Temporally-dependent image similarity measure for longitudinal analysis

Current longitudinal image registration methods rely on the assumption that image appearance between time-points remains constant or changes uniformly within intensity classes. This assumption, however, is not valid for magnetic resonance imaging of brain development. Registration methods developed to align images with non-uniform appearance change either (i) locally minimize some global similarity measure, or (ii) iteratively estimate an intensity transformation that makes the images similar. However, these methods treat the individual images as independent static samples and are inadequate for the strong non-uniform appearance changes seen in neurodevelopmental data. Here, we propose a model-based similarity measure intended for aligning longitudinal images that locally estimates a temporal model of intensity change. Unlike previous approaches, the model-based formulation is able to capture complex appearance changes between time-points and we demonstrate that it is critical when using a deformable transformation model.