Automatic Segmentation of a Fetal Echocardiogram Using Modified Active Appearance Models and Sparse Representation

Abstract

A novel approach is presented to automatically segment the left ventricle in fetal echocardiograms. The proposed approach strategically integrates sparse representation, global constraint, and local refinement algorithms into an active appearance model (AAM) framework. In the training stage, we construct an enhanced AAM texture model to deal with the speckle and texture ambiguities. In the segmentation stage, the initial pose is located by a sparse representation method. Globally constrained points and local features with high clinical relevance are effectively incorporated into the AAM framework to make the model converge toward a desired position. Our proposed approach has been compared with the traditional ASM, the traditional AAM, and the globally constrained AAM on the synthetic and clinical data. The results show that compared with experts drawn contours, the overall segmentation accuracy of overlapped area in the synthetic and clinical images are 84.12% and 84.39%, respectively, superior to those of the other three methods. The experiments demonstrate that sparse representative methods greatly facilitate the initializations and our approach is capable of detecting the fetal left ventricle effectively, offering a better segmentation results.

Investigation on ultrasound images for detection of fetal congenital heart defects

“…When an image's US speckles are diminished, it becomes easier to analyze the image, whether static or moving. Methodologies for minimizing US erratic noise include Rayleigh-based reduced filtration as well as anisotropic dispersion [93,94], probability-based patch-based estimation of maximum likelihood [95], and just a combined effect of dimension reduction and nonlocal means [96]. After detecting ROI, structures interested in it can be identified.…”

“…An active appearance model (AAM) was used to determine the fetal heart structure [93]. Guo et al [96] used an improved AAM model with a sparse representation of the left ventricle (LV) [15][16][17].…”

Real-time echocardiography image analysis and quantification of cardiac indices

“…Previously reported methods for echo segmentation used low-level image processing-based methods such as watershed ( Cheng et al, 2005 ; Lacerda et al, 2008 ) and Otsu thresholding ( Santos et al, 2007 ), deformable model-based methods such as active contour ( Chen et al, 2007 ), B-spline snake ( Marsousi et al, 2010 ; Oktay and Akgul, 2009 ) and level set ( Nandagopalan et al, 2010 ), and statistical model-based methods such as active shape ( Guo et al, 2014 ; Beymer et al, 2009 ) and active appearance models ( Belous et al, 2013 ).…”