Echocardiography to cardiac CT image registration: Spatial and temporal registration of the 2D planar echocardiography images with cardiac CT volume

Abstract

This study proposes a registration framework to register 2D echocardiography images with cardiac CT volume. The registration realizes the fusion of CT and echocardiography with the aim to aid the diagnosis of cardiac diseases. The image registration framework consists of two major steps: temporal and spatial registration. Temporal registration utilizes the ECG data to identify frames at similar cardiac phase as the CT volume. Spatial registration is an intensity-based normalized mutual information (NMI) method applied with pattern search optimization algorithm to produce interpolated cardiac CT image that matches the echocardiography image. Our proposed registration method has been applied on the short axis "Mercedes Benz" sign view of the aortic valve. The accuracy of our fully automated registration method were 0.81 ± 0.08 and 1.30 ± 0.13 mm in terms of Dice coefficient and Hausdorff distance. This accuracy is comparable to gold standard manual registration by expert. There was no significant difference in aortic annulus diameter measurement between the automatically and manually registered CT images. Without the use of optical tracking, we have shown the applicability of this technique for effective registration of echocardiography with cardiac CT volume.