Abstract
We present an algorithm for passing from dense noisy neuroanatomical segmentations, directly to a complexity-reduced representation with respect to a deformed smooth template surface, bypassing the need for triangulation of any target data. We demonstrate the utility of this algorithm toward improving reproducibility of hippocampal definitions, using a dataset containing 4 MR images per subject, two within the same visit on each of two dates, with dense segmentations provided by unedited longitudinal Freesurfer analysis. We quantify reproducibility of intra-visit and inter-visit variability through L2 distances and Hausdorff distances between pairs of segmentations, and show that our method results in a statistically significant improvement by a factor of 1.63 to more than 3-fold.
This is a preview of subscription content, log in via an institution to check access.
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
Reuter, M., Schmansky, N.J., Rosas, H.D., Fischl, B.: Within-Subject Template Estimation for Unbiased Longitudinal Image Analysis. Neuroimage 61(4), 1402–1418 (2012)
Csernansky, J.G., et al.: Preclinical detection of Alzheimer’s disease: hippocampal shape and volume predict dementia onset in the elderly. NeuroImage 25(3), 783–792 (2005)
Gau, Y., Riklin-Raviv, T., Bouix, S.: Shape Analysis, A Field in Need of Careful Validation. Hum. Brain Mapp. (in press, 2014), doi:10.1002/hbm.22525
Beg, M.F., Miller, M.I., Trouvé, A., Younes, L.: Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms. Int. J. Comput. Vision 61(2), 139–157 (2005)
Wang, L., et al.: Large Deformation Diffeomorphism and Momentum Based Hippocampal Shape Discrimination in Dementia of the Alzheimer type. IEEE Trans. Med. Imaging 26(4), 462–470 (2007)
Singh, N., Wang, A.Y., Sankaranarayanan, P., Fletcher, P.T., Joshi, S.: Genetic, Structural and Functional Imaging Biomarkers for Early Detection of Conversion from MCI to AD. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part I. LNCS, vol. 7510, pp. 132–140. Springer, Heidelberg (2012)
Tang, X., et al.: Detecting, quantifying, and predicting. Hum. Brain Mapp. (2014), doi: 10.1002/hbm.22431
Ma, J., Miller, M.I., Younes, L.: A bayesian generative model for surface template estimation. Int. J. Biomedical Imaging 2010, ID 974957, 14 pages (2010)
Miller, M.I., Trouvé, A.: Geodesic Shooting for Computational Anatomy. Journal of Mathematical imaging and Vision 24(2), 209–228 (2006)
Vailard, F.-X., Risser, L., Rueckert, D., Cotter, C.J.: Diffeomorphic 3D Image Registration via Geodesic Shooting Using an Efficient Adjoint Calculation. Int. J. Comput. Vision 97(2), 229–241 (2011)
Durrleman, S., Allassonnière, S., Joshi, S.: Sparse adaptive parameterization of variability in image ensembles. Int. J. Comput. Vision 101(1), 161–183 (2013)
Staniforth, A., Côté, J.: Semi-Lagrangian integration schemes for atmospheric models—a review. Mon. Wea. Rev. 119(9), 2206–2223 (1991)
Jovicich, J., et al.: Brain morphometry reproducibility in multi-center 3 T MRI studies: A comparison of cross-sectional and longitudinal segmentations. Neuroimage 83, 472–484 (2013)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Tward, D. et al. (2014). Improved Reproducibility of Neuroanatomical Definitions through Diffeomorphometry and Complexity Reduction. In: Wu, G., Zhang, D., Zhou, L. (eds) Machine Learning in Medical Imaging. MLMI 2014. Lecture Notes in Computer Science, vol 8679. Springer, Cham. https://doi.org/10.1007/978-3-319-10581-9_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-10581-9_28
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10580-2
Online ISBN: 978-3-319-10581-9
eBook Packages: Computer ScienceComputer Science (R0)