Hybrid Segmentation and Features Extraction of Ischemic stroke on CT brain
|International Journal of Engineering Trends and Technology (IJETT)||
|© 2016 by IJETT Journal|
|Year of Publication : 2016|
|Authors : Ms. Pavithra S, Ms. Sivasankari S, Mr. Sunderlin Shibu. D
|DOI : 10.14445/22315381/IJETT-V42P221|
Ms. Pavithra S, Ms. Sivasankari S, Mr. Sunderlin Shibu. D " Hybrid Segmentation and Features Extraction of Ischemic stroke on CT brain", International Journal of Engineering Trends and Technology (IJETT), V42(3),96-101 December 2016. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group
Ischemic stroke is the blocking of blood clot in the artery which supply blood to the brain. Computed Tomography (CT) images are widely used to diagnose brain stroke. Segmentation is the process of segmenting ROI in an image. Feature extraction is a method of transforming large data into small amount of data. The traditional segmentation technique shows disadvantages like over segmentation in images. The main objective of this project is to eliminate over segmentation in brain stroke images by using Marker based water shed segmentation and the results are compared with k-means clustering technique and then performing features extraction. Initially the images are undergoing segmentation techniques and features extraction process. The primary segmentations are performed initially by using K-means clustering technique and then secondary segmentation are done by using Marker based water shed technique with the help of internal marker and external marker. The shape and statistical features were obtained from gray level co occurrence matrix method and histogram technique. By using features extraction technique can differentiate normality and abnormality in the brain. The abnormality of the brain is measured by calculating features such as statistical and shape by dividing the brain into two equal parts. Mathematical calculations and comparison of results with standard dataset values are performed in order to check whether the brain belongs to normal or abnormal condition.
 Atam, P. Dhawan, S.Loncaric, K. Hitt, J. Broderick, and T. Brott,“Image analysis and 3-d visualization of intracerebral brain hemorrhage,” in IEEE Symposium on Computer-Based Medical Systems, 1993, p. 140145.
 A. Usinskas, R. A. Dobrovolskis, and B. F. Tomandl, “Ischemic stroke segmentation on ct images using joint features,” Informatica., vol. 15, no. 2, 2004.
 A. Devi, S. P. Rajagopalan, "Brain Stroke Classification Based on Multi-Layer Perceptron Using Watershed Segmentation and Gabor Filter", Journal of Theoretical and Applied Information Technology, Vol. 56 No. 2, PP: 410-416, Oct 2013.
 Bryan S. Morse, Lecture 18: Segmentation (Region Based), Brigham Young University, 1998.  D. Cosic and S. Loncaric, “Computer system for quantitative analysis of ich from ct head images,” in 19th Annual International Conference of the IEEE, 1997.
 Dr. (Mrs.) G.Padmavathi, Dr. (Mrs.) P.Subashini and Mrs.A.Sumi “Empirical Evaluation of Suitable Segmentation Algorithms for IR Images”, IJCSI International Journal of Computer Science Issues, Vol. 7, Issue 4, No 2, July 2010.
 E. Hudyma and G. Terlikowski, “Computer-aided detection of early strokes and its evaluation on the base of ct images,” in International Multiconference on Computer Science and Information Technology, 2008, pp. 251–254.
 F. Zhu, "Brain Perfusion Imaging–Performance and Accuracy", Centre for Intelligent System and their Applications, School of Information, Uni-versity of Edinburgh, 2012.
 K. Sklinda, P. Bargiel, A. Przelaskowski, T. Bulski, J. Walecki, and P. Grieb, “Multiscale extraction of hypodensity in hyperacute stroke,” Med Sci Monit, 2007.
 J. Zhang, C.-H. Yan, C.-K. Chui, and S.-H. Ong, ”Fast segmentation of bone in CT images using 3D adaptive thresholding” Computers in Biology and Medicine, vol. 40, pp. 231-236, 2010.
Brain, Ischemic stroke, Segmentation, K-means clustering, Marker based water shed Transformation, Features extraction.