Now showing 1 - 2 of 2
PublicationStatistical Medial Model dor Cardiac Segmentation and Morphometry(2010-05-17) Sun, HuiIn biomedical image analysis, shape information can be utilized for many purposes. For example, irregular shape features can help identify diseases; shape features can help match different instances of anatomical structures for statistical comparison; and prior knowledge of the mean and possible variation of an anatomical structure's shape can help segment a new example of this structure in noisy, low-contrast images. A good shape representation helps to improve the performance of the above techniques. The overall goal of the proposed research is to develop and evaluate methods for representing shapes of anatomical structures. The medial model is a shape representation method that models a 3D object by explicitly defining its skeleton (medial axis) and deriving the object's boundary via "inverse-skeletonization". This model represents shape compactly, and naturally expresses descriptive global shape features like "thickening","bending", and "elongation". However, its application in biomedical image analysis has been limited, and it has not yet been applied to the heart, which has a complex shape. In this thesis, I focus on developing efficient methods to construct the medial model, and apply it to solve biomedical image analysis problems. I propose a new 3D medial model which can be efficiently applied to complex shapes. The proposed medial model closely approximates the medial geometry along medial edge curves and medial branching curves by soft-penalty optimization and local correction. I further develop a scheme to perform model-based segmentation using a statistical medial model which incorporates prior shape and appearance information. The proposed medial models are applied to a series of image analysis tasks. The 2D medial model is applied to the corpus callosum which results in an improved alignment of the patterns of commissural connectivity compared to a volumetric registration method. The 3D medial model is used to describe the myocardium of the left and right ventricles, which provides detailed thickness maps characterizing different disease states. The model-based myocardium segmentation scheme is tested in a heterogeneous adult MRI dataset. Our segmentation experiments demonstrate that the statistical medial model can accurately segment the ventricular myocardium and provide useful parameters to characterize heart function. PublicationEfficient Generation of Shape-Based Reference Frames for the Corpus Callosum for DTI-based Connectivity Analysis(2006-06-01) Sun, Hui; Yushkevich, Paul A; Gee, James C.; Zhang, Hui; Simon, Tony JYushkevich et.al. [17, 18] established a PDE-based deformable modeling approach called continuous medial representation (cm-rep), in which the geometric relationship between the medial axis of a 3D object and its boundary is captured. Continuous medial description of an object not only provides useful shape features for object characterization and comparison; it also imposes a shape-based reference frame on the interior of that object. Such a reference frame provides a useful means of representing different instances of an anatomical structure using a common canonical parametrization domain. This paper presents an efficient method to construct continuous medial shape models for 2D objects. A closed form solution for the ordinary differential equation (ODE) is derived via Pythagorean hodograph (PH) curves. That closed form solution reduces the computation complexity from solving an ODE system to pure algebraic manipulation. Using this method, we generate shape-based reference frames, and demonstrate how they can be applied to the analysis of anatomical connectivity of corpora callosa, obtained by fiber tracking in diffusion tensor magnetic resonance imaging (DTI) in a chromosome 22q11.2 deletion syndrome study.