Deep Learning for Brain Tumor Classification from MRI Images
Shaveta Arora, Meghna Sharma
Abstract
Magnetic Resonance Imaging popularly known as MRI is one of the primary scans to visualize the brain tumor. The detailed pictures obtained from MRI when processed using deep learning methods help the neurologist in classifying brain tumor. The paper shows the exploratory analysis of brain MRI images based on extracted features and also a comparative analysis of different CNN based transfer learning models for the classification of MRI images for brain tumor. It shows the efficiency of deep learning techniques for the detection of brain cancer from the MRI images of the brain. The performance is measured in terms of training accuracy and test accuracy. Here binary classification is done with no tumor and with tumor classes. The goal of our study is to accurately detect tumors in the brain and classify it through the means of several techniques involving medical image processing, pattern analysis, and computer vision for enhancement, segmentation and classification of brain diagnosis.