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

Lebenberg, Jessica; Buvat, Irène; Lalande, Alain; Clarysse, Patrick; Casta, Christopher; Cochet, Alexandre; Constantinidès, Constantin; Cousty, Jean; Cesare, Alain De; Jehan‐Besson, Stéphanie; Lefort, Muriel; Najman, Laurent; Roullot, Elodie; Sarry, Laurent; Tilmant, Christophe; Garreau, Mireille; Frouin, F.

doi:10.1109/tmi.2012.2201737

Cited by 31 publications

(37 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[24][25][26][27]33,46 This is especially true in the context of evaluating FDG-PET segmentation methods, where the task of interest is the estimation of volumetric metrics such as MTV and TLG. 33,47,48 However, an issue with these taskbased evaluations is the lack of knowledge about the true value of the metric.…”

Section: Discussionmentioning

confidence: 99%

“…The NSR metric has been widely used for evaluating imaging methods using NGS techniques on the basis of precision. 21,22,[24][25][26][27] However, to evaluate the imaging methods, instead of directly comparing the NSRs for the different methods, we suggest an alternative strategy that accounts for the uncertainty in the NSR metric. Before describing that strategy, we provide an intuitive explanation for how the NGS technique estimates the linearrelationship parameters for the different methods.…”

Section: No-gold-standard Evaluation Technique: Theorymentioning

confidence: 99%

“…22,23 This technique assumes that the measured quantitative values obtained using each imaging method are linearly related to the true quantitative values, and that the true quantitative values have been sampled from a distribution with known upper and lower limits. This approach has been used to compare software packages 24 and segmentation methods 25 on the task of measuring the cardiac ejection fraction. However, for some quantitative metrics, such as the MTV, the upper and lower limits on the distribution of true values are not known a priori.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Practical no-gold-standard evaluation framework for quantitative imaging methods: application to lesion segmentation in positron emission tomography

et al. 2017

View full text Add to dashboard Cite

Abstract. Recently, a class of no-gold-standard (NGS) techniques have been proposed to evaluate quantitative imaging methods using patient data. These techniques provide figures of merit (FoMs) quantifying the precision of the estimated quantitative value without requiring repeated measurements and without requiring a gold standard. However, applying these techniques to patient data presents several practical difficulties including assessing the underlying assumptions, accounting for patient-sampling-related uncertainty, and assessing the reliability of the estimated FoMs. To address these issues, we propose statistical tests that provide confidence in the underlying assumptions and in the reliability of the estimated FoMs. Furthermore, the NGS technique is integrated within a bootstrap-based methodology to account for patient-sampling-related uncertainty. The developed NGS framework was applied to evaluate four methods for segmenting lesions from F-Fluoro-2-deoxyglucose positron emission tomography images of patients with head-and-neck cancer on the task of precisely measuring the metabolic tumor volume. The NGS technique consistently predicted the same segmentation method as the most precise method. The proposed framework provided confidence in these results, even when gold-standard data were not available. The bootstrap-based methodology indicated improved performance of the NGS technique with larger numbers of patient studies, as was expected, and yielded consistent results as long as data from more than 80 lesions were available for the analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: No-gold-standard Evaluation Technique: Theorymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Practical no-gold-standard evaluation framework for quantitative imaging methods: application to lesion segmentation in positron emission tomography

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Raters, in this case, can be a collection of automated segmentation results, manual assessment, or a mixture between the two. Other recent approaches regarding the evaluation of segmentation methods without ground truth will be profitably investigated (Kohlberger et al, 2012;Lebenberg et al, 2012).…”

Section: Perspectivesmentioning

confidence: 99%

Right ventricle segmentation from cardiac MRI: A collation study

Petitjean¹,

Zuluaga²,

Bai³

et al. 2015

Medical Image Analysis

209

139

View full text Add to dashboard Cite

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/).

show abstract

“…However, the manual segmentation still has a certain degree of subjective, and the objective comparison of different approaches is still controversial. Confronted to this problem, Lebenberg et al proposed an unsupervised statistical evaluation (called the extended Regression Without Truth (eRWT)) to rank different segmentation approaches by using the computed clinical parameters such as EF and LVM [20,39]. In [20], three manual delineation methods were evaluated with the eRWT approach (M1-M3 are, respectively, delineated by three experts, and M1 is the used ground truth in the aforementioned experiments).…”

Section: Discussionmentioning

confidence: 99%

An SPCNN-GVF-based approach for the automatic segmentation of left ventricle in cardiac cine MR images

Wang

et al. 2016

Int J CARS

View full text Add to dashboard Cite

show abstract

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

Cited by 31 publications

References 21 publications

Practical no-gold-standard evaluation framework for quantitative imaging methods: application to lesion segmentation in positron emission tomography

Practical no-gold-standard evaluation framework for quantitative imaging methods: application to lesion segmentation in positron emission tomography

Right ventricle segmentation from cardiac MRI: A collation study

An SPCNN-GVF-based approach for the automatic segmentation of left ventricle in cardiac cine MR images

Contact Info

Product

Resources

About