Title
Comparison of different segmentation approaches without using gold standard. Application to the estimation of the left ventricle ejection fraction from cardiac cine MRI sequences.
Abstract
A statistical method is proposed to compare several estimates of a relevant clinical parameter when no gold standard is available. The method is illustrated by considering the left ventricle ejection fraction derived from cardiac magnetic resonance images and computed using seven approaches with different degrees of automation. The proposed method did not use any a priori regarding with the reliability of each method and its degree of automation. The results showed that the most accurate estimates of the ejection fraction were obtained using manual segmentations, followed by the semiautomatic methods, while the methods with the least user input yielded the least accurate ejection fraction estimates. These results were consistent with the expected performance of the estimation methods, suggesting that the proposed statistical approach might be helpful to assess the performance of estimation methods on clinical data for which no gold standard is available.
Year
DOI
Venue
2011
10.1109/IEMBS.2011.6090732
EMBC
Keywords
Field
DocType
left ventricle ejection fraction,cardiology,segmentation approach,gold standard,image segmentation,biomedical mri,cardiac cine mri sequences,statistical method,cardiac magnetic resonance images,medical image processing,automation,databases,ejection fraction,magnetic resonance imaging,estimation,magnetic resonance image,gold
Nuclear medicine,Ejection fraction,Computer science,Regression analysis,A priori and a posteriori,Image segmentation,Artificial intelligence,Ventricle,Gold standard,Computer vision,Pattern recognition,Segmentation,Magnetic resonance imaging
Conference
Volume
ISSN
ISBN
2011
1557-170X
978-1-4244-4122-8
Citations 
PageRank 
References 
1
0.45
4
Authors
17