3D Nonlinear PET-CT Image Registration Algorithm with Constrained Free-form Deformations

O. Camara, O. Colliot, G. Delso, and I. Bloch (France)


nonlinear registration, constrained Free-Form Deforma tions, Mutual Information


This paper presents a 3D nonlinear PET-CT image regis tration method guided by a B-Spline Free-Form Deforma tions (FFD) model, dedicated to thoracic and abdominal regions. It is divided into two stages: one FFD-based reg istration of structures that can be identified in both images; and a whole-image intensity registration step constrained by the FFD computed during the first step. Different sim ilarity criteria have been adopted for both stages: Root Mean Square (RMS) to register recognized structures and Normalized Mutual Information (NMI) for optimizing the whole-image intensity stage. Structure segmentation is per formed according to a hierarchical procedure, where the extraction of a given structure is driven by information de rived from a simpler one. This information is composed of spatial constraints and expressed by the means of regions of interest, in which a 3D simplex mesh deformable model based method is applied. The results have been very posi tively evaluated by three medical experts.

Important Links:

Go Back