Brain Tumor Segmentation based on Rough Set Theory for MR Images with Cellular Automata Approach
D. Ramamurthy1, Mahesh P K2
1D.Ramamurthy, Assistant Professor, Department of Electronics & Communication Engineering, Navodaya Institute of Technology, Raichur (Karnataka), India.
2Mahesh P K, Professor & Head, Department of Electronics & Communication Engineering, Navodaya Institute of Technology, Raichur (Karnataka), India.
Manuscript received on 05 February 2019 | Revised Manuscript received on 13 February 2019 | Manuscript published on 28 February 2019 | PP: 495-499 | Volume-8 Issue-4, February 2019 | Retrieval Number: D2875028419/19©BEIESP
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 (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Prediction of brain tumour and analysis is very critical in medical image processing since the treatment is based on radio surgery. Classifying the enhanced and necrotic cells is very essential in clinical radio surgeries, where in a radio oncology expert predicts the tumors manually for contrast enhanced T1-MR images. Prediction best works with cellular automata (CA) iterative algorithm by deriving transition rules from the tumour properties with adaptive method. Rough set theory with attribute reduction algorithm is used for classifying the enhanced and necrotic cells. In this work a semi interactive prediction algorithm is used with CA and Rough set theory for incomplete data prediction in medical images. Semi interactive algorithms require less manual intervention with high computation speed.
Keyword: Brain Tumor Prediction, Rough Set Algorithm, Cellular Automata, Magnetic Resonance Imaging (MRI), Radio Surgery, Enhanced Cells, Necrotic Cells, Reduct.
Scope of the Article: Image Security