Table of Contents Author Guidelines Submit a Manuscript
BioMed Research International
Volume 2016, Article ID 1480423, 13 pages
http://dx.doi.org/10.1155/2016/1480423
Research Article

Many Is Better Than One: An Integration of Multiple Simple Strategies for Accurate Lung Segmentation in CT Images

1School of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China
2Xianyang Hospital, Yan’an University, Xianyang 712000, China
3First Affiliated Hospital of School of Medicine, Xian Jiaotong University, Xian 710061, China
4School of Information Science and Technology, Aichi Prefectural University, Nagakute, Aichi 480-1198, Japan
5Medical Imaging Research Center, Illinois Institute of Technology, Chicago, IL 60616-3793, USA

Received 28 April 2016; Accepted 19 July 2016

Academic Editor: Weidong Cai

Copyright © 2016 Zhenghao Shi et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Accurate lung segmentation is an essential step in developing a computer-aided lung disease diagnosis system. However, because of the high variability of computerized tomography (CT) images, it remains a difficult task to accurately segment lung tissue in CT slices using a simple strategy. Motived by the aforementioned, a novel CT lung segmentation method based on the integration of multiple strategies was proposed in this paper. Firstly, in order to avoid noise, the input CT slice was smoothed using the guided filter. Then, the smoothed slice was transformed into a binary image using an optimized threshold. Next, a region growing strategy was employed to extract thorax regions. Then, lung regions were segmented from the thorax regions using a seed-based random walk algorithm. The segmented lung contour was then smoothed and corrected with a curvature-based correction method on each axis slice. Finally, with the lung masks, the lung region was automatically segmented from a CT slice. The proposed method was validated on a CT database consisting of 23 scans, including a number of 883 2D slices (the number of slices per scan is 38 slices), by comparing it to the commonly used lung segmentation method. Experimental results show that the proposed method accurately segmented lung regions in CT slices.