Automated segmentation of the left ventricle including papillary muscles in cardiac magnetic resonance images

Authors:
R. El Berbari;I. Bloch;A. Redheuil;E. D. Angelini;E. Mousseaux;F. Frouin;A. Herment
Affiliations:
INSERM, Paris, France and Université Pierre Marie Curie, Paris, France and GET, ENST TSI Department, CNRS UMR, Paris, France;GET, ENST, TSI Department, CNRS, UMR, Paris, France;APHP, HEGP Department of Cardiovascular Radiology, Paris, France;GET, ENST TSI Department, CNRS, UMR, Paris, France;APHP, HEGP Department of Cardiovascular Radiology, Paris, France;INSERM, Paris, France and Université Pierre Marie Curie, Paris, France;INSERM, Paris, France and Université Pierre Marie Curie, Paris, France
Venue:
FIMH'07 Proceedings of the 4th international conference on Functional imaging and modeling of the heart
Year:
2007

Citing 6
Cited 1

On active contour models and balloons

CVGIP: Image Understanding
A Comparison of Algorithms for Connected Set Openings and Closings

IEEE Transactions on Pattern Analysis and Machine Intelligence
Myocardial Delineation via Registration in a Polar Coordinate System

MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part I
Automatic Segmentation of the Left Ventricle in Cardiac MR and CT Images

International Journal of Computer Vision
Automatic segmentation of the left ventricle cavity and myocardium in MRI data

Computers in Biology and Medicine
Snakes, shapes, and gradient vector flow

IEEE Transactions on Image Processing

Development of an accelerated GVF semi-automatic contouring algorithm for radiotherapy treatment planning

Computers in Biology and Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel approach to segment cardiac magnetic resonance (CMR) images is presented in order to overcome some challenges such as problems with papillary muscles and the non homogeneities of the cavity due to blood flow. It consists in filtering short axis CMR images, using connected operators (area-open and area-close filters) to homogenize the cavity, prior to the segmentation which is performed using GVF-Snake algorithm in two steps. Validation was performed on thirty-nine slices by comparing resulting segmentation to the manual contours traced by an expert. This comparison showed good results with an overall average similarity area of 90.7% and an average distance between the two contours of 0.6 pixel.