Abstract
Medical image processing tools are playing an increasingly important role in assisting the clinicians in diagnosis, therapy planning and image-guided interventions. Accurate, robust and fast tracking of deformable anatomical objects, such as the heart, is a crucial task in medical image analysis. One of the main challenges is to maintain an anatomically consistent representation of target appearance that is robust enough to cope with inherent changes due to target movement, imaging device movement, varying imaging conditions, and is consistent with the domain expert clinical knowledge. To address these challenges, this chapter presents a probabilistic framework that relies on anatomically indexed component-based object models which integrate several sources of information to determine the temporal trajectory of the deformable target. Large annotated imaging databases are exploited to encode the domain knowledge in shape models and motion models and to learn discriminative image classifiers for the target appearance. The framework robustly fuses the prior information with traditional tracking approaches based on template matching and registration. We demonstrate various medical image analysis applications with focus on cardiology such as 2D auto left heart, catheter detection and tracking, 3D cardiac chambers surface tracking, and 4D complex cardiac structure tracking, in multiple modalities including Ultrasound (US), cardiac Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and X-ray fluoroscopy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Akgul Y, Kambhamettu C (2003) A coarse-to-fine deformable contour optimization framework. IEEE Trans Pattern Anal Mach Intell 25(2):174–186
Akhter I, Sheikh Y, Khan S, Kanade T (2008) Nonrigid structure from motion in trajectory space. In: Advances in neural information processing systems, pp 41–48
Black MJ, Jepson AD (1998) Eigentracking: robust matching and tracking of articulated objects using a view-based representation. Int J Comput Vis 26:63–84
Bookstein FL (1989) Principal warps: thin-plate splines and the decomposition of deformation. IEEE Trans Pattern Anal Mach Intell 11(6):567–585
Briassouli A, Ahuja N (2007) Extraction and analysis of multiple periodic motions in video sequences. IEEE Trans Pattern Anal Mach Intell 29(7):1244–1261
Comaniciu D (2003) Nonparametric information fusion for motion estimation. In: Proceedings of IEEE conference on computer vision and pattern recognition, Madison, Wisconsin, pp 59–66
Comaniciu D, Zhou X, Krishnan S (2004) Robust real-time tracking of myocardial border: an information fusion approach. IEEE Trans Med Imaging 23(7):849–860
Cootes T, Taylor C (2001) Statistical models of appearance for medical image analysis and computer vision. In Proceedings of SPIE medical imaging, pp 236–248
Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23(6):681–685
Craene MD, Camara O, Bijnens BH, Frangi AF (2009) Large diffeomorphic FFD registration for motion and strain quantification from 3D-US sequences. In: Functional imaging and modeling of the heart (2009), vol 5528. Springer, pp 437–446
Dryden IL, Mardia KV (1998) Statistical shape analysis. Wiley, New York
Duan Q, Parker KM, Lorsakul A, Angelini ED, Hyodo E, Homma S, Holmes JW, Laine AF (2009) Quantitative validation of optical flow based myocardial strain measures using sonomicrometry. In: Proceedings of IEEE international symposium on biomedical imaging, pp 454–457
Edwards GJ, Cootes TF, Taylor CJ (1998) Face recognition using active appearance models. In: European conference on computer vision, pp 581–595
Elen A, Choi HF, Loeckx D, Gao H, Claus P, Suetens P, Maes F, D’hooge J (2008) Three-dimensional cardiac strain estimation using spatio-temporal elastic registration of ultrasound images: a feasibility study. IEEE Trans Med Imaging 27(11):1580–1591
Georgescu B, Zhou XS, Comaniciu D, Rao B (2004) Real-time multi-model tracking of myocardium in echocardiography using robust information fusion. In: Proceedings of international conference on medical image computing and computer assisted intervention
Georgescu B, Zhou XS, Comaniciu D, Gupta A (2005) Database-guided segmentation of anatomical structures with complex appearance. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 429–436
Grau V, Becher H, Noble J (2007) Registration of multiview real-time 3-D echocardiographic sequences. IEEE Trans Med Imaging 26(9):11541165
Ionasec R, Voigt I, Georgescu B, Wang Y, Houle H, Fernando-Vega H, Navab N, Comaniciu D (2010) Patient-specific modeling and quantification of the aortic and mitral valves from 4-D cardiac CT and TEE. IEEE Trans Med Imaging 29(9):1636–1651
Jacob G, Noble J, Behrenbruch C, Kelion A, Banning A (2002) A shape-space-based approach to tracking myocardial borders and quantifying regional left-ventricular function applied in echocardiography. IEEE Trans Med Imaging 21(3):226–238
Jepson AD, Fleet DJ, El-Maraghi TF (2003) Robust online appearance models for visual tracking. IEEE Trans Pattern Anal Mach Intell 25:1296–1311
Little SH (2010) Quantifying mitral valve regurgitation: new solutions from the 3rd dimension. J Am Soc Echocardiogr 23(1):9–12
Lloyd-Jones D, Adams R, Carnethon M, Simone GD, Ferguson TB, Flegal K, Ford E, Furie K, Go A, Greenlund K, Haase N, Hailpern S, Ho M, Howard V, Kissela B, Kittner S, Lackland D, Lisabeth L, Marelli A, McDermott M, Meigs J, Mozaffarian D, Nichol G, ODonnell C, Roger V, Rosamond W, Sacco R, Sorlie P, Stafford R, Steinberger J, Thom T, Wasserthiel-Smoller S, Wong N, Wylie-Rosett J, Hong Y (2009) Heart disease and stroke statistics-2009 update: a report from the american heart association statistics committee and stroke statistics subcommittee. Circulation 119:3
Lu X, Wang Y, Georgescu B, Littman A, Comaniciu D (2011) Automatic delineation of left and right ventricles in cardiac MRI sequences using a joint ventricular model. In: Proceedings IEEE international symposium on biomedical, pp 250–258
Mikić I, Krucinski S, Thomas JD (1998) Segmentation and tracking in echocardiographic sequences: active contours guided by optical flow estimates. IEEE Trans Med Imaging 17(2):274–284
Naftel A, Khalid S (2006) Motion trajectory learning in the DFT-coefficient feature space. In : Proceedings of international conference on computer vision systems, p 47
Peters J, Ecabert O, Meyer C, Kneser R, Weese J (2010) Optimizing boundary detection via simulated search with applications to multi-modal heart segmentation. Med Image Anal 14(1):70–84
Shi J, Tomasi C (1994) Good features to track. In: IEEE conference on computer vision and pattern recognition, pp 593–600
Sidenbladh H, Black MJ, Fleet DJ (2000) Stochastic tracking of 3d human figures using 2D image motion. In: European conference on computer vision, vol 2, pp 702–718
Stauffer C, Grimson WEL (1999) Adaptive background mixture models for real-time tracking. In: IEEE conference on computer vision and pattern recognition, vol 2, pp 246–252
Sun H, Frangi A, Wang H, Sukno F, Tobon-Gomez C, Yushkevich P (2010) Automatic cardiac mri segmentation using a biventricular deformable medial model. In: Proceedings of international conference on medical image computing and computer assisted intervention
Tao H, Sawhney HS, Kumar R (2000) Dynamic layer representation with application to tracking. In: IEEE conference on computer vision and pattern recognition, vol 2, pp 134–141
Tenenbaum JB, de Silva V, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290(5500):2319–2323
Tu Z (2005) Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering. In: Proceedings of international conference on computer vision, part II, pp 1589–1596
Veronesi F, Corsi C, Sugeng L, Mor-Avi V, Caiani E, Weinert L, Lamberti C, Lang RM (2009) A study of functional anatomy of aortic-mitral valve coupling using 3D matrix transesophageal echocardiography. Circ Cardiovasc Imaging 2(1):24–31
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features. In: IEEE conference on computer vision and pattern recognition, pp 511–518
Wang L, Geng X, Leckie C, Kotagiri R (2008) Moving shape dynamics: a signal processing perspective. In: IEEE conference on computer vision and pattern recognition
Wang X, Chen T, Zhang S, Metaxas D, Axel L (2008) LV motion and strain computation from tMRI based on meshless deformable models. In: Proceedings of international conference on medical image computing and computer assisted intervention
Wang P, Chen T, Zhu Y, Zhang W, Zhou S, Comaniciu D (2009) Robust guidewire tracking in fluoroscopy. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 691–698
Wang Y, Georgescu B, Comaniciu D, Houle H (2010) Learning-based 3D myocardial motion flow estimation using high frame rate volumetric ultrasound data. In: Proceedings of IEEE international symposium on biomedical imaging, pp 1097–1100
Wang Y, Georgescu B, Houle H, Comaniciu D (2010) Volumetric myocardial mechanics from 3d+t ultrasound data with multi-model tracking. In: Statistical atlases and computational models of the heart: map** structure and function (STACOM) + a cardiac electrophysiological simulation, challenge (CESC’10), pp 184–193
Wang P, Zheng Y, John M, Comaniciu D (2012) Catheter tracking via online learning for dynamic motion compensation in transcatheter aortic valve implantation. In: Proceedings of international conference on medical image computing and computer assisted intervention
Wu W, Chen T, Barbu A, Wang P, Strobel N, Zhou S, Comaniciu D (2011) Learning-based hypothesis fusion for robust catheter tracking in 2D X-ray fluoroscopy. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 1097–1104
Yang L, Georgescu B, Zheng Y, Wang Y, Meer P, Comaniciu D (2011) Prediction based collaborative trackers (PCT): a robust and accurate approach toward 3D medical object tracking. IEEE Trans Med Imaging 30(11):1921–1932
Zelnik Manor L, Irani M (2004) Temporal factorization vs. spatial factorization. In: European conference on computer vision, part II, pp 434–445
Zhao T, Nevatia R (2002) 3D tracking of human locomotion: a tracking as recognition approach. In: International conference on pattern recognition, part I, pp 546–551
Zheng Y, Barbu A, Georgescu B, Scheuering M, Comaniciu D (2008) Four-chamber heart modeling and automatic segmentation for 3-D cardiac CT volumes using marginal space learning and steerable features. IEEE Trans Med Imaging 27(11):1668–1681
Zhuang X, Leung K, Rhode K, Razavi R, Hawkes DJ, Ourselin S (2010) A registration-based propagation framework for automatic whole heart segmentation of cardiac MRI. IEEE Trans Med Imaging 29(9):1612–1625
Acknowledgments
The authors would like to thank Dr. David Sahn and Dr. Muhammad Ashraf at OHSU for providing the volumetric ultrasound sequences and sonomicrometry data in the in vitro animal study, Dr. Alan Katz from St. Francis Hospital and Dr. Mani Vannan from OSU Medical Center for fruitful interactions and guidance, and SCR colleagues for helpful discussions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Wang, Y. et al. (2013). Learning-Based Detection and Tracking in Medical Imaging: A Probabilistic Approach. In: González Hidalgo, M., Mir Torres, A., Varona Gómez, J. (eds) Deformation Models. Lecture Notes in Computational Vision and Biomechanics, vol 7. Springer, Dordrecht. https://doi.org/10.1007/978-94-007-5446-1_9
Download citation
DOI: https://doi.org/10.1007/978-94-007-5446-1_9
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-007-5445-4
Online ISBN: 978-94-007-5446-1
eBook Packages: EngineeringEngineering (R0)