ABSTRACT
Brain tumors classification is one of the most essential and difficult issues in medical image processing since manual classification with human aid might result in inaccurate prognosis and diagnosis. Furthermore, it is a challenging task when there is a large amount of data to filter through. It is difficult to discern tumors regions from surrounding normal tissue when extracting them from pictures because of the high degree of visual diversity and resemblance between brain tumors and normal tissues. In this research, we propose a method for automatically identifying and segmenting brain tumors in MRI scans utilizing convolutional neural network (CNN) and machine learning (ML) techniques. When these algorithms are applied to MRI scans, the prediction of brain tumors is very quick, and the increased accuracy aids in the treatment of patients. These forecasts also assist the radiologist in making timely decisions. Different medical images, such as MRI brain cancer images, are used in this proposed work to detect tumors stages. The purpose of this research is to design and build a system that uses CNN and ML algorithms to reliably classify brain tumors stages. Over various ML techniques, CNN findings showed the highest accuracy of 98.21%, precision of 97.08%, and recall of 96.52%.
