Medical image alignment based on landmark- and approximate contour-matching.

Purpose: Our goal is to propose a landmark- and contour-matching (LCM) registration method that uses both landmark information and approximate point correspondences to boost the similarity between image pairs with sparse landmark information. Approach: A model for registering two-dimensional (2D) medical images with landmark information and contour-approximating landmarks was proposed. The model was also extended to accommodate the registration of three-dimensional (3D) cardiac images. We validated the LCM method on 2D hand x-rays and 3D porcine cardiac magnetic resonance images. The following metrics were used to assess the quality of specific aspects of the registered images: Dice similarity coefficient for the overall image overlap, target registration error for pointwise correspondence, and interior angle for local curvature. Results: Target registrations were reduced from 27.12 to 0.01 mm post-LCM registration. Implementing the proposed algorithm also led to a 112% average improvement in image similarity in terms of Dice coefficients. In addition, interior angle measurements indicate that the proposed method preserved the local curvature at major reference landmarks and mitigated the appearance of deformities in the registered images. Conclusions: The proposed method addressed several issues associated with purely landmark-based techniques, such as iterative closest point registration and thin plate spline interpolation. Furthermore, it provided accurate registration results even in the presence of landmark localization errors.

Novel atlas of fiber directions built from ex-vivo diffusion tensor images of porcine hearts.

Cardiac MR image-based predictive models integrating statistical atlases of heart anatomy and fiber orientations can aid in better diagnosis of cardiovascular disease, a major cause of death worldwide. Such atlases have been built from diffusion tensor (DT) images and can be used in anisotropic models for personalized computational electro-mechanical simulations when the fiber directions from DTI are not available. In this paper, we propose a framework for building the first statistical fiber atlas from high-resolution ex-vivo DT images of porcine hearts. A mean geometry that represents the average cardiac morphology of the dataset was first generated via groupwise registration. Then, the associated average cardiac fiber architecture was mapped out by computing the mean of the transformed DT fields of the subjects. To evaluate the stability of the atlas, we performed leave-one-out cross-validation. The resulting tensor statistics indicate that the fiber atlas could accurately describe the fiber architecture of a healthy pig heart.