TRUS Image Segmentation Driven by Narrow Band Contrast Pattern Using Shape Space Embedded Level Sets

详细信息    查看全文

• 作者：Pengfei Wu (19)
  Yiguang Liu (19)
  Yongzhong Li (20)
  Liping Cao (21)
  
• 关键词：Prostate segmentation ; transrectal ultrasound images ; active contours ; level sets ; shape prior ; narrow band contrast pattern
• 刊名：Lecture Notes in Computer Science
• 出版年：2013
• 出版时间：2013
• 年：2013
• 卷：7751
• 期：1
• 页码：347-355
• 全文大小：2199KB
• 参考文献：1. American Cancer Society: The prostate cancer quandary (2011), http://www.cancer.org/
  2. Shen, D., Lao, Z., Zeng, J., Zhang, W., Sesterhenn, I.A., Sun, L., Moul, J.W., Herskovits, E.H., Fichtinger, G., Davatzikos, C.: Optimized prostate biopsy via a statistical atlas of cancer spatial distribution. Med. Image Anal.?8(2), 139-50 (2004) CrossRef
  3. Terris, M., Stamey, T.: Determination of prostate volume by transrectal ultrasound. J. Urol.?145(5), 984 (1991)
  4. Noble, J.A., Boukerroui, D.: Ultrasound image segmentation: a survey. IEEE Trans. Med. Imag.?25(8), 987-010 (2006) CrossRef
  5. Ghose, S., Oliver, A., Martí, R., Lladó, X., Freixenet, J., Villanova, J., Meriaudeau, F.: Prostate segmentation with local binary patterns guided active appearance models. Medical Imaging: Image Processing, France (2011)
  6. Yan, P., Xu, S., Turkbey, B., Kruecker, J.: Discrete deformable model guided by partial active shape model for trus image segmentation. IEEE Trans. Biomed. Eng.?57(5), 1158-166 (2010) CrossRef
  7. Zhan, Y.Q., Shen, D.G.: Deformable segmentation of 3-d ultrasound prostate images using statistical texture matching method. IEEE Trans. Med. Imag.?25(3), 256-72 (2006) CrossRef
  8. Tsai, A., Yezzi Jr., A., Wells, W., Tempany, C., Tucker, D., Fan, A., Grimson, W.E., Willsky, A.: A shape-based approach to the segmentation of medical imagery using level sets. IEEE Trans. Med. Imag.?22(2), 137-54 (2003) CrossRef
  9. Shen, D.G., Zhan, Y.Q., Davatzikos, C.: Segmentation of prostate boundaries from ultrasound images using statistical shape model. IEEE Trans. Med. Imag.?22(4), 539-51 (2003) CrossRef
  10. Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models-their training and application. Comput. Vis. Image Understanding?61(1), 38-9 (1995) CrossRef
  11. Chan, T., Vese, L.A.: An Active Contour Model without Edges. In: Nielsen, M., Johansen, P., Fogh Olsen, O., Weickert, J. (eds.) Scale-Space 1999. LNCS, vol.?1682, pp. 141-51. Springer, Heidelberg (1999) CrossRef
  12. Betrouni, N., Vermandel, M., Pasquier, D., Maouche, S., Rousseau, J.: Segmentation of abdominal ultrasound images of the prostate using a priori information and an adapted noise filter. Compt. Med. Imag. and Graph.?29, 43-1 (2005) CrossRef
  13. Cosío, F.A.: Automatic initialization of an active shape model of the prostate. Med. Image Anal.?12(4), 469-83 (2008) CrossRef
  14. Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. Int. J. Comput. Vis.?1(4), 321-31 (1988) CrossRef
  
• 作者单位：Pengfei Wu (19)
  Yiguang Liu (19)
  Yongzhong Li (20)
  Liping Cao (21)
  
  19. School of Computer Science, Sichuan University, Chengdu, China
  20. Ultrasound Department of West China Hospital, Sichuan University, Chengdu, China
  21. Library, Sichuan University, Chengdu, China
  
• ISSN：1611-3349

文摘

Prostate segmentation in transrectal ultrasound (TRUS) images is highly desired in many clinical applications. However, manual segmentation is difficult, time consuming and irreproducible. In this paper, we present a novel automatic approach using narrow band contrast pattern to segment prostates in TRUS images. Implicit representation of the segmenting level sets curve is firstly trained via principal component analysis, which also constraints the shape of prostate into a linear subspace. Then the model evolves to segment the prostate by maximizing the contrast in a narrow band near the segmenting curve. Many experimental results demonstrate the performance of the proposed algorithm, whose favorableness is validated by comparing to the state-of-the-art algorithms. Especially, the shape of prostate segmented by our algorithm is close to the one manually obtained by expert, and the mean absolute distance is only 1.07±0.77mm, which is quite promising.