Automated Leukaemia Cancer Detection Using Deep Learning Techniques

Leukaemia, a critical blood cancer, is marked by an excessive proliferation of immature white blood cells in the bone marrow, significantly impacting healthy cell function and presenting serious health risks. Early and accurate diagnosis of leukaemia remains a major challenge, with the disease categorized into acute and chronic forms, and acute lymphocytic leukaemia (ALL) accounting for around 25% of childhood cancer cases. This paper proposes a novel method for leukaemia detection using advanced deep learning techniques. We specifically use VGG19 and ResNet152, to analyze blood smear images and extract detailed features that enhance classification precision. Our approach is novel in integrating deep learning models with traditional machine learning classifiers, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, Random Forest, XGBoost, Logistic Regression, and AdaBoost. This hybrid method leverages the strengths of both deep learning for feature extraction and machine learning classifiers for enhanced classification, setting it apart from previous approaches that rely solely on deep learning models. The experimental results highlight the effectiveness of this deep learning-based approach in improving diagnostic accuracy and supporting effective clinical decision-making.