Source: Dissertation Abstracts International, Volume: 74-11(E), Section: B.

Adviser: James S. Duncan.

Heart disease is the number one cause of death in the United States and the left ventricle is often studied as an overall indicator of heart health. Quantitative analysis of left ventricular deformation has been an active area of research within the medical imaging community for many years. Accurate motion tracking can provide quantitative information about the extent and location of myocardial injury. This information can be useful both in the diagnosis of disease and in studying the efficacy of disease treatments. Echocardiography provides a non-invasive, readily available method for generating real-time images of the left ventricle.

Left ventricle deformation analysis often begins with some form of frame to frame displacement estimation. While there are a variety of strategies that might accomplish this, we chose two complementary approaches that can estimate information at both the myocardial boundaries (shape tracking) and mid-wall (RF-based speckle tracking). In shape tracking, features are generated directly from image intensity values or segmentation of the ventricle and then matched in neighboring frames using a point-matching technique. Speckle tracking is an alternative approach that tracks patterns in the ultrasound data in subsequent frames. These two methods provide complementary information. Shape tracking gives high accuracy on boundaries of the heart wall, while speckle tracking gives reliable displacements across the myocardium. This work focuses on combining these two methods to yield a more accurate representation of the overall ventricular deformation. The displacements generated from the two methods provide sparse information over the heart wall and radial basis functions can be used to combine the two sources of information to generate a dense displacement field. From the displacement data measures of deformation, cardiac strains, can be calculated to determine the condition of the heart.

In this work we develop an adaptive multilevel radial basis function approach to combine shape and speckle tracked displacements for both 2D+time and 3D+time data. These methods are evaluated on acute open-chest canines pre- and post-coronary artery occlusion to show the ability of the combined method to differentiate diseased tissue. The proposed methods are compared against magnetic resonance tagged images for both 2D+time and 3D+time data to validate the results. We further validate our findings by comparing functionally defined infarct zones found using our methods to post-mortem histology of the hearts. We show that our methods are able to identify normal and diseased tissue, as well as a functional border zone that is critical for treatment. We also show that our methods are able to define and track these zones in closed-chest chronic data acquired at four time points following coronary artery occlusion. The findings suggest that the combined method will allow for the use of these methods in investigating new treatment methods for heart disease.