HealthCore: A Multi-Modal Framework to Predict Leukemia Disease Using Integrative Healthcare Image Evaluation
Napa Lakshmi, Arun Prasath K, Joshua Kennedy D, Koramutla Teja Sai, Meenakshi M, B Miruna · 2025
The metastasis, cell destruction, and uncontrolled multiplication of white blood cells that characterize blood cancer make it one of the deadly childhood disorders. Blood malignancy can result in death if it is not promptly dealt with. Leukemia, which is also referred to as “White Blood Cancer,” is the most prevalent form of blood cancer and has a severe impact on a significant number of individuals. It is primarily formed in the marrow of bones. The body is harmed and malignant cells are produced as a result of uncontrolled white blood cell proliferation in leukemia. There have been several advancements in the use of computer-assisted technology for leukemia detection, management, treatment, and diagnosis in recent years. Numerous researchers proposed algorithms, methods, and approaches to combat this illness. Upon implementing these methods with conventional dataset samples and their own creations, they achieved numerous favorable results. The use of imaging data sets in medical tests signifies the significant significance that big data plays in the data gathering process for datasets. In this paper, a novel deep learning methodology known as Enhanced Neuro Learning Optimization (ENLO) is introduced to effectively identify the Leukemia disease. The proposed scheme is cross-validated with the traditional learning algorithm Convolutional Neural Network (CNN) to assess its efficiency. The ENLO model that has been proposed is crucial in the reduction of mortality rates, as it identifies blood cancer in its early phases, thereby increasing the probability of successful treatment and a potential cure. The goal is to reduce the mortality rate of blood cancer by facilitating the early diagnosis of the disease, thereby providing individuals with a greater likelihood of survival.