Recent findings indicate a strong correlation between the risk of future heart disease and the volume of adipose tissue inside of the pericardium. So far, large-scale studies have been hindered by the fact that manual delineation of the pericardium is extremely time-consuming and that existing methods for automatic delineation lack accuracy. An efficient and fully automatic approach to pericardium segmentation and epicardial fat volume (EFV) estimation is presented, based on a variant of multi-atlas segmentation for spatial initialization and a random forest classifier for accurate pericardium detection. Experimental validation on a set of 30 manually delineated computer tomography angiography volumes shows a significant improvement on state-of-the-art in terms of EFV estimation [mean absolute EFV difference: 3.8 ml (4.7%), Pearson correlation: 0.99] with run times suitable for large-scale studies (52 s). Further, the results compare favorably with interobserver variability measured on 10 volumes.

No abstract

Registration is a key component in multi-atlas approaches to medical image segmentation. Current state of the art uses intensitybased registration methods, but such methods tend to be slow, which sets practical limitations on the size of the atlas set. In this paper, a novel feature-based registration method for affine registration is presented. The algorithm constructs an abstract representation of the entire atlas set, anüberatlas, through clustering of features that are similar and detected consistently through the atlas set. This is done offline. At runtime only the feature clusters are matched to the target image, simultaneously yielding robust correspondences to all atlases in the atlas set from which the affine transformations can be estimated efficiently. The method is evaluated on 20 CT images of the heart and 30 MR images of the brain with corresponding gold standards. Our approach succeeds in producing better and more robust segmentation results compared to two baseline methods, one intensity-based and one feature-based, and significantly reduces the running times.