Feature-aligned 4D spatiotemporal image registration

Abstract

In this paper, we develop a feature-aware 4D spa-tiotemporal image registration method. Our model is based on a 4D (3D+time) free-form B-spline deforma-tion model which has both spatial and temporal smooth-ness. We first introduce an automatic 3D feature extrac-tion and matching method based on an improved 3D SIFT descriptor, which is scale- and rotation- invariant. Then we use the results of feature correspondence to guide an intensity-based deformable image registration. Experimental results show that our method can lead to smooth temporal registration with good matching ac-curacy; therefore this registration model is potentially suitable for dynamic tumor tracking. 1.