Detection and Classification of Brain Tumor in MRI Images using Deep Convolutional Network

Brain tumor is a serious disease occurring in human being. Medical treatment process mainly depends on tumor types and its location. The final decision of neuro-specialists and radiologist for the tumor diagnosis mainly depend on evaluation of MRI (Magnetic Resonance Imaging) Images. The manual evaluation process is time-consuming and needs domain expertise to avoid human errors. To overcome this issue, Faster R-CNN deep learning algorithm was proposed for detecting the tumor and marking the area of their occurrence with Region Proposal Network (RPN). The selected MR image dataset consists of three primary brain tumors namely glioma, meningioma and pituitary. The proposed algorithm uses VGG-16 architecture as a base layer for both the region proposal network and the classifier network. Detection and classification results of the algorithm demonstrate that it is able to achieve an average precision of 75.18% for glioma, 89.45% for meningioma and 68.18% for pituitary tumor. As a performance measure, the algorithm achieved a mean average precision of 77.60% for all the classes.

I. Introduction

The abnormal growth of cells in human brain is called as brain tumor. A tumor which occurs in the brain or spinal cord is called as glioma and the tumor that arises from the meninges is called as meningioma. The abnormal cell growth in the pituitary gland is observed as pituitary tumor. The T1-weighted contrast enhanced Magnetic Resonance (MR) images can be used for the detection and localization of brain tumor. Based on color contrast differences, it is also able to differentiate brain tissues, edema and cerebrospinal fluid [1]. The early brain tumor detection is very much needed for effective treatment. For medical image diagnosis, the images can be obtained from various imaging modalities namely Positron Emission Tomography (PET), Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). Among all these modalities, MRI is found to be best for brain tumor diagnosis. MRI is harmless because it is based on magnetic field and radio waves and do not pose any radiation hazard to human body [2].