Performance Analysis of Supervised & Unsupervised Techniques for Brain Tumor Detection and Segmentation from MR Images Brijesha D. Rao and Mukesh M. Goswami Abstract Brain tumor detection and segmentation from the magnetic resonance images (MRI) is a dif ficult task as in the MR brain images, various tissues such as white matter, gray matter, and cerebrospinal fluid have complicated structures that make it dif ficult to segment the tumor. An automated system for brain tumor detection and segmentation will help the patients for proper treatment planning. Also, it will improve the diagnosis and reduce the diagnostic time. Segmentation of brain tumor MR images is the most dif ficult task as the tumor varies in terms of size, shape, location, and texture. In this paper, we discuss various supervised and unsupervised techniques for brain tumor detection and segmentation such as K-nearest neighbor (K-NN), K-means clustering, and using morphological opera- tors. We also review the results obtained. Keywords Brain tumor Á Magnetic resonance image (MRI) Á Feature extraction Supervised and unsupervised techniques 1 Introduction Brain tumor is the extra cells growing in the brain, which form a mass of tissue. Survey says that 7.6 million people die among 12.7 million cancerous people in a year [1]. Gliomas are the primary brain tumor which found more frequent in adults [2]. The survival rate for high-grade tumor is almost two years while several years for low-grade tumors. If the automated system for brain tumor detection and seg- mentation is available, then it may help to minimize the rate of diagnosis of brain tumor abnormality which helps the patients for proper treatment planning. B. D. Rao (&) Á M. M. Goswami Information Technology, Dharmsinh Desai University, Nadiad, India e-mail: brijesha_056102@yahoo.co.in M. M. Goswami e-mail: mukesh.goswami@gmail.com © Springer Nature Singapore Pte Ltd. 2018 R. Kher et al. (eds.), Proceedings of the International Conference on Intelligent Systems and Signal Processing, Advances in Intelligent Systems and Computing 671, https://doi.org/10.1007/978-981-10-6977-2_4 35