical health condition that affects both sultry and frigid region worldwide, giving rise to millions of cases of disease and thousands of deaths over the years. Malaria is caused by parasites that enter the human red blood cells, grow there, and damage them over time. Therefore, it is diagnosed by a detailed examination of blood cells under the microscope. This is the most extensively used malaria diagnosis technique, but it yields limited and unreliable results due to the manual human involvement. In this work, an automated malaria blood smear classification model is proposed, which takes images of both infected and healthy cells and preprocesses them in the L*a*b* color space by employing several contrast enhancement methods. Feature extraction is performed using two pretrained deep convolutional neural networks, DarkNet-53 and DenseNet-201. The features are subsequently agglutinated to be optimized through a nature-based feature reduction method called the whale optimization algorithm. Several classifiers are effectuated on the reduced features, and the achieved results excel in both accuracy and time compared to previously proposed methods.

---

Keywords

---

Citations