Automatic Model-Based Segmentation of the Heart in CT Images

Abstract

Automatic image processing methods are a prerequisite to efficiently analyze the large amount of image data produced by computed tomography (CT) scanners during cardiac exams. This paper introduces a model-based approach for the fully automatic segmentation of the whole heart (four chambers, myocardium, and great vessels) from 3-D CT images. Model adaptation is done by progressively increasing the degrees-of-freedom of the allowed deformations. This improves convergence as well as segmentation accuracy. The heart is first localized in the image using a 3-D implementation of the generalized Hough transform. Pose misalignment is corrected by matching the model to the image making use of a global similarity transformation. The complex initialization of the multicompartment mesh is then addressed by assigning an affine transformation to each anatomical region of the model. Finally, a deformable adaptation is performed to accurately match the boundaries of the patient's anatomy. A mean surface-to-surface error of 0.82 mm was measured in a leave-one-out quantitative validation carried out on 28 images. Moreover, the piecewise affine transformation introduced for mesh initialization and adaptation shows better interphase and interpatient shape variability characterization than commonly used principal component analysis.

A competitive strategy for atrial and aortic tract segmentation based on deformable models

“…Then, during the segmentation, competitive contours with equal weights ( = 0.5) were used. The fixed threshold ( ℎ) was computed as the average value between the mean intensity on the selected region (window of size equal to 3 × 3 × 3 mm 3 ) and the expected intensity of the atrial/aortic walls (50 HU, (Ecabert et al, 2008)). The stop criteria of the BEAS-threshold method relies on the difference between mesh positions in two consecutive iterations and it finishes when small differences are found.…”

A bi-ventricular cardiac atlas built from 1000+ high resolution MR images of healthy subjects and an analysis of shape and motion

“…Based on the atlas, the cardiac shape or function of a popula- Rougon et al (2004) Tagged MR 11 healthy Statistical motion model Suinesiaputra et al (2009) 2D cine MR 44 healthy Statistical contour model Fonseca et al (2011) 2D cine MR 2864 healthy, 470 patients Statistical shape model Duchateau et al (2011) 2D US 21 healthy Statistical motion model Duchateau et al (2012) 2D Ecabert et al (2008) CT 13 patients Statistical shape model Zhuang et al (2010) Whole-heart MR 10 healthy - Hoogendoorn et al (2013) CT 138 patients Statistical shape model tion can be analysed and compared in a common space. The statistical shape model is the most commonly used tool for shape analysis.…”

Aortic valve prosthesis tracking for transapical aortic valve implantation

“…The main advantage of our tracking method is that it is a template/model-based tracking of the AVP in fluoroscopic sequences, to overcome the limitations of edge detection image-based methods [24]. Searching two feature points (i.e.…”