Brain Tumor Classification and Detection Using Machine Learning by Analyzing MRI Images

In recent years, there has been a rise in the death rate as a consequence of the proliferation of encephaloma tumors among individuals of all ages. The identification of physical tumors is a challenging endeavor that requires a significant amount of time and effort on the part of medical professionals. This is due to the complex nature of the tumors and the presence of unwanted noise in the MR imaging data. Since this is the case, the diagnosis and location of tumors at an early stage are of the highest significance. The use of medical imaging in conjunction with segmentation and relegation techniques has the potential to deliver an accurate and speedy diagnosis. This is accomplished by monitoring and forecasting the progression of cancer at its various stages. In this article, we provide a method that is based on machine learning and is used to segment and categorize magnetic resonance imaging (MRI) pictures for the purpose of detecting brain cancers. To segment pictures, extract features, and categorize them, this system makes use of the Naive Bayes method, the Support Vector Machine technique, and the K Nearest Neighbor algorithm.