Nonsupervised Ranking of Different Segmentation Approaches: Application to the Estimation of the Left Ventricular Ejection Fraction From Cardiac Cine MRI Sequences

Abstract : A statistical methodology is proposed to rank several estimation methods of a relevant clinical parameter when no gold standard is available. Based on a regression without truth method, the proposed approach was applied to rank eightmethods without using any a priori information regarding the reliability of each method and its degree of automation. It was only based on a prior concerning the statistical distribution of the parameter of interest in the database. The ranking of the methods relies on figures of merit derived from the regression and computed using a bootstrap process. The methodology was applied to the estimation of the left ventricular ejection fraction derived from cardiac magnetic resonance images segmented using eight approaches with different degrees of automation: three segmentations were entirely manually performed and the others were variously automated. The ranking of methods was consistent with the expected performance of the estimation methods: the most accurate estimates of the ejection fraction were obtained using manual segmentations. The robustness of the ranking was demonstrated when at least three methods were compared. These results suggest 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.
Document type :
Journal articles
IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers (IEEE), 2012, 31 (8), pp.1651-1660. <10.1109/TMI.2012.2201737>


https://hal.archives-ouvertes.fr/hal-00726197
Contributor : Alain Lalande <>
Submitted on : Wednesday, August 29, 2012 - 12:08:17 PM
Last modification on : Thursday, January 29, 2015 - 9:26:44 AM

File

Lebenberg_TMI_2012.pdf
fileSource_public_greenPublisher

Identifiers

Citation

Jessica Lebenberg, I. Buvat, Alain Lalande, Patrick Clarysse, Christopher Casta, et al.. Nonsupervised Ranking of Different Segmentation Approaches: Application to the Estimation of the Left Ventricular Ejection Fraction From Cardiac Cine MRI Sequences. IEEE Transactions on Medical Imaging, Institute of Electrical and Electronics Engineers (IEEE), 2012, 31 (8), pp.1651-1660. <10.1109/TMI.2012.2201737>. <hal-00726197>

Export

Share

Metrics

Consultation de
la notice

233

Téléchargement du document

74