Brain Tumor Detection using Smart Deep Learning

The very common and aggressive disease, brain tumors, has a short period of existence in human life in its most severe form. As a result, therapy planning is critical to increasing patients' quality of life. To examine cancers in the brain, breast, liver, and other body parts, image modalities such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging) are utilized. This research uses X-ray pictures in particular to diagnose brain cancers. This research is about Convolutional Neural Networks, or CNN, and this research describes how to detect brain tumors using X-rays and MRIs. It speeds up and increases the treatment's uniformity. A lot of papers have already been published on “brain tumor detection”. This proposed CNN model is all about increasing the accuracy while applying a transfer learning technique. This research was conducted with the help of Python and Jupyter Notebook. Here, deep feature extraction was achieved using deep CNN models that had been pre-trained. Our paper's achievements are evaluated using three metrics: Classification Accuracy, F1-Score, and Validation Accuracy. CNN was used to create the models, with a test accuracy of 98.4% and an Fl-score of 98.5%. This precision helps to detect the tumors at an early stage, before they can harm the physical body, such as stroke, paralysis, or other disa bilities.