Abstract
A locally weighted normalized mutual information (wNMI) metric is proposed to highlight spatial correspondences in an image pair. Aiming to account for local similarities, our proposal computes the normalized mutual information on local regions and linearly weights them depending on their information. Additionally, we introduce a criterion for tuning the number of regions based on the variability maximization of the metric values in a given dataset. To assess our proposal, we compare wNMI to means squares (MS), cross correlation (CC) and global normalized mutual information (NMI) to select the closest atlases on a multi-atlas segmentation scheme for labeling ganglia basal structures. Obtained results show that our proposed measure provides a more robust atlas selection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Rueckert, M., Clarkson, M,J., Hill D,L., Hawkes, D,J.: Non-rigid registration using higher-order mutual information. In: Proceedings of SPIE Medical Imaging, vol. 2, pp. 438–447 (2000)
Razlighi, Q.R., Kehtarnavaz, N., Yousefi, S.: Evaluating similarity measures for brain image registration. J. Vis. Commun. Image Represent. 24(7), 977–987 (2013)
Sundar, H., Shen, D., Biros, G., Xu, C., Davatzikos, C.: Robust computation of mutual information using spatially adaptive meshes. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part I. LNCS, vol. 4791, pp. 950–958. Springer, Heidelberg (2007)
Studholme, C., Drapaca, C., Iordanova, B., Cardenas, V.: Deformation-based mapping of volume change from serial brain mri in the presence of local tissue contrast change. IEEE Trans. Med. Imaging 25(5), 626–639 (2006)
Rivaz, H., Karimaghaloo, Z., Collins, D.L.: Self-similarity weighted mutual information: a new nonrigid image registration metric. Med. Image Anal. 18(2), 343–358 (2014)
Álvarez-Meza, A.M., Cárdenas-Peña, D., Castellanos-Dominguez, G.: Unsupervised kernel function building using maximization of information potential variability. In: Bayro-Corrochano, E., Hancock, E. (eds.) CIARP 2014. LNCS, vol. 8827, pp. 335–342. Springer, Heidelberg (2014)
Gousias, I.S., Rueckert, D., Heckemann, R., Dyet, L.E., Boardman, J.P., Edwards, D., Hammers, A.: Automatic segmentation of brain mris of 2-year-olds into 83 regions of interest. NeuroImage 40(2), 672–684 (2008)
Acknowledgments
This work was supported by Programa Nacional de Formación de Investigadores “Generación del Bicentenario”, 2011/2012, the research project 111056934461, both funded by COLCIENCIAS, and the research project 22506 founded by Dirección de Investigación Sede Manizales (DIMA).
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
Orbes-Arteaga, M., Cárdenas-Peña, D., Álvarez, M.A., Orozco, A.A., Castellanos-Dominguez, G. (2015). Spatial-Dependent Similarity Metric Supporting Multi-atlas MRI Segmentation. In: Paredes, R., Cardoso, J., Pardo, X. (eds) Pattern Recognition and Image Analysis. IbPRIA 2015. Lecture Notes in Computer Science(), vol 9117. Springer, Cham. https://doi.org/10.1007/978-3-319-19390-8_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-19390-8_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19389-2
Online ISBN: 978-3-319-19390-8
eBook Packages: Computer ScienceComputer Science (R0)