Tumor segmentation in lung CT images based on support vector machine and improved level set

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.

Keywords

Support Vector Machine / Support Vector Machine Classifier / Initial Contour / Tumor Segmentation / Tumor Contour

References

[1] LARTIZIENC., MARACHEF. S., PROSTR.. IEEE Trans. Nucl. Sci, 2012, 59: 102

[2] LINY., TIANJ.. International Journal of Pattern Recognition and Artificial Intelligence, 2002, 6: 192

[3] DUNCANJ. S., AVACHEN.. IEEE Transactions on Medical Imaging, 2000, 33: 85

[4] SHANJ., CHENGH. D., WangY. X.. Proceedings of the 19th IEEE International Conference on Pattern Recognition, 2008, 1

[5] LIX., LIUH., WANGF., BAIC.. Journal of Image and Graphics, 2012, 17: 447

[6] LiuG., ZhaoZ., ZhangY.. IEEE Journals & Magazines, 2015, 12: 1770

[7] CHANGC. Y., HONGY. C., CHUNGP. C., TSENGC. H.. IEEE Computational Intelligence Magazine, 2011, 6: 43

[8] SHANJ., WANGY. X., ChengH. D.. Proceedings of the 17th IEEE International Conference on Image Processing, 2010, 1713

[9] JungT. H., ChoiS. W., KoK. S.. Electronics Letters, 2010,

[10] LANH., ZHANGL.. Journal of Image and Graphics, 2012, 17: 873

[11] SulaimanS. N., IsaN. A. M.. IEEE Transactions on Consumer Electronics, 2010, 56: 2661

[12] FARROKHINAF., JAINA. K.. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1991, 364

[13] MOONP., SPENCERD. E.. Journal of the Optical Society of America, 1944, 34: 234

[14] LiuX., TangJ.. IEEE Systems Journal, 2014, 8: 910

[15] LinK. P., ChenM. S.. IEEE Transactions on Knowledge & Data Engineering, 2010, 23: 1704

[16] LiuY., YuY.. IEEE Transactions on Visualization & Computer Graphics, 2012, 18: 202