[ITK-users] New Submission: Segmentation of Multi-Center 3D Left Ventricular Echocardiograms by Active Appearance Models

[MIDAS Journal]

Hello,

A new submission has been added to the MIDAS Journal.

Title: Segmentation of Multi-Center 3D Left Ventricular Echocardiograms by Active Appearance Models
Authors: Van Stralen M., Haak A., Leung E.K., Van Burken G., Bosch J.G.
Abstract: Segmentation of 3D echocardiograms (3DEs) is still a challenging task due to the low signal-to-noise ratio, the limited field of view, and typical ultrasound artifacts. We propose to segment the left ventricular endocardial surface by using Active Appearance Models (AAMs). Separate end-diastolic (ED) and end-systolic (ES) AAMs were built from presegmented 3DEs of the CETUS training data and 25 previously acquired 3DEs, imaged using various 3DE equipment. The AAMs fully automatically segmented the 15 training sets in a leave-one-out cross validation, comparing two training populations and various initialization strategies. All segmentations took about 15 seconds per patient. The comparison on the CETUS training data shows that the AAM benefits from additional training data and more accurate initialization. The results on the CETUS training and testing data confirm good ED and ES segmentation accuracy on multi-center, multi-vendor, multi-pathology data, and corresponding EF e
 stimation. Selection from different initialization strategies, based on the minimal residual error, and propagation of detected ED contours to initialize ES detection, contributed to more accurate segmentations in this heterogeneous population.

Download and review this publication at: http://hdl.handle.net/10380/3488

Generated by the MIDAS Journal

You are receiving this email because you asked to be informed by the MIDAS Journal for new submissions. To change your email preference visit http://www.midasjournal.org/ .