Brain tumor detection and classification based on machine learning systems

As a growing country, Zimbabwe must adopt these technologies since they offer numerous benefits, including precision and accuracy. Because a significant volume of MRI data must be reviewed, this procedure takes long and is unsuitable for big data. Because automated solutions are more cost-effective, they are essential. Automated medical imaging has become a hot issue in a variety of medical diagnostic checking. Magnetic Resonance Imaging (MRI) tumor diagnosis that is automated is crucial because it provides information about abnormal tissues that are needed for treatment planning. Human inspection is the traditional approach for detecting defects in magnetic resonance brain imaging. This method is impractical when dealing with large amounts of data. As a result, radiologists are developing automated tumor detection technologies to save time. It is necessary to use MATLAB to train an artificial neural network to identify brain cancers. In addition, an algorithm that can distinguish and categorize tumors into carcinogenic and non-cancerous tumors must be developed. The complexity and variety of malignancies make MRI brain tumor diagnosis tough task. Machine learning approaches are utilized to detect malignancies in brain MRI in this study. In this research paper work, three stages are implemented in preprocessing on the brain. To extract texture features, the Gray Level Co-occurrence Matrix (GLCM) is used. They are then classified using a machine learning technique, indicating the feasibility of utilizing machine vision to discriminate between cancerous and non-cancerous brain tumors. As a result, an AI process is used to arrange them correctly, demonstrating the feasibility of using machine vision to distinguish between cancerous and non-malignant cerebrum growths. It has the potential to make patient management easier in the future. Computer vision is one of the most widely utilized technology technologies for skin cancer detection systems in most industrialized countries.