Format

Send to

Choose Destination
Med Image Anal. 2015 Jan;19(1):187-202. doi: 10.1016/j.media.2014.10.004. Epub 2014 Oct 28.

Right ventricle segmentation from cardiac MRI: a collation study.

Author information

1
LITIS EA 4108, Université de Rouen, 76801 Saint-Etienne-du-Rouvray, France. Electronic address: Caroline.Petitjean@univ-rouen.fr.
2
Centre for Medical Image Computing, University College London, London, UK.
3
Biomedical Image Analysis Group, Department of Computing, Imperial College London, UK.
4
INSERM U1096, Université de Rouen, 76031 Rouen Cedex, France.
5
LITIS EA 4108, Université de Rouen, 76801 Saint-Etienne-du-Rouvray, France.
6
GE Healthcare, London, Ontario, Canada.
7
Graduate Institute of Biomedical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan.
8
Biomedical Image Technologies, Universidad Politécnica de Madrid and CIBERBBN, Spain.
9
Section of Biomedical Image Analysis (SBIA), Department of Radiology, University of Pennsylvania, USA.
10
Western University, Robarts Research Institute, London, Ontario, Canada.
11
Section of Biomedical Image Analysis (SBIA), Department of Radiology, University of Pennsylvania, USA; A.A. Martinos Biomedical Imaging Center, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, USA.
12
National Heart and Lung Institute, St. Mary's Hospital, Imperial College London, UK.

Abstract

Magnetic Resonance Imaging (MRI), a reference examination for cardiac morphology and function in humans, allows to image the cardiac right ventricle (RV) with high spatial resolution. The segmentation of the RV is a difficult task due to the variable shape of the RV and its ill-defined borders in these images. The aim of this paper is to evaluate several RV segmentation algorithms on common data. More precisely, we report here the results of the Right Ventricle Segmentation Challenge (RVSC), concretized during the MICCAI'12 Conference with an on-site competition. Seven automated and semi-automated methods have been considered, along them three atlas-based methods, two prior based methods, and two prior-free, image-driven methods that make use of cardiac motion. The obtained contours were compared against a manual tracing by an expert cardiac radiologist, taken as a reference, using Dice metric and Hausdorff distance. We herein describe the cardiac data composed of 48 patients, the evaluation protocol and the results. Best results show that an average 80% Dice accuracy and a 1cm Hausdorff distance can be expected from semi-automated algorithms for this challenging task on the datasets, and that an automated algorithm can reach similar performance, at the expense of a high computational burden. Data are now publicly available and the website remains open for new submissions (http://www.litislab.eu/rvsc/).

KEYWORDS:

Cardiac MRI; Collation study; Right ventricle segmentation; Segmentation challenge; Segmentation method evaluation

PMID:
25461337
DOI:
10.1016/j.media.2014.10.004
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center