Abstract
Sensorless freehand 3D ultrasound (US) exploits the correlation between pairs of images in order to track the rigid motion of the US probe without an external position sensor. Conventionally, in-plane motion is compensated by maximizing image correlation. Out-of-plane motion is then estimated using a calibrated model of elevational speckle decorrelation. This approach is prone to systematic error due to interactions between the effects of in-plane and out-of-plane motion components on speckle decorrelation. This paper proposes to establish an error correction model using relevance vector regression and a database of image pairs with known probe motion. Preliminary results on synthetic US image pairs show a statistically significant reduction in mean target registration error, illustrating the promise of the new approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bohs, L.N., Trahey, G.E.: A novel method for angle independent ultrasonic imaging of blood flow and tissue motion. IEEE T. Biomed. Eng. 38(3), 280–286 (1991)
Chen, J.-F., et al.: Determination of scan-plane motion using speckle decorrelation: theoretical considerations and initial test. Int. J. Imaging Syst. Technol. 8(1), 38–44 (1997)
Gee, A.H., et al.: Sensorless freehand 3D ultrasound in real tissue: speckle decorrelation without fully developped speckle. Med. Image Anal. 10(2), 137–149 (2006)
Guizar-Sicairos, M., et al.: Efficient subpixel image registration algorithms. Opt. Lett. 33(2), 156–158 (2008)
Housden, R.J., et al.: Sub-sample interpolation strategies for sensorless freehand 3D ultrasound. Ultrasound Med. Biol. 32(12), 1897–1904 (2006)
Housden, R.J., et al.: Sensorless reconstruction of unconstrained freehand 3D ultrasound data. Ultrasound Med. Biol. 33(3), 408–419 (2007)
Housden, R.J., et al.: Rotational motion in sensorless freehand three-dimensional ultrasound. Ultrasonics 48(5), 412–422 (2008)
Jensen, J.A.: Field: a program for simulating ultrasound systems. In: Proc. Nordic-Baltic Conf. Biomedical Imaging, vol. 4, pp. 351–353 (1996)
Kallel, F., et al.: Speckle motion artifact under tissue rotation. IEEE T. Ultrason. Ferr. 41(1), 105–122 (1994)
Lang, A., et al.: Fusion of electromagnetic tracking with speckle-tracked 3D freehand ultrasound using an unscented Kalman filter. In: Proc. SPIE Med. Imaging, vol. 7265, pp. 72651A–1–72651A–12 (2009)
Lang, A., et al.: Multi-modal registration of speckle-tracked freehand 3D ultrasound to CT in the lumbar spine. Med. Image Anal. 16, 675–686 (2012)
Laporte, C., Arbel, T.: Combinatorial and probabilistic fusion of noisy correlation measurements for untracked freehand 3D ultrasound. IEEE T. Med. Imaging 27(7), 984–994 (2008)
Laporte, C., Arbel, T.: Learning to estimate out-of-plane motion in ultrasound imagery of real tissue. Med. Image Anal. 15, 202–213 (2011)
Li, P.-C., et al.: Tissue motion and elevational speckle decorrelation in freehand 3D ultrasound. Ultrason. Imaging 24, 1–12 (2002)
Prager, R.W., et al.: Decompression and speckle detection for ultrasound images using the homodyned k-distribution. Patt. Recogn. Lett. 24, 705–713 (2003)
Prager, R.W., et al.: Sensorless freehand 3-D ultrasound using regression of the echo intensity. Ultrasound Med. Biol. 29(3), 437–446 (2003)
Prager, R.W., et al.: Three dimensional ultrasound imaging. P. I. Mech. Eng. H 24(2), 193–223 (2010)
Thayananthan, A., Navaratnam, R., Stenger, B., Torr, P., Cipolla, R.: Multivariate Relevance Vector Machines for Tracking. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 124–138. Springer, Heidelberg (2006)
Tipping, M.E.: Sparse Bayesian learning and the relevance vector machine. J. Machine Learning Research 1, 211–244 (2001)
Tuthill, T.A., et al.: Automated three-dimensional US frame positioning computed from elevational speckle decorrelation. Radiology 209(2), 575–582 (1998)
Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. IEEE T. Pattern Anal. 13(4), 376–380 (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Conrath, J., Laporte, C. (2012). Towards Improving the Accuracy of Sensorless Freehand 3D Ultrasound by Learning. In: Wang, F., Shen, D., Yan, P., Suzuki, K. (eds) Machine Learning in Medical Imaging. MLMI 2012. Lecture Notes in Computer Science, vol 7588. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35428-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-35428-1_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35427-4
Online ISBN: 978-3-642-35428-1
eBook Packages: Computer ScienceComputer Science (R0)