Journal of Medical Systems

, Volume 34, Issue 2, pp 101–105 | Cite as

Classification of the Colonic Polyps in CT-Colonography Using Region Covariance as Descriptor Features of Suspicious Regions

Original Paper


We present an algorithm to classify polyps in CT colonography images utilizing covariance matrices as object descriptors. Since these descriptors do not lie on a vector space, they cannot simply be fed to traditional machine learning tools such as support vector machines (SVMs) or artificial neural networks (ANNs). To benefit from the simple yet one of the most powerful nonparametric machine learning approach k-nearest neighbor classifier, it suffices to compute the pairwise distances among the covariance descriptors using a distance metric involving their generalized eigenvalues, which also follows from the Lie group structure of positive definite matrices. This approach is fast and discriminates polyps from non-polyps with high accuracy using only a small size descriptor, which consists of 36 unique features per image region extracted from the suspicious regions that we have obtained by combined cellular neural network (CNN) and template matching detection method. These suspicious regions are, in average, 15 × 17 = 255 pixels in our experiments.


CT colonography Colonic polyp detection Covariance descriptor 



This research is supported by Istanbul University, Research Fund. Project No: T-502.


  1. 1.
    Summers, R. M., Johnson, C., Pusanik, L. M., Malley, J. D., Youssef, A., and Reed, J., Automated polyp detector at CT colonography: feasibility assessment in a human population. Radiology. 219:51–59, 2001.Google Scholar
  2. 2.
    Banerjee, S., and Van Dam, J., CT colonography for colon cancer screening. Gastrointest. Endosc. 63:11210–1233, 2006. doi: 10.1016/j.gie.2005.07.021.CrossRefGoogle Scholar
  3. 3.
    Macari, M., Virtual colonoscopy: clinical results. Semin. Ultrasound CT. 22(5):432–442, 2001.Google Scholar
  4. 4.
    Gluecker, T. M., and Fletcher, J. G., CT colonography (virtual colonoscopy) for the detection of colorectal polyps and neoplasms: current status and future developments. Eur. J. Cancer. 38:162070–2078, 2002. doi: 10.1016/S0959-8049(02)00384-2.CrossRefGoogle Scholar
  5. 5.
    Buthiau, D., Rixe, O., Spano, J. P., Nizri, D., Delgado, M., Gutierrez, M. et al., New imaging techniques in oncology. EJC Suppl. 1:228–42, 2003. doi: 10.1016/S1359-6349(03)00012-0.CrossRefGoogle Scholar
  6. 6.
    Yao, J., Miller, M., Franaszek, M., and Summers, R. M., Colonic polyp segmentation in CT colonography-based on fuzzy clustering and deformable models. IEEE Trans. Med. Imaging. 23:1344–1352, 2004. doi: 10.1109/TMI.2004.826941.CrossRefGoogle Scholar
  7. 7.
    Yoshida, H., and Nappi, J., Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps. IEEE Trans. Med. Imaging. 20:1261–1274, 2001. doi: 10.1109/42.974921.CrossRefGoogle Scholar
  8. 8.
    Kilic, N., Ucan, O. N., and Osman, O., Automatic colon segmentation using cellular neural network for the detection of colorectal polyps. IU-JEEE. 7:419–423, 2007.Google Scholar
  9. 9.
    Miller, M. T., Jerebko, A. K., Malley, J. D., Franaszek, M., and Summers, R. M., Feature selection for computer aided detection using genetic algorithms. Proc. SPIE. 5031:102–110, 2003. doi: 10.1117/12.485796.CrossRefGoogle Scholar
  10. 10.
    Li, J., Franaszek, M., Petrick, N., Yao, J., Huang, A., Summers, R. M., Wavelet method for CT Colonography computer-aided polyp detection. Proc. IEEE International Symposium on Biomedical Imaging (ISBI): From Nano to Macro, pp:1316–1319, Arlington, VA, USA, 6–9 April 2006.Google Scholar
  11. 11.
    Chowdhury, T. A., Ghita, O., and Whelan, P. F., The use of 3D surface fitting for robust polyp detection and classification in CT colonography. Comput. Med. Imaging Graph. 30:427–436, 2006. doi: 10.1016/j.compmedimag.2006.06.004.CrossRefGoogle Scholar
  12. 12.
    Ertas, G., Gulcur, H. O., Tunacı, M., Osman, O., and Ucan, O. N., A preliminary study on computerized lesion localization in MR mammography using 3D NMITR maps, multilayer cellular neural networks and fuzzy C-partitioning. Med. Phys. 35:195, 2008. doi: 10.1118/1.2805477.CrossRefGoogle Scholar
  13. 13.
    Kilic, N., Ucan, O. N., Osman, O., Colonic polyp detection in CT colonography with fuzzy rule based 3D template matching. J. Med. Syst. 2008. doi: 10.1007/s10916-008-9159-3.
  14. 14.
    Porikli, F., and Kocak, T., Robust license plate detection using covariance descriptor in a neural network framework. Proc. AVSS. 06:107–112, 2006.Google Scholar
  15. 15.
    Forstner, W., Moonen, B., A metric for covariance matrices. Technical report, Dept. of Geodesy and Geoinformatics: Stuttgart University, 1999.Google Scholar
  16. 16.
    Tuzel, O., Porikli, F., and Meer, P., Region covariance: a fast descriptor for detection and classification, ECCV 2006. Part II LNCS. 3952:589–600, 2006.Google Scholar
  17. 17.
    Jerebko, A. K., Malley, J. D., Franaszek, M., and Summers, R. M., Support vector machines committee classification method for computer aided polyp detection in CT colonography. Acad. Radiol. 12:479–486, 2005. doi: 10.1016/j.acra.2004.04.024.CrossRefGoogle Scholar
  18. 18.
    Jerebko, A. K., Malley, J. D., Franaszek, M., Summers, R. M., Multi-network classification scheme for detection of colonic polyps in CT colonography data sets. Acad. Radiol. 10:154–160, 2003.Google Scholar
  19. 19.
    Tuzel, O., Porikli, F., Meer, P., Region covariance: a fast descriptor for detection and classification. In Proc. 9th European Conf. on Computer Vision, Leonardis A., Bischof H., Pinz A (eds.), vol. 2, Lecture Notes in Computer Science 3952, pp. 589–600, Berlin: Springer, 2006.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  1. 1.Electrical and Electronics Dept.Istanbul UniversityAvcilarTurkey
  2. 2.Computer Engineering Dept.Bahcesehir UniversityBesiktasTurkey

Personalised recommendations