Automated Cardiovascular Segmentation in Patients with Congenital Heart Disease from 3D CMR Scans: Combining Multi-atlases and Level-Sets

This paper presents an automatic method that enables segmentation of the whole heart and the great vessels from 3D MRI scans. The proposed method is built upon a multi-atlas-based segmentation approach and consists of a number of intermediate steps to enable accurate segmentation of the ventricular myocardial tissue, intra-cardiac blood pool, and the aorta. The method was tested on the datasets provided by the HVSMR 2016 MICCAI challenge organizers. Results on the testing data show that, the proposed method achieved an average Dice index of 0.89 for the blood pool and 0.75 for the ventricular myocardial tissue. The corresponding average surface distance error were 1.6 mm and 1.1 mm, respectively.

[1]  Chunming Li,et al.  MRI Tissue Classification and Bias Field Estimation Based on Coherent Local Intensity Clustering: A Unified Energy Minimization Framework , 2009, IPMI.

[2]  T van Walsum,et al.  Evaluation of a multi-atlas based method for segmentation of cardiac CTA data: a large-scale, multicenter, and multivendor study. , 2010, Medical physics.

[3]  L.-K. Shark,et al.  Medical Image Segmentation Using New Hybrid Level-Set Method , 2008, 2008 Fifth International Conference BioMedical Visualization: Information Visualization in Medical and Biomedical Informatics.

[4]  Coert Metz,et al.  Automatic quantification of epicardial fat volume on non-enhanced cardiac CT scans using a multi-atlas segmentation approach. , 2013, Medical physics.

[5]  Ronald van 't Klooster,et al.  Quantification of common carotid artery and descending aorta vessel wall thickness from MR vessel wall imaging using a fully automated processing pipeline , 2017, Journal of magnetic resonance imaging : JMRI.

[6]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[7]  Max A. Viergever,et al.  elastix: A Toolbox for Intensity-Based Medical Image Registration , 2010, IEEE Transactions on Medical Imaging.

[8]  L. V. van Vliet,et al.  Vessel specific coronary artery calcium scoring: an automatic system. , 2013, Academic radiology.

[9]  R. J. van der Geest,et al.  Fully automatic segmentation of left atrium and pulmonary veins in late gadolinium‐enhanced MRI: Towards objective atrial scar assessment , 2016, Journal of magnetic resonance imaging : JMRI.