Abstract
Automated algorithms designed for comparison of medical images are generally dependent on a sufficiently large dataset and highly accurate registration as they implicitly assume that the comparison is being made across a set of images with locally matching structures. However, very often sample size is limited and registration methods are not perfect and may be prone to errors due to noise, artifacts, and complex variations of brain topology. In this paper, we propose a novel statistical group comparison algorithm, called block-based statistics (BBS), which reformulates the conventional comparison framework from a non-local means perspective in order to learn what the statistics would have been, given perfect correspondence. Through this formulation, BBS (1) explicitly considers image registration errors to reduce reliance on high-quality registrations, (2) increases the number of samples for statistical estimation by collapsing measurements from similar signal distributions, and (3) diminishes the need for large image sets. BBS is based on permutation test and hence no assumption, such as Gaussianity, is imposed on the distribution. Experimental results indicate that BBS yields markedly improved lesion detection accuracy especially with limited sample size, is more robust to sample imbalance, and converges faster to results expected for large sample size.
This work was supported in part by a UNC BRIC-Radiology start-up fund and NIH grants (EB006733, EB009634, AG041721, and MH100217).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ashburner, J., Friston, K.J.: Voxel-based morphometry - the methods. NeuroImage 11(6), 805–821 (2000)
Efron, B., Tibshirani, R.J.: An Introduction to the Bootstrap. Monographs on Statistics and Applied Probablilty. Chapman and Hall, Boca Raton (1994)
Buades, A., Coll, B., Morel, J.M.: A review of image denoising algorithms, with a new one. Multiscale Model. Simul. 4(2), 490–530 (2005)
Härdle, W., Müller, M.: Multivariate and semiparametric kernel regression. In: Schimek, M.G. (ed.) Smoothing and Regression: Approaches, Computation, and Application. Wiley, Hoboken (2000)
Yap, P.T., An, H., Chen, Y., Shen, D.: Uncertainty estimation in diffusion MRI using the non-local bootstrap. IEEE Trans. Med. Imaging 33(8), 1627–1640 (2014)
Härdle, W.: Applied Nonparametric Regression. Cambridge University Press, Cambridge (1992)
Manjón, J., Carbonell-Caballero, J., Lull, J., García-Martí, G., Martí-Bonmatí, L., Robles, M.: MRI denoising using non-local means. Med. Image Anal. 12(4), 514–523 (2008)
Silverman, B.: Density Estimation for Statistics and Data Analysis. Monographs on Statistics and Applied Probablilty. Chapman and Hall, London (1998)
Zhang, P., Niethammer, M., Shen, D., Yap, P.T.: Large deformation diffeomorphic registration of diffusion-weighted imaging data. Med. Image Anal. 18(8), 1290–1298 (2014)
Yap, P.T., Shen, D.: Spatial transformation of DWI data using non-negative sparse representation. IEEE Trans. Med. Imaging 31(11), 2035–2049 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chen, G. et al. (2015). Block-Based Statistics for Robust Non-parametric Morphometry. In: Wu, G., Coupé, P., Zhan, Y., Munsell, B., Rueckert, D. (eds) Patch-Based Techniques in Medical Imaging. Patch-MI 2015. Lecture Notes in Computer Science(), vol 9467. Springer, Cham. https://doi.org/10.1007/978-3-319-28194-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-28194-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-28193-3
Online ISBN: 978-3-319-28194-0
eBook Packages: Computer ScienceComputer Science (R0)