Open Access

ARTICLE

Diagnosis of Leukemia Disease Based on Enhanced Virtual Neural Network

K. Muthumayil¹, S. Manikandan², S. Srinivasan³, José Escorcia-Gutierrez^4,*, Margarita Gamarra⁵, Romany F. Mansour⁶

1 Department of Information Technology, PSNA College of Engineering and Technology, Dindigul, 624622, India
2 Department of Information Technology, K. Ramakrishnan College of Engineering, Tiruchirappalli, 621112, India
3 Department of Biomedical Engineering, Saveetha School of Engineering, SIMATS, Chennai, 602105, India
4 Electronic and Telecommunicacions Program, Universidad Autónoma del Caribe, Barranquilla, 08001, Colombia
5 Department of Computational Science and Electronic, Universidad de la Costa, CUC, Barranquilla, 08001, Colombia
6 Department of Mathematics, Faculty of Science, New Valley University, El-Kharga, 72511, Egypt

* Corresponding Author: José Escorcia-Gutierrez. Email:

Computers, Materials & Continua 2021, 69(2), 2031-2044. https://doi.org/10.32604/cmc.2021.017116

Received 21 January 2021; Accepted 16 April 2021; Issue published 21 July 2021

Abstract

White Blood Cell (WBC) cancer or leukemia is one of the serious cancers that threaten the existence of human beings. In spite of its prevalence and serious consequences, it is mostly diagnosed through manual practices. The risks of inappropriate, sub-standard and wrong or biased diagnosis are high in manual methods. So, there is a need exists for automatic diagnosis and classification method that can replace the manual process. Leukemia is mainly classified into acute and chronic types. The current research work proposed a computer-based application to classify the disease. In the feature extraction stage, we use excellent physical properties to improve the diagnostic system's accuracy, based on Enhanced Color Co-Occurrence Matrix. The study is aimed at identification and classification of chronic lymphocytic leukemia using microscopic images of WBCs based on Enhanced Virtual Neural Network (EVNN) classification. The proposed method achieved optimum accuracy in detection and classification of leukemia from WBC images. Thus, the study results establish the superiority of the proposed method in automated diagnosis of leukemia. The values achieved by the proposed method in terms of sensitivity, specificity, accuracy, and error rate were 97.8%, 89.9%, 76.6%, and 2.2%, respectively. Furthermore, the system could predict the disease in prior through images, and the probabilities of disease detection are also highly optimistic.

---

Keywords

---