Segmentation of elastographic images using a coarse-to-fine active contour model

Abstract

Delineation of radiofrequency-ablation-induced coagulation (thermal lesion) boundaries is an important clinical problem that is not well addressed by conventional imaging modalities. Elastography, which produces images of the local strain after small, externally applied compressions, can be used for visualization of thermal coagulations. This paper presents an automated segmentation approach for thermal coagulations on 3-D elastographic data to obtain both area and volume information rapidly. The approach consists of a coarse-to-fine method for active contour initialization and a gradient vector flow, active contour model for deformable contour optimization with the help of prior knowledge of the geometry of general thermal coagulations. The performance of the algorithm has been shown to be comparable to manual delineation of coagulations on elastograms by medical physicists (r = 0.99 for volumes of 36 radiofrequency-induced coagulations). Furthermore, the automatic algorithm applied to elastograms yielded results that agreed with manual delineation of coagulations on pathology images (r = 0.96 for the same 36 lesions). This algorithm has also been successfully applied on in vivo elastograms.

Measurement of thermally ablated lesions in sonoelastographic images using level set methods

“…Subsequently, the resulting outline can be used as the input for the segmentation of the lesion in the following image during the length of the procedure. Template matching has been used previously to automate the initialization step of a segmentation algorithm for compression elastography [14]. In our experiments, this approach fails due to the presence of respiratory and boundary artifacts.…”

“…The algorithm was based on thresholding and morphological operations and was applied to in vitro RFA lesions. Later, an automated algorithm was reported by the same group [14]. The approach consisted of a coarse-to-fine method which was initialized by template matching and then refined by an active contour model.…”

Edge and line oriented contour detection: State of the art

“…In [131,262], EF is not performed pixel by pixel, but connectivity information about the object contours is taken into account. In [263][264][265] snakes based on EF are described. In [129,130] EF is combined with biologically motivated texture suppression schemes and in [266] EF is applied to color images.…”

Augmenting CT cardiac roadmaps with segmented streaming ultrasound

“…To accomplish this, manual initialization is usually required, which is not preferred in our interventional application. Automated and semi-automated methods have been proposed to solve this problem, which use optical flow tracking 26 , Hough tranform 27 , or a multi-scale implementation 28 . Since temporal performance is critically important for our real-time interventional application, a computationally efficient approach was needed.…”