Knowledge-based system for boundary detection of four-dimensional cardiac magnetic resonance image sequences

Abstract

A strategy for a knowledge-based system to detect the interior and exterior boundaries of the left ventricle from time-varying cross-sectional images obtained by ECG-gated magnetic resonance imaging (MRI) is discussed. The system uses both fuzzy set theory and Dempster and Shafer theory to manage the knowledge and to control the flow of system information for more efficient use of limited computational resources and memory space. The key to the approach is that it performs edge detection on images through integration and unification of knowledge and information from edge candidates on all the slices and phases of the acquired cardiac MRI dataset. The analysis system does not base decisions on individual measurements, but on consensus opinions by combining many knowledge sources, some of which may not be completely accurate.

Quantification in cardiac MRI

“…ES ϭ end-systolic, ED ϭ end-diastolic. tion of the endocardial and epicardial contours from short-axis cine MR imaging studies (32)(33)(34)(35). In the next section a short description is given of the underlying methods and validation results from the algorithms developed at our laboratory, which have been integrated in a software package, MASS, implemented on a SUN workstation (36).…”

Left Ventricular Ejection Fraction Calculation from Automatically Selected and Processed Diastolic and Systolic Frames in Short?Axis Cine?MRI

“…Several authors have developed algorithms designed on a semiautomatic or automatic delineation of the left ventricular cavity (Baldy et al, 1994;Boudraa, 1997;Fleagle et al, 1991;Furber et al, 1998;Goshtasby and Turner, 1995;Graves et al, 2000;Nachtomy et al, 1998;Ranganath, 1995;Suh et al, 1993;van der Geest et al, 1997;Waiter et al, 1999;Zimmer and Akselrod, 1996). Some of them use techniques based on geometrical information on pixel groups.…”

Cue-Based Segmentation of 4D Cardiac Image Sequences

“…Let s denote a 4D image, or volume sequence, defined over 4D Euclidean space 4 . Let (x, y, z, t) ∈ 4 denote a 4D image point, or hypervoxel, and let s(x, y, z, t) denote the gray-scale value of 4D image s at hypervoxel (x, y, z, t).…”

“…Let (x, y, z, t) ∈ 4 denote a 4D image point, or hypervoxel, and let s(x, y, z, t) denote the gray-scale value of 4D image s at hypervoxel (x, y, z, t). For a typical radiological imaging scanner, the volume sequence s is usually defined over a finite-extent lattice of 4 ,…”

“…Static analyses of the heart can yield information such as chamber volumes and morphology, while dynamic analyses can provide information on myocardial wall mechanics, valvular function, and physiologic parameters such as ejection fraction. Several studies using 4D cardiac analysis have already demonstrated its utility [3][4][5][6][7].…”