Joint clustering and component analysis of correspondenceless point sets: application to cardiac statistical modeling

Gooya, A. , Lekadir, K., Alba, X., Swift, A.J., Wild, J.M. and Frangi, A.F. (2015) Joint clustering and component analysis of correspondenceless point sets: application to cardiac statistical modeling. In: Ourselin, S., Alexander, D. C., Westin, C.-F. and Cardoso, M. J. (eds.) Information Processing in Medical Imaging: 24th International Conference, IPMI 2015, Sabhal Mor Ostaig, Isle of Skye, UK, June 28 - July 3, 2015, Proceedings. Series: Lecture notes in computer science (9123). Springer, pp. 98-109. ISBN 9783319199917 (doi: 10.1007/978-3-319-19992-4_8)

Abstract

Construction of Statistical Shape Models (SSMs) from arbitrary point sets is a challenging problem due to significant shape variation and lack of explicit point correspondence across the training data set. In medical imaging, point sets can generally represent different shape classes that span healthy and pathological exemplars. In such cases, the constructed SSM may not generalize well, largely because the probability density function (pdf) of the point sets deviates from the underlying assumption of Gaussian statistics. To this end, we propose a generative model for unsupervised learning of the pdf of point sets as a mixture of distinctive classes. A Variational Bayesian (VB) method is proposed for making joint inferences on the labels of point sets, and the principal modes of variations in each cluster. The method provides a flexible framework to handle point sets with no explicit point-to-point correspondences. We also show that by maximizing the marginalized likelihood of the model, the optimal number of clusters of point sets can be determined. We illustrate this work in the context of understanding the anatomical phenotype of the left and right ventricles in heart. To this end, we use a database containing hearts of healthy subjects, patients with Pulmonary Hypertension (PH), and patients with Hypertrophic Cardiomyopathy (HCM). We demonstrate that our method can outperform traditional PCA in both generalization and specificity measures.

• Item Type: Book Sections
• Additional Information: eISBN: 9783319199924.
• Status: Published
• Glasgow Author(s) Enlighten ID: Gooya, Dr Ali
• Authors: Gooya, A., Lekadir, K., Alba, X., Swift, A.J., Wild, J.M., and Frangi, A.F.
• College/School: College of Science and Engineering > School of Computing Science
• Publisher: Springer
• ISBN: 9783319199917

Related URLs

• University of Glasgow Library Catalogue