Blood Leukemia remains among the most lethal diseases globally, marked by a significantly high mortality rate. Early diagnosis poses a major challenge due to the subtle and incomplete manifestation of symptoms in initial stages. Recently, artificial intelligence has emerged as a transformative force in healthcare, offering solutions to problems that traditional methods struggle to address. A key area of advancement is the AI-driven classification of leukemia. Prior research underscores the critical role of classification accuracy in this domain, though achieving consistently high precision remains complex. Various methodologies offer distinct advantages and limitations. This study delivers an in-depth evaluation of machine learning techniques applied to automated leukemia detection, emphasizing the unique strengths of each approach. This paper presents a comprehensive analysis of the various machine learning based approaches employed for automated blood leukemia detection, highlighting the salient features of each approach.

Keywords—Blood Leukemia, Microscopic images, machine learning, automated classification, classification accuracy.