Brain Tumor Classification using Deep Learning Convolutional Neural Network

Abstract

Brain tumors are another prevalent and devastating disease, with a life expectancy of only a few years in the most advanced stages. As a result, therapy planning is crucial in enhancing a patient's quality of life. Computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound imaging are all commonly used to assess tumors in the brain, lungs, liver, breast, prostate, and other parts of the body. MRI imaging is used to diagnose several brain cancers in particular. On the other hand, the massive volume of data collected by MRI scans disrupts tumor or non-tumor segregation for a long time. However, due to the limited quantity of photos, it has a lot of drawbacks (for example, accurate values). A dependable and automatic separation mechanism is necessary to avoid death. Automatic brain tumor differentiation is a serious difficulty in terms of discerning large areas and the surrounding numerous variations of brain tumor shapes. This study employs Convolutional Neural Networks (CNN) classification to detect brain cancers automatically. The small bundles make up deep structural plans. A brain tumor is a malignant growth that results from unregulated and abnormal cell division. Deep learning developments in the realm of medical imaging for disease diagnosis have aided healthcare goods. Machine learning systems that perform visual learning or image recognition tasks (CNNs) are commonly used.