Topology-Preserving Tissue Classification of Magnetic Resonance Brain Images

This paper presents a new framework for multiple object segmentation in medical images that respects the topological properties and relationships of structures as given by a template. The technique, known as topology-preserving, anatomy-driven segmentation (TOADS), combines advantages of statistical tissue classification, topology-preserving fast marching methods, and image registration to enforce object-level relationships with little constraint over the geometry. When applied to the problem of brain segmentation, it directly provides a cortical surface with spherical topology while segmenting the main cerebral structures. Validation on simulated and real images characterises the performance of the algorithm with regard to noise, inhomogeneities, and anatomical variations

I. Introduction

The topological properties of 2-D and 3-D objects are often very simple, regardless of their geometric complexity. Human anatomy generally follows this rule, even for extremely convoluted shapes like the cerebral cortex or the vasculature. It also imposes strict spatial relationships. For example, the brain is enclosed inside the skull, and the cerebellum and cerebrum are neighboring but separated organs, linked by the brainstem. These relationships can be largely captured by topology, by considering all the related structures simultaneously.