Blood Cells Cancer Detection Based on Deep Learning

1 Electrical and Electronics Engineering, University of Tripoli, Libya
2 Faculty of Engineering, Sabratha University, Sabratha, Libya
3 School of Computational Sciences, S.R.T.M. University, Nanded, India
4 Department of Information System Management, Sanaa University, Sana'a Yemen
5 Department of Computer Engineering, Faculty of Engineering Ege University, Turkey
* Corresponding author. Tel.: +218 91-6094184; email: a.abougarair@uot.edu.ly
Manuscript submitted January 10, 2024; revised March 8, 2024; accepted May 21, 2024.

Abstract—Acute Lymphocytic Leukemia (ALL) is a form of cancer characterized by the abnormal production of white blood cells in the bone marrow. These cells do not function properly, leading to the overcrowding of healthy cells and weakening the body's immune system, making it more susceptible to infections. ALL progresses rapidly in children, and without timely treatment, it can be fatal. However, manually detecting this disease is a time-consuming and laborious task. In contrast, machine learning and deep learning techniques offer faster and more accurate detection methods. This study proposes a deep feature selection approach for identifying Acute Lymphocytic Leukemia in images of peripheral blood specimens. The approach utilizes the MobileNetV2 model to extract deep features from a dataset of peripheral blood specimen images, which are then used to train the model. By leveraging the base structure of MobileNetV2, the model demonstrates a high level of accuracy. Furthermore, by incorporating activation functions and additional layers into the model, the accuracy is significantly improved..

keywords—Blood cell, Cancer, CNN, deep learning, MobileNetV2.

Cite: Ahmed J. Abougarair, M. Alshaibi, Amany K. Alarbish, Mohammed Ali Qasem, Doaa Abdo Othman Qasem, Fursan Thabit, Ozgu Can"Blood Cells Cancer Detection Based on Deep Learning," Journal of Advances in Artificial Intelligence vol. 2, no. 1, pp. 108-121, 2024.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).