DCVCP: Experimental Evaluation of Leukaemia Disease Prediction Using Deep Convoluted Vector Classification Principle

A wide variety of cancers, including skin, breast, lung, and blood malignancies such as lymphoma and leukemia, are defined by the uncontrolled growth of cells within the body. Acquired lymphoblastic leukemia is among the most prominent cancers. Blood cancer diagnoses are notoriously time-consuming because hematologists often make mistakes. With the use of cutting-edge tools like Deep Learning and Machine Learning, this study considers a fresh approach to leukemia classification. The precise diagnosis of blood cancer is a crucial medical process, but it is also one of the most costly and challenging for clinical staff to do. Blood cancer is one of many severe forms of the disease. The devastating and deadly blood cancers, lymphoma and leukemia, impact people of all ages and genders, and they are a leading cause of other illnesses and an elevated survival rate. Damage to and an increase in immature monocytes, neutrophils, eosinophils, and lymphocytes are hallmarks of both leukemia and lymphoma. Predicting and treating blood cancer early is crucial for improving survival rates in the health industry. These days, a number of manual methods exist for analyzing and predicting blood cancer based on microscopic medical reports of white blood cell images; this method is both reliable and deadly. It takes a lot of time and effort to manually forecast and analyze eosinophils, lymphocytes, monocytes, and neutrophils. The Deep Convoluted Vector Classification Principle (DCVCP) is a new deep learning technique for leukemia illness detection that was described in this study. To test how well it works, it was cross-validated with the current method, the Convolutional Neural Network (CNN). findings from this study show that DCVCP can effectively leverage data from network sensors to identify blood cancer, which might lead to faster findings and lower costs in clinical settings.