ELVCP: A Comprehensive Evaluation of Leukemia Prediction Using Enhanced Learning Based Vector Classification Principle

Cancer, defined as the uncontrolled growth of cells within the body, can take numerous forms, including but not limited to skin cancer, breast cancer, lung cancer, as well as blood malignancies such as leukaemia and lymphoma. Within numerous serious kinds of cancer, acute lymphoblastic leukaemia strikes out. Blood cancer diagnoses are notoriously time-consuming because haematologists often make mistakes. Therefore, this study considers a fresh approach to leukaemia classification using state-of-the-art technologies such as Deep Learning and Machine Learning. Eosinophil, lymphocyte, monocyte, and neutrophil prediction and analysis by hand is a laborious and time-consuming process. Earlier research attempted to forecast blood cancer using a plethora of deep learning and machine learning methods; however, these efforts were not without their flaws. In order to assess the efficacy of the suggested scheme, the proposed research pipeline is comprised of several interdependent components, such as dataset construction and feature extraction using an advanced deep learning based approach known as the Enhanced Learning based Vector Classification Principle (ELVCP). Image processing is a strength of the proposed deep learning model, ELVCP, which employs a number of learning criteria, including learning rate and epochs, and a range of analysis, prediction, and learning methods at different degrees. The proposed model used an extensive range of performance methods and processes to incorporate techniques for image processing to predict cancer-causing white blood cells, as well as used an extensive number of models for transfer learning with various parameters for each model to select the best prediction model.