EfficientNetB3 in Leukemia Detection: Advancements in Medical Imaging Analysis

Abstract

The diagnosis of leukemia is essential for prompt and effective treatment, but conventional methods can be invasive, costly, and lengthy. The emergence of sophisticated machine learning models, like the EfficientNetB3 model, presents a hopeful option by utilizing the capabilities of artificial intelligence to improve diagnostic methods. This literature review explores the application of EfficientNetB3 in leukemia diagnosis, emphasizing its methodology, benefits, and limitations. EfficientNetB3, a member of the EfficientNet family, employs a scalable neural network architecture that balances efficiency and accuracy, resulting in enhanced diagnostic precision and robustness. By automating the detection process, the model has the potential to significantly improve diagnostic speed while reducing reliance on invasive procedures. However, challenges persist, including the quality and diversity of training datasets, the interpretability of model decisions, and the computational resources required for large-scale implementation. Recent advancements suggest strategies to address these obstacles, showing the way for integrating EfficientNetB3 into clinical practice soon enough to improve patient outcomes in the future.

Received: 2 July 2024 | Revised: 7 January 2025 | Accepted: 24 January 2025

Conflicts of Interest

The author declares that he has no conflicts of interest to this work.

Data Availability Statement

The data that support the findings of this study are openly available in The Cancer Imaging Archive at https://www.cancerimagingarchive.net/.

Author Contribution Statement

Aseel Alshoraihy: Conceptualization, Software, Validation, Formal analysis, Resources, Writing – original draft, Writing – review & editing, Visualization, Supervision.