Journal of Medical Systems

, Volume 32, Issue 4, pp 259–268 | Cite as

Liver Isolation in Abdominal MRI

  • Rajasvaran Logeswaran
  • Tan Wooi Haw
  • Shakowat Zaman Sarker
Original Paper


This work presents a method for liver isolation in magnetic resonance imaging (MRI) abdomen images. It is based on a priori statistical information about the shape of the liver obtained from a training set using the segmentation approach. Morphological watershed algorithm is used as a key technique as it is a simple and intuitive method, producing a complete division of the image in separated regions even if the contrast is poor, and it is fast, with possibility for parallel implementation. To overcome the over-segmentation problem of the watershed process, image preprocessing and post-processing are applied. Morphological smoothing, Gaussian smoothing, intensity thresholding, gradient computation and gradient thresholding are proposed for preprocessing with morphological and graph based region adjacent list constructed for region merging. A new integrated region similarity function is also defined for region merging control. The proposed method produces good isolation of liver in axial MRI images of the abdomen, as is shown in this paper.


Morphological operations Region merging Watershed transform Abdominal axial MRI Object extraction 


  1. 1.
    Heiken, J. P., Wegman, P. J., and Lee, J. K. T., Detection of focal hepatic masses: Prospective evaluation with CT, delayed CT, CT during arterial portography, and MR imaging. Radiology 171:47–51, 1989.Google Scholar
  2. 2.
    Sung, J. L., Wang, T. H., and Yu, J. Y., Clinical study on primary carcinoma of the liver in Taiwan. Amer. J. Dig. Dis 12:101036–1049, 1967.CrossRefGoogle Scholar
  3. 3.
    Lim, S. J., Jeong, Y. Y., and ans Ho, Y. S., Automatic liver segmentation for volume measurement in CT Images. J. Vis. Commun. Image Represent 17:4860–875, 2006.CrossRefGoogle Scholar
  4. 4.
    Woodhouse, C. E., Ney, D. R., Sitzmann, J. V., and Fishman, E. K., Spiral computed tomography arterial portography with three-dimensional volumetric rendering for oncologic planning: A retrospective analysis. Invest. Radiol 29:1031–1037, 1994.CrossRefGoogle Scholar
  5. 5.
    Soyer, P., Roche, A., Gad, M., Shapeero, L., Breittmayer, F., Elias, D., Lasser, P., Rougier, P., and Levesque, M., Preoperative segmental localization of hepatic metastases: Utility of three-dimensional CT during arterial portography. Radiology 180:653–658, 1991.Google Scholar
  6. 6.
    Kuszyk, B. S., Ney, D. R., and Fishman, E. K., The current state of the art in 3D oncologic imaging: An overview. Int. J. Radiat. Oncol. Biol. Phys 33:1029–1039, 1995.Google Scholar
  7. 7.
    Bae, K. T., Giger, M. L., Chen, C. T., and Kahn, C. E., Automatic segmentation of liver structure in CT images. Med. Phys 20:71–78, 1993.CrossRefGoogle Scholar
  8. 8.
    Brummer, M. E., Mersereau, R. M., Eisner, R. L., and Lewine, R. R. J., Automatic detection of brain contour in MRI data sets. IEEE Trans. Med. Imag 12:153–166, 1993.CrossRefGoogle Scholar
  9. 9.
    Philip, K. P., Dove, E. L., McPherson, D. D., etal, Automatic detection of myocardial contours in cine-computed tomographic images. IEEE Trans. Med. Imag 13:241–253, 1994.CrossRefGoogle Scholar
  10. 10.
    Williams, D. M., Bland, P., Liu, L., Farjo, L., Francis, I. R., and Meyer, C. R., Liver-tumor boundary detection: Human observer vs. computer edge detection. Invest. Radiol 24:768–775, 1989.CrossRefGoogle Scholar
  11. 11.
    Campadelli, P., and Casiraghi, E., Liver segmentation from CT scans: A survey. Proc. LNCS 4578:520–528, 2007.Google Scholar
  12. 12.
    Rogovich, A., Nepa, P., Manara, G., and Monorchio, A., RF coils for MRI applications—A design procedure. IEEE Antennas Propagation Soc. Int. Symp. 1B:856–859, 2005.CrossRefGoogle Scholar
  13. 13.
    Nakamichi, K., Karungaru, S., Fukumi, M., and Akamatsu, N., Extraction of the liver tumor in CT images by Real-Coded Genetic Algorithm (RGA). In Proc. IASTED Intl. Conf. Comp. Intell. (CI 2006), pp. 366–371, 2006.Google Scholar
  14. 14.
    Campadelli, P., Casiraghi, E., and Lombardi, G., Automatic liver segmentation from abdominal CT scans. In Intl. Conf. Image Anal. Process, pp. 731–736, 2007.Google Scholar
  15. 15.
    Zhanga, X., Fujitab, H., Harab, T., Zhoub, X., Kanematsuc, M., Yokoyamac, R., Kondoc, H., and Hoshi, H., CAD on liver using CT and MRI. Proc. Intl. Conf. Med. Imag. Informatics (MIMI 2007), pp. 279–288, 2007.Google Scholar
  16. 16.
    Jack, C. R. Jr., Shiung, M. M., Gunter, J. L., O’Brien, P. C., Weigand, S. D., Knopman, D. S., Boeve, B. F., Ivnik, R. J., Smith, G. E., Cha, R. H., Tangalos, E. G., and Petersen, R. C., Comparison of different MRI brain atrophy rate measures with clinical disease progression in AD. Neurology 62:591–600, 2004.Google Scholar
  17. 17.
    Nemitz, O., Rumpf, M., Tasdizen, T., and Whitaker, R., Anisotropic curvature motion for structure enhancing smoothing of 3D MR angiography data. JMIV 27:3217–229, 2007.CrossRefMathSciNetGoogle Scholar
  18. 18.
    Shen, D. F., and Huang, M. T., A watershed-based image segmentation using JND property. IEEE Int. Conf. Acoust. Speech Signal Process Proc. 3:377–380, 2003.Google Scholar
  19. 19.
    Haris, K., and Efstratiadis, N., Hybrid image segmentation using watershed and fast region merging. IEEE Trans. Image. Proc 7:121684–169, 1998.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Rajasvaran Logeswaran
    • 1
    • 2
  • Tan Wooi Haw
    • 1
  • Shakowat Zaman Sarker
    • 1
  1. 1.Center for Image Processing and Telemedicine (CIPTEM), Faculty of EngineeringMultimedia UniversityCyberjayaMalaysia
  2. 2.Post-doctoral researcher, BK Digital Media DivisionSoongsil UniversitySeoulSouth Korea

Personalised recommendations