Leukaemia Blood Cancer Detection using Machine Learning

Leukaemia is a cancer of the blood and bone marrow caused by the uncontrolled growth of abnormal white blood cells. Conventional diagnosis is mostly carried out by pathologists using microscopic blood smear examination, which is labour-intensive, time-consuming, and sometimes inconsistent. This paper introduces a computer-assisted system that applies machine learning and digital image processing to automate the detection process. The system follows a modular pipeline consisting of pre-processing, segmentation, feature extraction, and classification using Convolutional Neural Networks (CNNs). A graphical user interface (GUI) was designed to make the tool user-friendly for healthcare professionals. The results show that the model is capable of achieving high accuracy in classifying leukaemia cell types, thus reducing diagnostic delays and minimizing human error. This approach has the potential to be deployed in hospitals and remote healthcare centers, providing fast and reliable decision support for doctors.