King Saud University Repository >
King Saud University >
Science Colleges >
College of Computer and Information Sciences >
College of Computer and Information Sciences >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/15057

Title: Fuzzy entropy based optimization of clusters for the segmentation of lungs in CT scanned images
Authors: Ayyaz Hussain
Anwar Majid Mirza
Keywords: Computer aided diagnosis - Mathematical morphology - Segmentation - Thresholding
Issue Date: 2010
Publisher: Springer
Abstract: In this paper, we have proposed a method for segmentation of lungs from Computed Tomography (CT)-scanned images using spatial Fuzzy C-Mean and morphological techniques known as Fuzzy Entropy and Morphology based Segmentation. To determine dynamic and adaptive optimal threshold, we have incorporated Fuzzy Entropy. We have proposed a novel histogram-based background removal operator. The proposed system is capable to perform fully automatic segmentation of CT Scan Lung images, based solely on information contained by the image itself. We have used different cluster validity functions to find out optimal number of clusters. The proposed system can be used as a basic building block for Computer-Aided Diagnosis. The technique was tested against the 25 datasets of different patients received from Aga Khan Medical University, Pakistan. The results confirm the validity of technique as well as enhanced performance
URI: http://hdl.handle.net/123456789/15057
Appears in Collections:College of Computer and Information Sciences

Files in This Item:

File Description SizeFormat
Journal3.docx12.17 kBMicrosoft Word XMLView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


DSpace Software Copyright © 2002-2009 MIT and Hewlett-Packard - Feedback