Integrative Deep Learning for Enhanced Acute Lymphoblastic Leukemia Detection: A Comprehensive Study on the ALL-IDB Dataset

Acute Lymphoblastic Leukemia (ALL) is a malignant neoplasm defined by the rapid proliferation of early lymphoid progenitors (lymphoblasts) within the bone marrow and peripheral blood. Due to its aggressive course, prompt and accurate diagnosis is essential and has a profound impact on patient outcomes. This study proposes an integrative deep learning method for ALL detection using the Acute Lymphoblastic Leukemia Image Database (ALL-IDB). This is accomplished by fusing one modified clinical data CNN integrated through an attention mechanism with another modified pre-trained CNN for image analysis. The performance of the proposed model was evaluated using the ALL-IDB1 and ALL-IDB2 datasets, achieving 99.2% accuracy with AUC at 0.998%. By incorporating clinical with image data, an overall increase of 2.3% in accuracy and 0.007 in AUC was observed. The results show that using deep learning to detect ALL is accurate and possible, laying the foundations for AI-based diagnoses of hematological cancers to be more accurate.