Abstract
Magnetic resonance cholangiopancreatography (MRCP) is the popular diagnostic imaging sequence for the diagnosis and surgery workup for the pancreatobiliary system and liver. The technique is relatively noisy and suffers from imaging characteristics such as the partial volume effect and varying acquisition orientation, making automatic analysis of the images difficult. This paper explores some of the popular image processing techniques with the goal of selecting suitable features in MRCP images, as a basis for preliminary computer-aided diagnosis systems in biliary structure image reconstruction and disease detection. Visual results and observations are given and analyzed. The findings support that many popular techniques such as texture analysis fail to highlight the structures of interest in MRCP images, whereas multi-scale, multi-resolution and dynamic thresholding achieve better success. The proposed multi-scale combination technique known as the Segment-Growing Hierarchical Model produced good visual results for detection of the bile ducts.










Similar content being viewed by others
References
Doi, K., MacMahon, H., Giger, M. L., and Hoffmann, K. R., In: Computer-aided diagnosis in medical imaging. Amsterdam: Elsevier, 1999.
Guibaud, L., Bret, P. M., Reinhold, C., Atri, M., and Barkun, A. N., Diagnosis of choledocholithiasis: Value of MR cholangiography. AJR. 163(4):847–850, 1994.
Bowen, R. Secretion of bile and the role of bile acids in digestion. http://arbl.cvmbs.colostate.edu/hbooks/pathphys/digestion/liver/bile.html, 2001.
Bister, M., Computer analysis of cardiac MR images. Ph.D. dissertation, Belgium: Vrije Universiteit Brussel, Brussels, 1990.
Cootes, T. F.,and Taylor, T. J., Active shape models—‘smart snakes’. In: Proc British Machine Vision Conf, pp 266–275, 1992.
Ginneken, B. V., Frangi, A. F., Staal, J. J., ter Haar Romeny, B. M., and Viegever, M. A., Active shape model segmentation with optimal features. IEEE Trans. Med. Img. 21(8):924–933, 2002.
Fanning, D. W. Active contouring (snakes) in IDL. http://www.dfanning.com/ip_tips/snakes.html, 2006.
Robinson, K. Efficient pre-segmentation filtering in MRCP. Ph.D. thesis. Ireland: Dublin City University, 2005.
NEMA, Digital imaging and communications in medicine (DICOM). National Electrical Manufacturers’ Association, Rosslyn, 1996. PS 3.1-1996-3.13-1996.
Candes, E., and Donoho, D., Ridgelets: the key to high dimensional intermittency. Philos. Trans. R. Soc. Lond. A357:2495–2509, 1999.
Do, M. N., and Vetterli, M., The contourlet transform: an efficient directional multiresolution image representation. IEEE Trans. Image. Process. 14(12):2091–2106, 2004.
ter Haar Romeny, B. M., Front-end vision and multi-scale image analysis. Holland: Kluwer, 2002.
Do, M. N., Contourlet Toolbox ver. 2.0. http://www.ifp.uiuc.edu/~minhdo/software, 2003.
Lo, P., Bister, M., and Eswaran, C., Watershed segmentation with gradient threshold and root merging for ultrasound images. In: Proc South-East Asian Congress of Med Phy (SEACOMP) & Asian-Oceania Congress of Med Phy (AOCMP), pp 251–256, 2004.
Logeswaran, R., Scale-space segment growing for hierarchical detection of biliary tree structure. Intl J Wavelets, Multiresolution and Info Process. 3(1):125–140, 2005.
Logeswaran R. Computer-aided detection, modelling and diagnostic techniques for biliary structure using MRCP. Ph.D. thesis. Malaysia: Multimedia University, 2006.
Logeswaran, R., A computer-aided multi-disease diagnostic system using MRCP. J Dig Img. 21:235–242, 2007. doi:10.1007/s10278-007-9029-4.
Acknowledgement
This work is supported by the Soongsil University Research Fund.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Logeswaran, R. Segment-growing Hierarchical Model for Bile Duct Detection in MRCP. J Med Syst 33, 423–433 (2009). https://doi.org/10.1007/s10916-008-9204-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10916-008-9204-2