Leukemia Detection Performance: A Comparative Study of EfficientNetB3 and EfficientNetB5
Aseel Alshoraihy, Housam Hasan Bou Issa, Anagheem Ibrahim, Agbonrhienrhien Osazee Osca · 2024
Leukemia, a complex hematologic malignancy, demands accurate and timely detection for effective treatment. This study investigates the performance of two deep learning models, EfficientN etB3 and EfficientN etB5, in the context of leukemia detection. Leveraging a dataset comprising diverse leukemia cell images, we conduct a comprehensive comparative analysis to evaluate the efficacy of these models. Our study delves into the complexity of detection sensitivity, specificity, and overall accuracy through careful consideration of experimentation and performance metrics assessment. The findings highlight distinguishing differences in detection capabilities between EfficientN etB3 and EfficientN etB5, shedding light on their strengths and weaknesses. Insights collected from this research Endeavor contribute to advancing the field of leukemia detection but also offer valuable guidance for healthcare practitioners and researchers aiming to leverage deep learning techniques for improved disease diagnosis and management.