Signed-distance function based non-rigid registration of image series with varying image intensity

Abstract

In this paper we propose a method for locally adjusted optical flow-based registration of multimodal images, which uses the segmentation of object of interest and its representation by the signed-distance function (OF dist method). We deal with non-rigid registration of the image series acquired by the Modiffied Look-Locker Inversion Recovery (MOLLI) magnetic resonance imaging sequence, which is used for a pixel-wise estimation of T 1 relaxation time. The spatial registration of the images within the series is necessary to compensate the patient's imperfect breath-holding. The evolution of intensities and a large variation of image contrast within the MOLLI image series, together with the myocardium of left ventricle (the object of interest) typically not being the most distinct object in the scene, makes the registration challenging. The paper describes all components of the proposed OF dist method and their implementation. The method is then compared to the performance of a standard mutual information maximization-based registration method, applied either to the original image (MIM) or to the signed-distance function (MIM dist). Several experiments with synthetic and real MOLLI images are carried out. On synthetic image with a single object, MIM performed the best, while OF dist and MIM dist provided better results on synthetic images with more than one object and on real images. When applied to signed-distance function of two objects of interest, MIM dist provided a larger registration error, but more homogeneously distributed, compared to OF dist. For the real MOLLI image series with left ventricle pre-segmented using a level-set method, the proposed OF dist registration performed the best, as is demonstrated visually and by measuring the increase of mutual information in the object of interest and its neighborhood.

Translational Cardiovascular Modeling: Tetralogy of Fallot and Modeling of Diseases

“…In this section we show the approach proposed in [60] for the registration of MOLLI MR image series. The MOLLI sequence is used for pixel-wise estimation of the tissue characteristics of T1 relaxation time.…”

“…The evolution of image intensity and large changes in image contrast are the factors that make the registration of the image series acquired by MOLLI challenging. In order to deal with this characteristics of the sequence, a special data similarity term was proposed by Škardová et al in [60], based on evaluating signed-distance of image voxels from segmented surfaces. The method requires the segmentation of epicardial and endocardial surface of the myocardium.…”