Directional mean shift and its application for topology classification of local 3D structures

Abstract

In this study, we introduce a new directional nonparametric clustering algorithm for 3D medical structure topology classification. This paper proposes directional mean shift (DMS) which extends the well known mean shift-based clustering, for handling directional statistics, toward analyzing directional/circular-domain data with phase-wraparound boundary conditions. Our overall approach transforms the 3D topology classification problem into a clustering analysis of a 2D image, following the work by Bahlmann et al. [2] in the context of computer-aided diagnosis (CAD). The proposed DMS replaces the expectation-maximization (EM) algorithm for Gaussian mixture model (GMM) fitting used in the previous method addressing the shortcomings of the Bahlmann's method. Results from our experiments demonstrate the effectiveness of DMS in contrast to the original EM-based approach in solving the clustering problem with a 2D image unwrapped from a 3D spherical data, leading to better accuracy in the topology classification task.