Structural template formation with discovery of subclasses
A ma jor focus of computational anatomy is to extract the most relevant information to identify and characterize anatomical variability within a group of sub jects as well as between different groups. The construction of atlases is central to this effort. An atlas is a deterministic or probabilistic model with intensity variance, structural, functional or biochemical information over a population. To date most algorithms to construct atlases have been based on a single sub ject assuming that the population is best described by a single atlas. However, we believe that in a population with a wide range of sub jects multiple atlases may be more representative since they reveal the anatomical differences and similairities within the group. In this work, we propose to use the K-means clustering algorithm to partition a set of images into several subclasses, based on a joint distance which is composed of a distance quantifying the deformation between images and a dissimilarity measured from the registration residual. During clustering, the spatial transformations are averaged rather than images to form cluster centers, to ensure a crisp reference. At the end of this algorithm, the updated centers of the k clusters are our atlases. We demonstrate this algorithm on a subset of a public available database with whole brain volumes of sub jects aged 18-96 years. The atlases constructed by this method capture the significant structural differences across the group.
Reference and Preprint
X. Long and C. Wyatt, Structural template formation with discovery of subclasses, Proc. SPIE 7623, 76231B (2010), DOI:10.1117/12.843994 [Presentation Slides].
Code and Example Data
The following package contains the source code, scripts, and instructions for replicating the results in the paper: K-MeansPackage.tar.gz.
Linux-x86 (GCC 3.4.3)
Comments and Bug Reports