Brain Tumor Classification using Transfer Learning

Abstract

Brain tumors are one of the more severe medical conditions that can affect both children and adults. Brain tumors make up between 85 and 90 percent of all primary Central Nervous System (CNS) malignancies. Each year, brain tumors are found in about 11,700 persons. The 5-year survival rate is around 34% for males and 36% for female patients with malignant brain or CNS tumors. Brain tumors can be classified as benign, malignant, pituitary, and other forms. Appropriate treatment, meticulous planning, and exact diagnostics must be used to prolong patient lives. The most reliable way for detecting brain cancer is Magnetic Resonance Imaging (MRI). The images are examined by the radiologist. As brain tumors are complex the MRI serve as guide to diagnose the seriousness of the disease. Since the placement and size of the brain tumor seems incredibly abnormal for persons affected by the disease it becomes difficult to properly comprehend the nature of the tumor. For MRI analysis, a qualified neurosurgeon is also necessary. Compiling the results of an MRI can be extremely difficult and time-consuming because there are typically not enough qualified medical professionals and individuals who are knowledgeable about malignancy in poor countries. Thus, this issue can be resolved by an automated cloud-based solution. In the proposed model, The Convolutional Neural Networks (CNN) is used for the classification of the brain tumor dataset with an accuracy of 99%.