Space-time segmentation using level set active contours applied to myocardial gated SPECT

Abstract

This paper presents a new variational method for the segmentation of a moving object against a still background, over a sequence of [two-dimensional or three-dimensional (3-D)] image frames. The method is illustrated in application to myocardial gated single photon emission computed tomography (SPECT) data, and incorporates a level set framework to handle topological changes while providing closed boundaries. The key innovation is the introduction of a geometrical constraint into the derivation of the Euler-Lagrange equations, such that the segmentation of each individual frame can be interpreted as a closed boundary of an object (an isolevel of a set of hyper-surfaces) while integrating information over the entire sequence. This results in the definition of an evolution velocity normal to the object boundary. Applying this method to 3-D myocardial gated SPECT sequences, the left ventricle endocardial and epicardial limits can be computed in each frame. This space-time segmentation method was tested on simulated and clinical 3-D myocardial gated SPECT sequences and the corresponding ejection fractions were computed.

Segmentation of Vectorial Image Features Using Shape Gradients and Information Measures

“…It happens when statistical features of a region such as, for example, the mean or the variance of the intensity, are involved in the minimization. This case has been studied in (Chan and Vese, 2001;Debreuve et al, 2001;Jehan-Besson et al, 2001;Kim et al, 2002;Yezzi et al, 1999). In (Jehan-Besson et al, 2001;Jehan-Besson et al, 2003) the authors show that the minimization of functionals involving region-dependent features can induce additional terms in the evolution equation of the active contour that are important in practice.…”

“…An example of such regiondependent descriptor is k(x, Ω) = (I(x) − µ) 2 , where µ represents the mean of the intensity over the region Ω. This descriptor has been used by (Chan and Vese, 2001;Debreuve et al, 2001) for the segmentation of homogeneous regions. Generally one uses a linear combination of region-based and contourbased terms in order to perform a segmentation task.…”

“…Another alternative is to keep the region formulation to compute the gradient of the energy criterion with respect to the region instead of reducing region integrals to boundary integrals. In (Debreuve et al, 2001), the authors propose to compute the derivative of the criterion while taking into account the discontinuities across the contour. In (Jehan-Besson et al, 2001;Jehan-Besson et al, 2003) the computation of the evolution equation is achieved through shape derivation principles.…”

Robust real-time segmentation of images and videos using a smooth-spline snake-based algorithm

“…Chakraborty et al [5] combined both boundary and region information for medical images segmentation. Then, Chesnaud et al [9], Chan et al [6], Zhu et al [35], Paragios et al [24], and Debreuve et al [12] introduce region-based statistic descriptors for image or video segmentation. Jehan-Besson et al [17], [20] address the segmentation problem where features of the region to be segmented are embedded in region functionals.…”

Smoothing B-spline active contour for fast and robust image and video segmentation

“…Region-based active contour were first introduced by Ronfard et al [4] and Cohen et al [5]. Then Chan et al [6], Zhu et al [7], Amadieu et al [8], Paragios et al [9] and Debreuve et al [10] introduce region-based statistic descriptors for image or video segmentation. Finally Jehan-Besson et al [11] address the segmentation problem where features of the region to be segmented are involved in region functionals.…”