Semiautomatic segmentation of aortic valve from sequenced ultrasound image using a novel shape-constraint GCV model

Abstract

Compared with the CV model, as a result of the combination of the gradient vector and neighborhood shape information, this semiautomatic segmentation method significantly improves the accuracy and robustness of AV segmentation, making it feasible for improved segmentation of aortic valves from US images that have fuzzy boundaries.

Automatic aortic root segmentation and anatomical landmarks detection for TAVI procedure planning

“…Zheng et al [11,12] proposed a learningbased approach to automatically detect major landmarks with marginal space learning based on the C-arm CT. Model-based approach has been followed by Waechter et al [13] to locate coronary ostia and annulus plane. Ionasec et al [14] also proposed a valve model to detect landmarks but their work was based on 4D CT. Automatic measurements of aortic annulus diameters has been proposed with 3d transesophageal echocardiography (TEE) [15] or ultrasound images [16][17][18]. Grbic et al [19] employed robust machine learning algorithms to estimate the valve model parameters from non-contrast CT including information on valve leaflets and calcium.…”