© 2020, IJCSE All Rights Reserved 57 International Journal of Computer Sciences and Engineering Open Access Research Paper Vol.-8, Issue-1, Jan 2020 E-ISSN: 2347-2693 Study of Machine Learning vs Deep Learning Algorithms for Detection of Tumor in Human Brain Dheeraj D. 1* , Prasantha H.S. 2 1 Dept. of ISE, Global Academy of Technology, Bangalore, India 2 Dept. of ECE, Nitte Meenakshi Institute of Technology, Bangalore, India * Corresponding Author: dwarakanathdheeraj@gmail.com, Tel.: +91 9880166448 DOI: https://doi.org/10.26438/ijcse/v8i1.5763 | Available online at: www.ijcseonline.org Accepted: 12/Jan/2020, Published: 31/Jan/2020 Abstract— Modern medical imaging research faces the challenge of detecting brain tumor through Magnetic Resonance Images (MRI). Brain tumor is an abnormal mass of tissue in which some cells grow and multiply uncontrollably, apparently unregulated by the mechanisms that control normal cells. There are three types of tumor that are commonly observed viz. Benign, Pre-Malignant, and Malignant. Many supervised and unsupervised classification algorithms are used for detection of tumor as benign or malignant. Usually lighter datasets are used for image classification in application field where as comparatively larger and heavier datasets are used in case of medical field. Many parameters chosen during training play a very important role in measuring the performance and accuracy of the system. Thus an attempt has been made to clearly show how accuracy of the algorithm varies based on the parameters chosen for detection of brain tumor in human brain for an MRI image. Keywords— CNN, Transfer Learning, Medical Imaging, Glioma, Image Classification, Machine Learning, Deep Learning. I. INTRODUCTION Medical image processing is the most challenging and emerging field today. Today’s modern medical imaging research faces the challenge of detecting brain tumor through Magnetic Resonance Images (MRI). Normally, to produce images of soft tissue of human body, MRI images are used by experts. It is used for analysis of human organs to replace surgery [14]. The word tumor is a synonym for a word neoplasm which is formed by an abnormal growth of cells [7].Brain tumor is an abnormal mass of tissue[11] in which some cells grow and multiply uncontrollably, apparently unregulated by the mechanisms that control normal cells. The growth of a tumor takes up space within the skull and interferes with normal brain activity. So detection of the tumor is very important in earlier stages. Various techniques [7] were developed for detection of tumor in brain. There are three types of tumor that are commonly observed viz. Benign, Pre-Malignant, Malignant [8]. Glioma is a general term used to describe any tumor that arises from the supportive (―gluey‖) tissue of the brain. This tissue, called ―glia,‖ helps to keep the neurons in place and functioning well. There are three types of normal glial cells that can produce tumors. An astrocyte will produce astrocytomas (including glioblastomas), an oligodendrocyte will produce oligodendroglioma, and ependymomas come from ependymal cells. Tumors that display a mixture of these different cells are called mixed glioma. Glioma is also classified by the type of cells they affect. The types of Glioma are:  Astrocytoma — develop in the connective tissue cells, called astrocytes  Brainstem Glioma — develop in the brain stem  Ependymoma — develop from ependymal cells  Mixed Glioma — develop from more than one type of glial cell  Oligodendroglioma — develop in the supportive tissue cells of the brain, called oliogendroctyes  Optic nerve Glioma — develop in or around the optic nerve Image Classification is an important task within the field of computer vision. Image classification refers to the labeling of images into one of a number of predefined categories. Classification includes image sensors, image pre-processing, object detection, object segmentation, feature extraction and object classification. Image classification is an important and challenging task in various application domains, including biomedical imaging, biometry, video surveillance, vehicle