Abstract
Objective
The segmentation of ultrasound (US) images is useful for several applications in computer aided interventions including the registration of pre-operative CT or MRI to intra-operative US. Shadowing, intensity inhomogeneity and speckle are the common effects on US images. They render the segmentation algorithms developed for other modalities inappropriate due to poor robustness. We present a novel method for classification of hepatic structures including vasculature and liver parenchyma on US images.
Methods
The method considers B-mode US images as a dynamic texture. The dynamics of each pixel are modelled as an auto regressive (AR) process perturbed with Gaussian noise. The linear coefficients and noise variance are estimated pixel-wise using Neumaier and Schneider’s algorithm. Together with mean intensity they comprise a parametric space in which classification (maximum a posteriori or K-nearest neighbour) of each pixel is performed. We emphasize the novelty of studying dynamics rather than static features such as intensity in the segmentation of various structures.
Results
We assessed the automatic segmentations of ten US sequences using Dice Similarity Coefficients. The algorithm’s capability of vessel extraction was tested on three sequences where Doppler US failed to capture vasculature.
Conclusion
The modelling of image dynamics with AR process combined with MAP classifier produced robust segmentation results indicating that the method has a good potential for intra-operative use.
Similar content being viewed by others
References
Soler L, Delingette H, Malandain G, Montagnat J, Ayache N, Koehl C, Dourthe O, Malassagne B, Smith M, Mutter D and Marescaux J (2001). Fully automatic anatomical, pathological, and functional segmentation from CT scans for hepatic surgery. Comput Aided Surg 6(3): 131–142
Liu F, Zhao B and Kijewski PK (2005). Liver segmentation for CT images using GVF snake. Med Phys 32(12): 3699–3706
Duncan JS and Ayache N (2000). Medical image analysis: progress over two decades and the challenges ahead. IEEE Trans Pattern Anal Mach Intell 22(1): 85–106
Xie J, Jiang Y and Tsui H (2005). Segmentation of kidney from ultrasound images based on texture and shape priors. IEEE Trans Med Imaging 24(1): 45–57
Zhan Y and Shen D (2006). Deformable segmentation of 3-D ultrasound prostate images using statistical texture matching method. IEEE Trans Med Imaging 25(3): 256–272
Sahba F, Tizhoosh HR and Salama MM (2005). A coarse-to-fine approach to prostate boundary segmentation in ultrasound images. BioMed Eng Online 4(1): 58
Viola P and Wells WM (1997). Alignment by maximization of mutual information. Int J Comput Vis 24(2): 137–194
Wein W, Röper B and Navab N (2007). Integrating diagnostic B-mode ultrasonography into CT-based radiation treatment planning. IEEE Trans Med Imaging 26(6): 866–879
Blackall JM, Penney GP, King AP and Hawkes DJ (2005). Alignment of sparse freehand 3-D ultrasound with preoperative images of the liver using models of respiratory motion and deformation. IEEE Trans Med Imaging 24(11): 1405–1416
Kaspersen JH, Sjølie E, Wesche J, Åsland J, Lundbom J, Ødegård A, Lindseth F and Nagelhus Hernes TA (2003). Three-dimensional ultrasound-based navigation combined with preoperative CT during abdominal interventions: a feasibility study. Cardiovasc Intervent Radiol 26: 347–356
Lange Th, Eulenstein S, Hünerbein M, Lamecker H and Schlag PM (2004). Augmenting intraoperative 3D ultrasound with preoperative models for navigation in liver surgery. Lect Notes Comput Sci 3217: 534–541
Roche A, Pennec X, Malandain G and Ayache N (2001). Rigid registration of 3D ultrasound with MR images: a new approach combining intensity and gradient information. IEEE Trans Med Imaging 20(10): 1038–1049
Zhan Y and Shen D (2003). Automated segmentation of 3D US prostate images using statistical texture-based matching method. Lect Notes Comput Sci 2878: 688–696
Mellor M, Brady M (2005) Fluid registration of ultrasound using multi-scale phase estimates. In: Proceedings of BMVA’05
Dinstein I and Cohen B (2002). New maximum likelihood estimation schemes for noisy ultrasound images. Pattern Recognit 35: 455–463
Dutt V and Greenleaf JF (1994). Ultrasound echo envelope analysis using a homodyned k distribution signal model. Ultrason Imaging 16: 265–287
Bertrand M and Meunier J (1995). Ultrasonic texture motion analysis: theory and simulation. IEEE Trans Med Imaging 14(2): 293–300
Boukerroui D (2003). Velocity estimation in ultrasound images: a block matching approach. Lect Notes Comput Sci 2732: 586–598
Doretto G, Cremers D, Favaro P, Soatto S (2003) Dynamic texture segmentation. In: Proceedings of the 9th IEEE international conference on computer vision, vol 2, pp 1236–1242
Ghoreyshi A and Vidal R (2007). Segmenting dynamic textures with ising descriptors, ARX models and level sets. Lect Notes Comput Sci 4358: 127–141
Vidal R and Ravichandran A (2005). Optical flow estimation and segmentation of multiple moving dynamic textures. Comput Vis Pattern Recognit 2(20–25): 516–521
Fitzgibbon A (2001) Stochastic rigidity: image registration for nowhere-static scenes. In: Proceedings of IEEE international conference on computer vision, vol 1, pp 662–669
Ravichandran A, Vidal R, Halperin H (2006) Segmenting a beating heart using polysegment and Spatial GPCA. In: 3rd IEEE international symposium on biomedical imaging: nano to macro, pp 634–637
Doretto G (2005) Dynamic textures: modeling, learning, synthesis, animation, segmentation, and recognition. PhD thesis, University of California, Los Angeles, CA
Doretto G, Chiuso A, Wu YN and Soatto S (2003). Dynamic textures. Int J Comput Vis 51(2): 91–109
Schneider T and Neumaier A (2001). Algorithm. ARfit—a matlab package for the estimation of parameters and eigenmodes of multivariate autoregressive models. ACM Trans Math Softw 27: 58–65
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Milko, S., Samset, E. & Kadir, T. Segmentation of the liver in ultrasound: a dynamic texture approach. Int J CARS 3, 143–150 (2008). https://doi.org/10.1007/s11548-008-0217-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-008-0217-6