Cover page and Table of Contents: PDF (size: 670KB)
Full Text (PDF, 670KB), PP.52-61
Views: 0 Downloads: 0
K-Means, self-initialization, histogram, bounding box, MRI brain, MRI scans
This paper proposed a self-initialization process to K-Means method for automatic segmentation of human brain Magnetic Resonance Image (MRI) scans. K-Means clustering method is an iterative approach and the initialization process is usually done either manually or randomly. In this work, a method has been proposed to make use of the histogram of the gray scale MRI brain images to automatically initialize the K-means clustering algorithm. This is done by taking the number of main peaks as well as their values as number of clusters and their initial centroids respectively. This makes the algorithm faster by reducing the number of iterations in segmenting the MRI image. The proposed method is named as Histogram Based Self Initializing K-Means (HBSIKM) method. Experiments were done with the MRI brain volumes available from Internet Brain Segmentation Repository (IBSR). Similarity validation was done by Dice coefficient with the available gold standards from the IBSR website. The performance of the proposed method is compared with the traditional K-Means method. For the IBSR volumes, the proposed method yields 3 to 4 times faster results and higher dice value than traditional K-Means method.
Kalaiselvi T, Kalaichelvi N, Sriramakrishnan P, "Automatic Brain Tissues Segmentation based on Self Initializing K-Means Clustering Technique", International Journal of Intelligent Systems and Applications(IJISA), Vol.9, No.11, pp.52-61, 2017. DOI:10.5815/ijisa.2017.11.07
L. Zhong-Wei, N. Ming-Jiu, P. Zhen-Kuan, “Variation level set method for multiphase image classification”, International Journal of Image, Graphics and signal Processing, MECS, 5: 51-57, 2011.
R. Kandwal, A. Kumar, S. Bhargava, “Review: Existing Image Segmentation Techniques”, International Journal of Advances Research in Computer Science & Software Engineering, 4(4): 153-156, 2014.
Yevgeniy Bodyanskiy, Olena Vynokurova, Volodymyr Savvo, Tatiana Tverdokhlib and Pavlo Mulesa, Hybrid Clustering-Classification Neural Network in the Medical Diagnostics of the Reactive Arthritis, International Journal of Intelligent Systems and Applications, MECS, 8: 1-9, 2016
Rabiu O. Isah, Aliyu D. Usman and A. M. S. Tekanyi Medical Image Segmentation through Bat-Active Contour Algorithm, International Journal of Intelligent Systems and Applications, MECS, 1: 30-36, 2017
T. Kalaiselvi, K. Somasundaram, “Knowledge Based Self Initializing FCM Algorithms for Fast Segmentation of Brain Tissues in Magnetic Resonance Image”, International Journal of Computer Applications, 90(14):19-26, 2014.
T. Kalaiselvi, “Brain Portion Extraction and Brain Abnormality Detection from Magnetic Resonance Imaging of Human Head Scans”, Pallavi Publications, India, 2011.
A. R. Malali, J. Light, T. Kalaiselvi, X. Li, “Fall Pattern Classification from Brain Signals using Machine Learning Models”, Journal of Selected Area in Telecommunications (JSAT), 3(10):1-5, 2015.
A. Anamika, “Study of Techniques used for Medical Image Segmentation and computation of Statistical test for region Classification of brain MRI”, I.J. Information Technology and Computer Science, MECS, 5: 44-53, 2013.
L. Kaufman, P. J. Rousseeuw, “Finding Groups in Data, An Introduction to Cluster Analysis”, John Wiley & Sons, Inc., Canada, 1990.
J. M. Pena, J. A Lozano, P. Larranaga, “An Empirical Comparisoin of Four Initialization Methods for the K-Means Algorithm”, Pattern Recognition Letters, 20(10), 1027-1040, 1999.
B. B. Bhusare, S.M. Bansode, “Centroids Initialization for K-Means Clustering using Improved Pillar Algorithm”, International Journal of Advanced Research in Computer Engineering & Technology, 3(4): 1317-1322, 2014.
M. Tian, Q. Yang, A. Maier, I. Schasiepen, N. Maass, M. Elter, “An Automatic Histogram-Based Initializing Algorithm for K-means Clustering in CT”, Bildverabeitung fur die medizin, Informatic Aktuell, Springer- Verlag Berlin Heidelberg, 2013.
A. Mohamed, A. Wesam, “Efficient Data Clustering Algorithms: Improvements over K-means”, I.J. Intelligent Systems and Applications, MECS, 3: 37-49, 2013.
T Raed. Aldahdooh, “DIMK-means ‘Distance based initialization method for K-means clustering algorithm’”, I.J. Intelligent Systems and Applications, MECS, 2: 41-51, 2013.
K. Somasundaram, S. Vijayalakshmi, T. Kalaiselvi, “Segmentation of Brain portion from MRI of head scans using K-means Cluster”, International Journal of Computational Intelligence and Informatics, 1:75-79, 2011.