Acute Lymphoblastic Leukemia Classification Using Modified VGG16 Architecture

Fallah H.  Najjar; Salman Abd  Kadum; Ola N.  Kadhim; Ali J.  Ramadhan

doi:10.24996/ijs.2025.66.11.37

Authors

Fallah H. Najjar Department of Computer System Techniques, Technical Institute of Najaf, Al-Furat Al-Awsat Technical University, 54001 Najaf, Iraq / Department of Emerging Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Malaysia https://orcid.org/0000-0002-5414-9260
Salman Abd Kadum Department of Computer System Techniques, Technical Institute of Najaf, Al-Furat Al-Awsat Technical University, 54001 Najaf, Iraq
Ola N. Kadhim Technical Institute of Al-Mussaib, Al-Furat Al-Awsat Technical University, 54001 Najaf, Iraq https://orcid.org/0000-0002-8037-0524
Ali J. Ramadhan Department of Computer Techniques Engineering, College of Technical Engineering, University of Alkafeel, 54001 Najaf, Iraq https://orcid.org/0000-0003-3253-3525

DOI:

https://doi.org/10.24996/ijs.2025.66.11.37

Keywords:

Acute Lymphoblastic Leukemia, ALL, VGG16, medical imaging, deep learning

Abstract

Acute lymphoblastic leukemia (ALL) diagnosis is a challenge, including invasive classical methods, which are time-consuming, inaccurate, and error-prone. In this paper, we propose modifying the VGG16 architecture to improve its performance in the classification task. We utilize the Acute Lymphoblastic Leukemia (ALL) image dataset to train the proposed modified VGG16 model. The dataset was split into training and testing sets at a ratio of 80% for training data, 10% for validation data, and 10% for testing data. The ALL dataset consists of four classes: Benign, Early, Pre, and Pro. The results of the proposed modified VGG16 model were very satisfactory: accuracy, 96.59%; precision, 96.61%; sensitivity, 96.59%; F1-score, 96.58%; and Matthew's correlation coefficient of 95.35%. It was demonstrated that the image size also influences the model, indicating a trade-off based on how efficient a computational one can be concerning classification accuracy. These findings highlight the promise of deep learning algorithms to revolutionize all characterizations and offer potential utility for future applications in medical imaging.