Abstract
In lung CT images, the edge of a tumor is frequently fuzzy because of the complex relationship between tumors and tissues, especially in cases that the tumor adheres to the chest and lung in the pathology area. This makes the tumor segmentation more difficult. In order to segment tumors in lung CT images accurately, a method based on support vector machine (SVM) and improved level set model is proposed. Firstly, the image is divided into several block units; then the texture, gray and shape features of each block are extracted to construct eigenvector and then the SVM classifier is trained to detect suspicious lung lesion areas; finally, the suspicious edge is extracted as the initial contour after optimizing lesion areas, and the complete tumor segmentation can be obtained by level set model modified with morphological gradient. Experimental results show that this method can efficiently and fast segment the tumors from complex lung CT images with higher accuracy.
Similar content being viewed by others
References
LARTIZIEN C, MARACHE F S and PROST R, IEEE Trans. Nucl. Sci 59, 102 (2012).
LIN Y and TIAN J, International Journal of Pattern Recognition and Artificial Intelligence 6, 192 (2002). (in Chinese)
DUNCAN J S and AVACHE N, IEEE Transactions on Medical Imaging 33, 85 (2000).
SHAN J, CHENG H D and Wang Y X, Proceedings of the 19th IEEE International Conference on Pattern Recognition, 1 (2008).
LI Xuchao, LIU Haikuan, WANG Fei and BAI Chunyan, Journal of Image and Graphics 17, 447 (2012). (in Chinese)
Liu G, Zhao Z and Zhang Y, IEEE Journals & Magazines 12, 1770 (2015).
CHANG C Y, HONG Y C, CHUNG P C and TSENG C H, IEEE Computational Intelligence Magazine 6, 43 (2011).
SHAN J, WANG Y X and Cheng H D, Proceedings of the 17th IEEE International Conference on Image Processing, 1713 (2010).
Jung T H, Choi S W and Ko K S, Electronics Letters, 2010.
LAN Hong and ZHANG Lu, Journal of Image and Graphics 17, 873 (2012). (in Chinese)
Sulaiman S N and Isa N A M, IEEE Transactions on Consumer Electronics 56, 2661 (2010).
FARROKHINA F and JAIN A K, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 364 (1991).
MOON P and SPENCER D E, Journal of the Optical Society of America 34, 234 (1944).
Liu X and Tang J, IEEE Systems Journal 8, 910 (2014).
Lin K P and Chen M S, IEEE Transactions on Knowledge & Data Engineering 23, 1704 (2010).
Liu Yugang and Yu Yizhou, IEEE Transactions on Visualization & Computer Graphics 18, 202 (2012).
Author information
Authors and Affiliations
Corresponding author
Additional information
This work has been supported by the National Natural Science Foundation of China (No.61261029) and Jinchuan Company Research Foundation (No.JCYY2013009).
Rights and permissions
About this article
Cite this article
Wang, Xp., Zhang, W. & Cui, Y. Tumor segmentation in lung CT images based on support vector machine and improved level set. Optoelectron. Lett. 11, 395–400 (2015). https://doi.org/10.1007/s11801-015-5148-1
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11801-015-5148-1