Adaptive Volumetric Detection of Lesions for Minimal-Preparation Dual-Energy CT Colonography

  • Janne J. Näppi
  • Se Hyung Kim
  • Hiroyuki Yoshida
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7601)


Dual-energy computed tomographic colonography (DE-CTC) provides detailed information about the chemical composition of colon that can be used to improve the accuracy of computer-aided detection (CAD). We investigated how to calculate a thick target region for volumetric detection of lesions in DE-CTC. After automated extraction of the region of colonic lumen, the target region is calculated by use of a distance-based scheme, where the image scale of the shape features that are used for the detection of lesion candidates is adapted to the thickness of the target region. False-positive (FP) detections are reduced by use of a random-forest classifier. The detection accuracy of the CAD scheme was evaluated at 5 thicknesses of the target region by use of a leave-one-patient-out evaluation with 23 clinical minimal-preparation DE-CTC cases including 27 lesions ≥6 mm in size. The results indicate that the optimal choice of thickness depends on the size and morphology of the target lesion. At optimal thickness, the per-patient sensitivity was 100% at 5 FP detections per patient on average, where the per-lesion sensitivity was 100% (94%) for lesions ≥10 mm (6 – 9 mm) in size. The results compare favorably with those of our previous approach.


Computer-aided detection dual energy polyp detection laxative-free non-cathartic virtual colonoscopy computed tomographic colonography 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Beebe, T., Johnson, C., Stoner, S., Anderson, K., Limburg, P.: Assessing attitudes toward laxative preparation in colorectal cancer screening and effects on future testing: potential receptivity to computed tomographic colonography. Mayo. Clinic. Proc. 82, 666–671 (2007)Google Scholar
  2. 2.
    Bielen, D., Kiss, G.: Computer-aided detection for CT colonography: update 2007. Abdom. Imaging 32, 571–581 (2007)CrossRefGoogle Scholar
  3. 3.
    Borgefors, G.: On digital distance transforms in three dimensions. Comput. Vis. Image Und. 64, 368–376 (1996)CrossRefGoogle Scholar
  4. 4.
    Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)zbMATHCrossRefGoogle Scholar
  5. 5.
    Johnson, C., Chen, M.H., Toleday, A., Heiken, J., Dachman, A., Kuo, M., et al.: Accuracy of CT colonography for detection of large adenomas and cancers. N. Engl. J. Med. 359, 1207–1217 (2008)CrossRefGoogle Scholar
  6. 6.
    Johnson, T., Krauss, B., Seldmair, M., Grasruck, M., et al.: Material differentiation by dual energy CT: initial experience. Eur. Radiol. 17, 1510–1517 (2006)CrossRefGoogle Scholar
  7. 7.
    Koenderink, J., Doorn, R.: Surface shape and curvature scales. Image and Vision Computing 10, 557–565 (1992)CrossRefGoogle Scholar
  8. 8.
    Lawrence, E., Pickhardt, P., Kim, D., Robbins, J.: Colorectal polyps: stand-alone performance of computer-aided detection in a large asymptomatic screening population. Radiology 256, 791–798 (2012)CrossRefGoogle Scholar
  9. 9.
    Lindeberg, T.: Scale-scape theory in computer vision. Kluwer Academic Publishers, Boston (1993)Google Scholar
  10. 10.
    Liu, J., Kabadi, S., Van Uitert, R., Petrick, N., Deriche, R., Summers, R.: Improved computer-aided detection of small polyps in CT colonography using interpolation for curvature estimation. Med. Phys. 38, 4276–4284 (2011)CrossRefGoogle Scholar
  11. 11.
    Lohmann, G.: Volumetric image analysis. John Wiley & Sons, New York (1998)zbMATHGoogle Scholar
  12. 12.
    Mang, T., Bogoni, L., Salganicoff, M., Wolf, M., Raykar, V., Macari, M., et al.: Computer-aided detection of colorectal polyps in CT colonography with and without fecal tagging: a stand-alone evaluation. Invest. Radiol. 47, 99–108 (2012)CrossRefGoogle Scholar
  13. 13.
    Näppi, J., Frimmel, H., Yoshida, H.: Virtual endoscopic visualization of the colon by shape-scale signatures. IEEE Trans. Inf. Technol. Biomed. 9, 120–131 (2005)CrossRefGoogle Scholar
  14. 14.
    Näppi, J., Kim, S., Yoshida, H.: Automated detection of colorectal lesions with dual-energy CT colonography. In: van Ginneken, B., Noval, C. (eds.) SPIE Medical Imaging 2012: Computed-Aided Diagnosis, vol. 8315, pp. 83150Y1–83150Y6 (2012)Google Scholar
  15. 15.
    Näppi, J., MacEneaney, P., Dachman, A., Yoshida, H.: Knowledge-guided automated segmentation of colon for computer-aided detection of polyps in CT colonography. J. Comput. Assist. Tomogr. 26, 493–504 (2002)CrossRefGoogle Scholar
  16. 16.
    Näppi, J., Yoshida, H.: Automated detection of polyps in CT colonography: evaluation of volumetric features for reduction of false positives. Acad. Radiol. 9, 386–397 (2002)CrossRefGoogle Scholar
  17. 17.
    Näppi, J., Yoshida, H.: Fully automated three-dimensional detection of polyps in fecal-tagging CT colonography. Acad. Radiol. 25, 287–300 (2007)CrossRefGoogle Scholar
  18. 18.
    Näppi, J., Yoshida, H.: Adaptive correction of the pseudo-enhancement of CT attenuation for fecal-tagging CT colonography. Med. Image Anal. 12, 413–426 (2008)CrossRefGoogle Scholar
  19. 19.
    Näppi, J., Kim, S., Yoshida, H.: Volumetric detection of colorectal lesions for noncathartic dual-energy computed tomographic colonography. In: 34th Annual International Conference of the IEEE Engineering in Medicine & Biology Society. IEEE Press, San Diego (in press, 2012)Google Scholar
  20. 20.
    Näppi, J., Nagata, K.: Sources of false positives in computer-assisted CT colonography. Abdom. Imaging 36, 153–164 (2011)CrossRefGoogle Scholar
  21. 21.
    Näppi, J.J., Regge, D., Yoshida, H.: Comparative Performance of Random Forest and Support Vector Machine Classifiers for Detection of Colorectal Lesions in CT Colonography. In: Yoshida, H., Sakas, G., Linguraru, M.G. (eds.) Abdominal Imaging 2011. LNCS, vol. 7029, pp. 27–34. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  22. 22.
    Näppi, J., Yoshida, H., Regge, D.: Accuracy of computer-aided detection in detecting flat lesions in CT colonography. Insights into Imaging 3(S1), S334 (2012)Google Scholar
  23. 23.
    Park, S., Choi, E., Lee, S., Woo, J., et al.: Linear polyp measurement at CT colonography: 3D endoluminal measurement with optimized surface-rendering threshold value and automated measurement. Radiology 246, 157–167 (2008)CrossRefGoogle Scholar
  24. 24.
    Winawer, S., Fletcher, R., Miller, L., Godlee, F., Stolar, M., Mulrow, C., Woolf, S., Glick, S., Ganiats, T., Bond, J., Rosen, L., Zapka, J., Olsen, S., Giardiello, F., Sisk, J., Van Antwerp, R., Brown-Davis, C., Marciniak, D., Mayer, R.: Colorectal cancer screening: clinical guidelines and rationale. Gastroenterology 112, 594–642 (1997)CrossRefGoogle Scholar
  25. 25.
    Yoshida, H., Näppi, J.: Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps. IEEE Trans. Med. Imaging 20, 1261–1274 (2001)CrossRefGoogle Scholar
  26. 26.
    Yoshida, H., Näppi, J.: CAD in CT colonography without and with oral contrast agents: progress and challenges. Comp. Med. Imag. Graph 31, 267–284 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Janne J. Näppi
    • 1
  • Se Hyung Kim
    • 2
  • Hiroyuki Yoshida
    • 1
  1. 1.3D Imaging Research, Department of RadiologyMassachusetts General Hospital and Harvard Medical SchoolBostonUSA
  2. 2.Seoul National University HospitalSeoulRepublic of Korea

Personalised recommendations