Page 174 - Read Online
P. 174
Arora et al. Neuroimmunol Neuroinflammation 2018;5:26 Neuroimmunology and
DOI: 10.20517/2347-8659.2018.11 Neuroinflammation
Technical Note Open Access
Classification of brain tumor using devernay sub-
pixel edge detection and k-nearest neighbours
methodology
Ayush Arora, Ritesh Kumar, Shubham Tiwari, Mysore Shwetha, Selvam Venkatesan, Ramesh Babu
Department of Computer Science, Dayananda Sagar College of Engineering, Bengaluru, Karnataka 560078, India.
Correspondence to: Mr. Ayush Arora, Department of Computer Science, Dayananda Sagar College of Engineering, 95th Cross Road,
1st Stage, Kumaraswamy Layout, Bengaluru, Karnataka 560078, India. E-mail: aayusharora6896@gmail.com
How to cite this article: Arora A, Kumar R, Tiwari S, Shwetha M, Venkatesan S, Babu R. Classification of brain tumor using devernay
sub-pixel edge detection and k-nearest neighbours methodology. Neuroimmunol Neuroinflammation 2018;5:26.
http://dx.doi.org/10.20517/2347-8659.2018.11
Received: 26 Apr 2018 First Decision: 27 Apr 2018 Revised: 15 May 2018 Accepted: 22 May 2018 Published: 19 Jun 2018
Science Editor: Athanassios P. Kyritsis Copy Editor: Jun-Yao Li Production Editor: Huan-Liang Wu
Abstract
Any disease can be treated only once it is imaged, detected and classified. This paper proposes a set of algorithms for
classification of a brain tumor with better accuracy and efficiency. The proposal uses a JPEG format of the DICOM image
fed into three stages namely pre-processing, segmentation using sub-pixel edge detection method and using the nearest
neighbor methodology for the detection and differentiation of benign and malignant tumors.
Keywords: Brain tumor, magnetic resonance imaging, k-nearest neighbor, sub-pixel edge detection, contrast
enhancement, malignant, benign, classification, medical image processing
INTRODUCTION
The field of biomedical imaging is highly used in today’s life for detection of even the smallest possible
abnormality in the human body. The primary goal of medical imaging is to extract the meaningful and
accurate information according to the region of interest from the images with better accuracy and least
possible error output. The various types of imaging methods in the scope of biomedical imaging are
[1]
computerized tomography (CT) scans, X-rays and magnetic resonance imaging (MRI) scans .
CT-scans make use of computer-processed combinations of many X-ray measurements taken from different
angles to produce tomographic images of the region of interest of the scanned object, allowing the user to see
© The Author(s) 2018. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use,
sharing, adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as long
as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license,
and indicate if changes were made.
www.nnjournal.net