Graph cut segmentation with a statistical shape model in cardiac MRI

•Challenging segmentation of the right ventricle in cardiac MR images.•Use of a statistical shape model based on a signed distance function in order to constrain the segmentation.•The shape prior is introduced into a graph cut approach.•Results are comparable to the state-of-the-art in RV segmentati...

Full description

Saved in:
Bibliographic Details
Published in:Computer vision and image understanding 2013-09, Vol.117 (9), p.1027-1035
Main Authors: Grosgeorge, D., Petitjean, C., Dacher, J.-N., Ruan, S.
Format: Article
Language:English
Subjects:
Assessments
Cardiac ventricle
Graph cut
Graphs
Image segmentation
Mathematical analysis
MRI
Segmentation
Shape
Shape prior
Tasks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Challenging segmentation of the right ventricle in cardiac MR images.•Use of a statistical shape model based on a signed distance function in order to constrain the segmentation.•The shape prior is introduced into a graph cut approach.•Results are comparable to the state-of-the-art in RV segmentation. Segmenting the right ventricle (RV) in magnetic resonance (MR) images is required for cardiac function assessment. The segmentation of the RV is a difficult task due to low contrast with surrounding tissues and high shape variability. To overcome these problems, we introduce a segmentation method based on a statistical shape model obtained with a principal component analysis (PCA) on a set of representative shapes of the RV. Shapes are not represented by a set of points, but by distance maps to their contour, relaxing the need for a costly landmark detection and matching process. A shape model is thus obtained by computing a PCA on the shape variations. This prior is registered onto the image via a very simple user interaction and then incorporated into the well-known graph cut framework in order to guide the segmentation. Our semi-automatic segmentation method has been applied on 248 MR images of a publicly available dataset (from MICCAI’12 Right Ventricle Segmentation Challenge). We show that encouraging results can be obtained for this challenging application.
ISSN:1077-3142
1090-235X
DOI:10.1016/j.cviu.2013.01.014