Algorithm for Brain Tumor Detection
K.Govinda, Dhruv Tiwari1, Sachin Mathur2, Somula Ramasubbareddy3

1K.Govinda, Associate Professor, School of Computer Engineering,VIT-Vellore India.

2Dhruv Tiwari, Computer Science and Engineering (Bioinformatics), VIT-Vellore Sachin Mathur, Computer Science and Engineering (Bioinformatics), VIT-Vellore, India.

3Somula Ramasubbareddy, Assistant Professor, Information Technology, VNRVJIET, Hyderabad, Telangana, India.

Manuscript received on 15 September 2019 | Revised Manuscript received on 23 September 2019 | Manuscript Published on 11 October 2019 | PP: 1035-1042 | Volume-8 Issue-11S September 2019 | Retrieval Number: K121309811S19/2019©BEIESP | DOI: 10.35940/ijitee.K1213.09811S19

Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (

Abstract: In today’s world many engineers have been concentrating in developing various tools for detection of tumor and processing its medical images. The extraction of brain tumor and analysing it is a very challenging task in the field of healthcare. Segmentation’s introduction solves the complexity to medical imaging and in turn “MRI (magnetic resonance imaging)” proves to bea very useful diagnostic tool for the detection of brain tumorin MRI’s. Here we have performed a comparative study between various clustering and segmentation algorithms. In healthcare field, detection of brain tumor from MRI of the brain, is the current most favourable and seeded area of research. Detecting tumors is one of the major focus areas of the system, it plays a critical role in extraction of details from graphic generated contents of the healthcare. MRI’s with brain scans are used in the processes. We have implemented “k-means, fuzzy-c means and watershed segmentation”with various soft computing image processing techniques in various test case scenarios which allows us to compare and contrast between the stated techniques. This paper also focuses on enhancing the performance of the algorithms by setting up a suitable parallel environment for these three tumor detection techniques. This will allow multiple MRI’s being evaluated simultaneously.

Keywords: Algorithm, MRI (Magnetic Resonance Imaging), Image Processing Techniques,
Scope of the Article:  Algorithm Engineering