ABSTRACT
Brain tumour segmentation is a challenging task because of high diversity of the tumour for different patients and the ambiguity in its location. The high accuracy of extracting the tumour region from the normal brain solely depends on the seed selection. This prior knowledge of the seed points is also required for the initialisation of the graph cut segmentation. In this paper, two techniques (Centroid-Based Seed Selection [CBSS] and k-Mean Seed Selection [KMSS]) for the seed selection and segmentation of the tumour region using the graph-cut technique are proposed. The intensity distribution in the MRI brain images is utilised for the calculation of these points. In (CBSS), the symmetrical intensity distribution on both half of the brain is exploited. While in (KMSS) different groups of the similar intensity distribution are formed. The seed values obtained initialise the Graph-cut method to perform the segmentation. The performance parameters for the proposed methods are evaluated using MR brain images from standard and real time dataset. The mean Dice Sensitivity Coefficient (DSC) and mean Jaccard Index (JI) values are evaluated for indicating effectiveness and accuracy of the proposed work.
Acknowledgments
We would like to thank the radiologist department of the Government hospital, Shimla, Himachal Pradesh, India for providing the data set and their expert assistance for helping us in validating our results.
Disclosure statement
No potential conflict of interest was reported by the authors.
Additional information
Notes on contributors
Jyotsna Dogra
Jyotsna Dogra has received M.Tech degree in Electronics and communication engineering from Jaypee Institute of Information technology, Noida (U.P.) in 2013. She worked as Assistant Professor in the Department of Electronics and Communication Engineering in Abhlashi Group of Institutes, Mandi, India from Feb. 2014 to Jan. 2017. She is currently pursuing for her Ph.D. degree in Biomedical Image Processing. Her current research interest is Biomedical Image processing and neural network.
Shruti Jain
Dr. Shruti Jain is Associate Professor in the Department of Electronics and Communication Engineering at Jaypee University of Information Technology, Waknaghat, H.P, India and has received her Ph.D. in Biomedical Image Processing. She has a teaching experience of around 15 years. Her research interests are Soft Computing, Image and Signal Processing, Bio-inspired Computing and Computer-Aided Design of FPGA and VLSI circuits. She has published more than 10 book chapters, 60 papers in reputed journals, and 40 papers in International conferences. She has also published five books. She is a senior member of IEEE, life member and Editor in Chief of Biomedical Engineering Society of India and a member of IAENG. She has completed one externally funded project and one in the pipeline. She has guided 01 Ph.D. student and now has 06 registered students. She is a member of the Editorial Board of many reputed journals. She is also a reviewer of many journals and a member of TPC of different conferences. She was awarded by Nation Builder Award in 2018-19.
Meenakshi Sood
Dr. Meenakshi Sood is Associate Professor in National Institute of Technical Teachers Training & Research, Chandigarh, MHRD, GOI, India She is Gold medallist in her M.E (ECE) and holds a Ph.D. in Biomedical Signal Processing. Her research interests are in Bio-inspired Computing, Image and Signal Processing, Antenna design, Metamaterials and Soft Computing. She has published more than 50 papers in reputed journals and 60 papers in international conference proceedings. She is a senior member of the IEEE and life member of the Institute of Engineers, Biomedical Engineering Society of India, and a member of the IAENG. She has two externally funded projects and has another one in the pipeline. She has published two books for undergraduates.