Classification of Subtypes of Acute Lymphoblastic Leukemia Using Feature Fusion from Blood Smear Images
Ghazala Alhadi Eljadi, Ahmed O. Lawgali, Salwa Elakeili · 2025
Early detection of Acute Lymphoblastic Leukemia (ALL) is vital for providing appropriate treatment, which requires accurate diagnosis to identify the types of the disease. Therefore, this study focuses on evaluating the performance of deep learning models in classifying different types of leukemia using three pre-trained CNN models: MobileNet V2, DenseNet201, and EfficientNet, to extract deep features. These features are then combined into a single set. An information exchange technique was used to select the best features after merging, and SMOTEENN was employed to address feature imbalance. The results showed that combining features extracted by the pre-trained CNN models achieved high accuracy and reliability, reaching 99.66%, enhancing the performance in accurately and quickly classifying patients. This approach not only improves diagnostic accuracy but also contributes to accelerating the decision-making process for treatment, enabling doctors to better tailor therapies and thereby improve patient outcomes. The findings underscore the importance of ongoing research in this field and provide future recommendations for enhancing performance and increasing classification accuracy in similar medical applications.