High-dimensional density ridges for hippocampus shape analysis

E. García Portugués, A. Meilán Vila

Skeletal representations (s-reps) have been successfully adopted to parsimoniously parametrize the shape of three-dimensional objects, and have been particularly employed in analyzing hippocampus shape variation. Within this context, we provide a fully-nonparametric dimension-reduction tool based on kernel smoothing for determining the main source of variability of hippocampus shapes parametrized by s-reps. The methodology introduces the so-called density ridges for data on the polysphere (a high-dimensional product of spheres) and involves addressing manifold computational challenges through closed formulae, efficient programming, and computational tricks.

Keywords: Density ridges, Dimension reduction, Directional data, Nonparametric Statistics, Skeletal representations.

GT09.NOPAR1 Invited Session. High dimension inference
November 7, 2023  3:30 PM
CC2: Conference Room

S. Novo Díaz, G. Aneiros Pérez

L. Freijeiro González, W. González Manteiga, M. Febrero Bande

A. Lago, I. Van Keilegom, J. C. Pardo Fernández, J. de Uña Álvarez