A New Model for Blood Cancer Classification Based on Deep Learning Techniques

Artificial intelligence and deep learning algorithms have become essential fields in medical science. These help doctors detect diseases early, reduce the incidence of errors, decrease time required for disease diagnosis, thereby saving human lives. Deep models are widely used Computer-Aided Diagnosis Systems (CAD) classification various diseases, including blood cancer. Early diagnosis cancer is crucial effective treatment patients' Therefore, this study developed two distinct to classify eight types include follicular lymphoma (FL), mantle cell (MCL), chronic lymphocytic leukemia (CLL), acute myeloid (AML), subtypes lymphoblastic (ALL) known as early pre-B, pro-B ALL, benign. AML ALL specific classifications cancer, while FL, MCL, CLL lymphoma. Both consist different phases, data collection, preprocessing, feature extraction techniques, process. The techniques applied these phases same both proposed models, except phase. first model utilizes VGG16 architecture, second DenseNet-121. results indicated that DenseNet-121 achieved a lower accuracy compared VGG16. exhibited excellent results, achieving an 98.2% when classifying classes. This outcome suggests most classifier utilized dataset.