A review on leukemia detection and classification using Artificial Intelligence-based techniques

Leukemia is a type of cancer affecting blood-forming tissues, where timely diagnosis is crucial for early intervention and better treatment outcomes. Traditional detection methods are time-intensive, laborious, and depend on skilled manual examination of bone marrow or peripheral blood smears. However, research in automated leukemia detection has significantly advanced with the development of sophisticated image processing techniques using Machine Learning (ML) and Deep Learning (DL) approaches. This literature review analyzes recent studies on automated leukemia detection, utilizing various specimens such as gene expression data, images of bone marrow, and peripheral blood smears. It also provides a list of public repositories offering access to these datasets. The reviewed articles are sourced from reputable databases like ScienceDirect, Springer, IEEE Xplore, Wiley, and others, covering the period from 2018 to 2023. The review examines the specificity of the field of study, techniques, classifiers, optimizers, platforms, and datasets used in the referenced articles. Findings indicate the efficacy of both ML and DL techniques, with DL often surpassing traditional ML methods. Diverse datasets, innovative feature selection, and optimization techniques have further enhanced leukemia detection and classification methodologies, highlighting ongoing advancements in the field. © 2024 Elsevier Ltd