Computer-Assisted Leukemia Detection and Classification using Machine Learning

In the contemporary era of technological advancements, the medical field has witnessed significant progress through the implementation of autonomous systems for disease identification. Leukemia, a type of blood cancer characterized by abnormal growth of white blood cells (WBC) in the bone marrow, presents a critical challenge in diagnosis and classification. Manual methods such as morphological image analysis or Complete Blood Count (CBC) are time-consuming and prone to inaccuracies, necessitating more efficient approaches. This research study proposes a Computer-Assisted Leukemia Detection and Classification using Machine Learning (ML) methodology. Leveraging a publicly available dataset from Kaggle, the approach identifies various cell types in images, distinguishing WBCs from red blood cells (RBC) and platelets. Features related to lymphocyte shape and color properties are extracted, followed by dimensionality reduction and classification using a Support Vector Machine (SVM) classifier to categorize cells into normal and blast. The proposed method is evaluated using metrics such as Mean-Square Error (MSE), Accuracy, Precision, and Recall, demonstrating superior performance compared to existing Machine Learning (ML) systems. This automated leukemia diagnosis approach offers increased accuracy, speed, and efficiency, showcasing its potential to revolutionize disease detection in the medical domain.