Abstract
Purpose
Quantitative assessment and essentially segmentation of liver and its tumours are of clinical importance in various procedures such as diagnosis, treatment planning, and monitoring. Moreover, segmentation of liver is the basis of further processing such as visualization, liver resection planning, and liver shape analysis. In this paper, we propose an algorithm to estimate an initial liver boundary.
Methods
The proposed method consists of four steps as follows: first, we compute statistical parameters of liver’s intensity range, associated with a large cross-section of liver CT image, utilizing expectation maximization (EM) algorithm. Second, by automatic extraction of ribs and segmentation of the heart, we define a ROI to confine the liver region for the next operations. Third, we propose a double thresholding approach to divide the liver intensity range into two overlapping ranges. In this case, based on a decision table, we label an object as a liver candidate or disregard it from the rest of the procedures. Finally, we employ an anatomical based rule to finalize a candidate as a liver tissue. In this case, we propose a color-map transformation scheme to convert the liver gray images into color images. In this way, we attempt to visually differentiate the liver from its surrounding tissues.
Results
We have evaluated the techniques in the presence of 14 randomly selected local datasets as well as all datasets from the MICCAI 2007 Grand Challenge workshop database. For the local datasets, the average overlap error and average volume difference were of values of 15.3 and 2.8%, respectively. In the case of the MICCAI datasets, the above values were estimated as 20.3 and −4.5%, respectively.
Conclusion
The results reveal that the proposed technique is feasible to perform consistent initial liver borders. The boundary might be then employed in an ‘Active Contour’ algorithm to finalize the liver mask.
Similar content being viewed by others
References
Meinzer HP, Thorn M, Cardenas CE (2002) Computerized planning of liver surgery: an overview. Comput Graph 26(4): 569–576
Reitinger B, Bornik A, Beichel R, Schmalstieg D (2006) Liver surgery planning using virtual reality. IEEE Comput Graph Appl 26(6): 36–47
Rusko L, Bekes G, Nemeth G, Fidrich M (2007) Fully automatic liver segmentation for contrast-enhanced CT images. In: Heimann T, Styner M, van Ginneken B (eds) Proceedings of MICCAI Workshop 3D segmentation in the clinic: a grand challenge
Kainmüller D, Lange T, Lamecker H (2007) Shape constrained automatic segmentation of the liver based on a heuristic intensity model. In: Heimann T, Styner M, van Ginneken B (eds) MICCAI workshop 3D segmentation in the clinic: a grand challenge
Lee J, Kim N, Lee H, Seo JB, Won HJ, Shin YM et al (2007) Efficient liver segmentation exploiting level-set speed images with 2.5D shape propagation. In: Heimann T, Styner M, van Ginneken B (eds) MICCAI workshop 3D segmentation in the clinic: a grand challenge
Evans A, Lambrou T, Linney A, Todd-Pokropek A (2004) Automatic segmentation of liver using a topology adaptive snake. In: Proceedings of BioMED2004, Austria
Lim SJ, Jeong YY, Ho YS (2006) Automatic liver segmentation for volume measurement in CT Images. J Vis Commun Image Represent 17(4): 860–875
Saitoh T, Tamura Y, Kaneko T (2004) Automatic segmentation of liver region based on extracted blood vessels. Syst Comput Jpn 35(5): 1–10
Gao L, Heath DG, Kuszyk BS, Fishman EK (1996) Automatic liver segmentation technique for three-dimensional visualization of CT data. Radiology 201(2): 359–364
Chen EL, Chung PC, Chen CL, Tsai HM, Chang CI (1998) An automatic diagnostic system for CT liver image classification. IEEE Trans Biomed Eng 45(6): 783–794
Masumoto J, Hori M, Sato Y, Murakami T, Johkoh T, Nakamura H et al (2003) Automated liver segmentation using multislice CT images. Syst Comput Jpn 34(9): 71–82
Susomboon R, Raicu DS, Furst J (2007) A hybrid approach for liver segmentation. In: Heimann T, Styner M, van Ginneken B (eds) MICCAI workshop 3D segmentation in the clinic: a grand challenge
Heimann T, Meinzer HP, Wolf I (2007) A statistical deformable model for the segmentation of liver CT volumes. In: Heimann T, Styner M, van Ginneken B (eds) MICCAI workshop 3D segmentation in the clinic: a grand challenge
Slagmolen P, Elen A, Seghers D, Loeckx D, Maes F, Haustermans K (2007) Atlas based liver segmentation using nonrigid registration with a B-spline transformation model. In: Heimann T, Styner M, van Ginneken B (eds) MICCAI workshop 3D segmentation in the clinic: a grand challenge
Wimmer A, Soza G, Hornegger J (2007) Two-stage semi-automatic organ segmentation framework using radial basis functions and level sets. In: Heimann T, Styner M, van Ginneken B (eds) Proceedings of MICCAI workshop 3D segmentation in the clinic: a grand challenge
Bishop CM (2006) Pattern recognition and machine learning. Springer, New York
Goshtasby AA (2005) 2-D and 3-D image registration. Wiley, New York
Foruzan AH, Zoroofi RA, Sato Y (2007) A hybrid technique for automatic liver segmentation of liver in CT images. In: Proceeding of CARS 2007. Berlin, pp s94–s96
Ginneken BV, Heimann T, Styner MA (2007) 3D segmentation in the clinic: a grand challenge. In: Workshop on 3D segmentation in the clinic, MICCAI 2007, pp 7–15
Foruzan AH, Zoroofi RA, Sato Y, Hori M, Murakami T, Nakamura H et al (2006) Automated segmentation of liver from 3D CT images. Int J Comput Assist Radiol Surg 1(1): 71–72
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Foruzan, A.H., Aghaeizadeh Zoroofi, R., Hori, M. et al. Liver segmentation by intensity analysis and anatomical information in multi-slice CT images. Int J CARS 4, 287–297 (2009). https://doi.org/10.1007/s11548-009-0293-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-009-0293-2