Brain Tumor Detection and Classification Using Deep Learning

Abstract

Brain tumor is a collection, or mass, of abnormal cells in your brain. Brain tumors can be cancerous (malignant) or noncancerous (benign). Brain tumor is a very common and destructive malignant tumor disease that leads to a shorter life if it is not diagnosed early enough. Brain tumor classification is a very critical step after detection of the tumor to be able to attain an effective treatment plan. So, early detection not only helps to come up with better medications, it can also save a life in due time. In thisproject, the dataset is being used contains human brain MRI images. It contains both tumor and non-tumor MRI images of brain. Then it undergoes data pre-processing that applies various image processing techniques such as filtering, blurring, cropping etc. The dataset is divided into training and testing sets. They undergo data augmentation by a number of random transformations. The pre-trained dataset is fed to a CNN (Convolutional Neural Networks) model. Then the model detects whether the tumor is present or not. If the tumor is present, it is further classified into three categories. They are glioma tumor, meningioma tumor and pituitary tumor.