Abstract
Contrast-enhanced ultrasound (CEUS) imaging has lately benefited of an increasing interest for diagnosis and intervention planning, as it allows to visualize blood flow in real-time harmlessly for the patient. It complements thus the anatomical information provided by conventional ultrasound (US). This chapter is dedicated to kidney segmentation methods in 3D CEUS images. First we present a generic and fast two-step approach to locate (via a robust ellipsoid estimation algorithm) and segment (using a template deformation framework) the kidney automatically. Then we show how user interactions can be integrated within the algorithm to guide or correct the segmentation in real-time. Finally, we develop a co-segmentation framework that generalizes the aforementioned method and allows the simultaneous use of multiple images (here the CEUS and the US images) to improve the segmentation result. The different approaches are evaluated on a clinical database of 64 volumes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Up to a constant multiplier.
- 2.
The ground truth may not exactly be reached because of the high intra-operator variability.
- 3.
For example, the seminal method of Chan and Vese [33] falls in this framework with f = H the Heaviside function and \(r_{I}({\bf x}) = {(I({\bf x}) - c_{\mathrm{ int}})}^{2} - {(I({\bf x}) - c_{\mathrm{ ext}})}^{2}\) with c int and c ext denoting mean intensities inside and outside the target object.
References
Albrecht T et al (2004) Guidelines for the use of contrast agents in ultrasound. Ultraschall Med 25(4):249–256
Noble JA, Boukerroui D (2006) Ultrasound image segmentation: a survey. IEEE Trans Med Imag 25(8):987–1010
Gasnier A, Ardon R, Ciofolo-Veit C, Leen E, Correas J (2010) Assessing tumour vascularity with 3D contrast-enhanced ultrasound: a new semi-automated segmentation framework. In: Proceedings of IEEE ISBI 2010, pp 300–303. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5490351
Kissi A, Cormier S, Pourcelot L, Bleuzen A, Tranquart E (2004) Contrast enhanced ultrasound image segmentation based on fuzzy competitive clustering and anisotropic diffusion. In: IEEE IEMBS 2004, vol 1, pp 1613–1615. http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=1403489
Prevost R, Cohen L, Correas J, Ardon R (2012) Automatic detection and segmentation of renal lesions in 3D contrast-enhanced ultrasound images. Proc. SPIE 8314:83141D–83141D1
Ma M, Stralen M, Reiber J, Bosch J, Lelieveldt B (2009) Left ventricle segmentation from contrast enhanced fast rotating ultrasound images using three dimensional active shape models. In: Proceedings of FIMH 2009, pp 295–302. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6235871
Prevost R, Mory B, Correas JM, Cohen LD, Ardon R (2012) Kidney detection and real-time segmentation in 3D contrast-enhanced ultrasound images. In: Proceedings of IEEE ISBI, pp 1559–62
Prevost R, Cuingnet R, Mory B, Correas JM, Cohen LD, Ardon R (2013) Joint co-segmentation and registration of 3D ultrasound images. In: To appear in Proceedings of IPMI, pp 268–279. Springer, Berlin, Heidelberg
Guil N, Zapata E (1997) Lower order circle and ellipse Hough transform. Pattern Recogn 30(10):1729–1744
McLaughlin RA (1998) Randomized Hough transform: improved ellipse detection with comparison. Pattern Recogn Lett 19(3):299–305
Wong C, Lin S, Ren T, Kwok N (2012) A survey on ellipse detection methods. In: 2012 I.E. international symposium on industrial electronics (ISIE), pp 1105–1110. IEEE, New York
Van Aelst S, Rousseeuw P (2009) Minimum volume ellipsoid. Wiley Interdisciplin Rev: Comput Statist 1(1):71–82
Saddi K, Chefd’Hotel C, Rousson M, Cheriet F (2007) Region-based segmentation via non-rigid template matching. In: Proceedings of ICCV, pp 1–7. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4409152
Somphone O, Mory B, Makram-Ebeid S, Cohen LD (2008) Prior-based piecewise-smooth segmentation by template competitive deformation using partitions of unity. In: Proceedings of ECCV, pp 628–641. http://link.springer.com/chapter/10.1007/978-3-540-88690-7_47
Mory B, Somphone O, Prevost R, Ardon R (2012) Real-time 3D image segmentation by user-constrained template deformation. In: Proceedings of MICCAI. LNCS, vol 7510, pp 561–568. Springer, Berlin
Cuingnet R, Prevost R, Lesage D, Cohen LD, Mory B, Ardon R (2012) Automatic detection and segmentation of kidneys in 3D CT images using random forests. In: Proceedings of MICCAI. LNCS, vol 7512, pp 66–74. Springer, Berlin
Yezzi A, Soatto S (2003) Deformotion: deforming motion, shape average and the joint registration and approximation of structures in images. IJCV 53(2):153–167
Schunck B, Horn B (1981) Determining optical flow. In: Image understanding workshop, pp 144–156. http://www.sciencedirect.com/science/article/pii/0004370281900242
Nocedal J, Wright SJ (1999) Numerical optimization. Springer, Berlin
Vicente S, Kolmogorov V, Rother C (2010) Cosegmentation revisited: models and optimization. In: Proceedings of ECCV, vol 6312, pp 465–479
Wang F, Vemuri B (2005) Simultaneous registration and segmentation of anatomical structures from brain MRI. In: Proceedings of MICCAI. LNCS, vol 3749, pp 17–25. Springer, Berlin
Pohl K, Fisher J, Grimson W, Kikinis R, Wells W (2006) A Bayesian model for joint segmentation and registration. NeuroImage 31(1):228–239
Lu C, Duncan J (2012) A coupled segmentation and registration framework for medical image analysis using robust point matching and active shape model. In: IEEE Workshop on MMBIA, pp 129–136
Wyatt P, Noble JA (2002) MAP MRF joint segmentation and registration. In: Proceedings of MICCAI. LNCS, vol 2488, pp 580–587. Springer, Berlin
Yezzi A, Zöllei L, Kapur T (2003) A variational framework for integrating segmentation and registration through active contours. MedIA 7(2):171–185
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Payet N, Todorovic S (2010) 2-Random forest random field. In: Proceedings of NIPS 2010
Montillo A, Shotton J, Winn J, Iglesias J, Metaxas D, Criminisi A (2011) Entangled decision forests and their application for semantic segmentation of CT images. In: Proceedings of IPMI. LNCS, vol 6801, pp 184–196. Springer, Berlin
Kontschieder P, Bulò S, Criminisi A, Kohli P, Pelillo M, Bischof H (2012) Context-sensitive decision forests for object detection. In: Proceedings of NIPS, pp 440–448
Glocker B, Pauly O, Konukoglu E, Criminisi A (2012) Joint classification-regression forests for spatially structured multi-object segmentation. In: Proceedings of ECCV. LNCS, vol 7575, pp 870–881. Springer, Berlin
Zikic D, Glocker B, Konukoglu E, Criminisi A, Demiralp C, Shotton J, Thomas O, Das T, Jena R, Price S (2012) Decision Forests for Tissue-specific Segmentation of High-grade Gliomas in Multi-channel MR. In: Proceedings of MICCAI. LNCS, vol 7512, pp 369–376. Springer, Berlin
Tu Z, Bai X (2010) Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE TPAMI 32(10):1744–1757
Chan T, Vese L (2001) Active contours without edges. IEEE TIP 10(2):266–277
Han D, Bayouth J, Song Q, Taurani A, Sonka M, Buatti J, Wu X (2011) Globally optimal tumor segmentation in PET-CT images: A graph-based co-segmentation method. In: Proceedings of IPMI, pp 245–256. http://link.springer.com/chapter/10.1007/978-3-642-22092-0_21
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: Choice of the Parameter μ for Ellipsoid Detection
Appendix: Choice of the Parameter μ for Ellipsoid Detection
The choice of μ in Eq. (3) is paramount as it controls the number of points that are taken into account for the ellipsoid matrix estimation. To find a suitable value, let us consider an ideal case of an image I 0 in which there is one white ellipsoid (I 0 = 1) on a black background (I 0 = 0), whose implicit function is \(\phi _{ {\bf c}_{0},{\bf M}_{0}}\). We also assume that the confidence weight is w ≡ 1 everywhere. Then the matrix estimated by our approach would be
Using the fact that \(I_{0} = \boldsymbol{ 1}_{\{1-{({\bf x}-{\bf c}_{0})}^{T}{\bf M}_{0}({\bf x}-{\bf c}_{0})\geq 0\}}\) is the indicator of the ellipsoid yields
After a variable substitution \({\bf x} \leftarrow {\bf M}_{0}^{1/2}({\bf x} -{\bf c}_{0})\), this expression becomes
With \(\text{Vol}({\bf M}_{0}) = \displaystyle\frac{4\pi } {3} \sqrt{\det ({\bf M} _{0 }^{-1 })} = \frac{4\pi } {3} \det ({\bf M}_{0}^{-1/2})\), we then obtain
Note that the integral \(\int _{\{\|{\bf x}\|\leq 1\}}{\bf x}{{\bf x}}^{T}d{\bf x}\) denotes the covariance matrix of a 3D unit ball, which is actually a scalar matrix that can be easily computed
Combining Eqs. (29) and (30) leads to
which yields the following relationship between M ∗ and M 0 :
This shows that the exact solution M 0 is retrieved for \(\mu = \frac{2} {5}\). This value actually depends on the dimension of Ω. Here we assumed \(\varOmega \subset \mathbb{R}^{3}\) but for 2D images, the optimal value would rather be \(\mu = \frac{1} {2}\).
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this chapter
Cite this chapter
Prevost, R., Mory, B., Cuingnet, R., Correas, JM., Cohen, L.D., Ardon, R. (2014). Kidney Detection and Segmentation in Contrast-Enhanced Ultrasound 3D Images. In: El-Baz, A., Saba, L., Suri, J. (eds) Abdomen and Thoracic Imaging. Springer, Boston, MA. https://doi.org/10.1007/978-1-4614-8498-1_2
Download citation
DOI: https://doi.org/10.1007/978-1-4614-8498-1_2
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4614-8497-4
Online ISBN: 978-1-4614-8498-1
eBook Packages: MedicineMedicine (R0)