Christopher Casta

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

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 eight methods 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.

Improved Estimation of Cardiac Function Parameters Using a Combination of Independent Automated Segmentation Results in Cardiovascular Magnetic Resonance Imaging.

This work aimed at combining different segmentation approaches to produce a robust and accurate segmentation result. Three to five segmentation results of the left ventricle were combined using the STAPLE algorithm and the reliability of the resulting segmentation was evaluated in comparison with the result of each individual segmentation method. This comparison was performed using a supervised approach based on a reference method. Then, we used an unsupervised statistical evaluation, the extended Regression Without Truth (eRWT) that ranks different methods according to their accuracy in estimating a specific biomarker in a population. The segmentation accuracy was evaluated by estimating six cardiac function parameters resulting from the left ventricle contour delineation using a public cardiac cine MRI database. Eight different segmentation methods, including three expert delineations and five automated methods, were considered, and sixteen combinations of the automated methods using STAPLE were investigated. The supervised and unsupervised evaluations demonstrated that in most cases, STAPLE results provided better estimates than individual automated segmentation methods. Overall, combining different automated segmentation methods improved the reliability of the segmentation result compared to that obtained using an individual method and could achieve the accuracy of an expert.

Estimation of in vivo human myocardial fibre strain by integrating diffusion tensor and tagged MRI using FE modelling

In this study, we propose a methodology to estimate 3D+time maps of left ventricular fibre strain from human structural and dynamic MRI data. A finite element model integrates fibre principal direction throughout the left ventricle from an ex vivo human diffusion tensor MRI acquisition and motion from tagged MRI. This combination enables the estimation of fibre strain and its variation throughout the cardiac cycle. The long-term goal of this study is to apply this technique to an atlas of human fibre orientations and to investigate the importance of having subject-specific fibre orientation for fibre strain analysis.

An exploration framework for segmentation parameter spaces

Segmenting 3D images is critical in medical imaging but the parameterization of segmentation algorithms is difficult due to their computation heaviness and complex interactions between the parameters. This paper targets the exploration of deformable-model-based segmentation parameter spaces to search for salient ranges. We propose a framework exploring the parameter space with a genetic algorithm and interactively clustering the segmentation results. The framework only requires a limited number of parameters, it does not make any assumption on the segmentation algorithm and it does not require any ground truth or gold standard. Results obtained on a 3D image of the heart show that the proposed method has good robustness capabilities and that it is able to efficiently exhibit interesting parameter ranges.

Comparison of different segmentation approaches without using gold standard. Application to the estimation of the left ventricle ejection fraction from cardiac cine MRI sequences

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.

Integrating fiber orientation constraint into a spatio-temporal FEM model for heart borders and motion tracking in dynamic MRI

The dynamic deformable elastic template (DET) model has been previously introduced for the retrieval of personalized anatomical and functional models of the heart from dynamic cardiac image sequences. The dynamic DET model is a finite element deformable model, for which the minimum of the energy must satisfy a simplified equation of Dynamics. In this paper, we extend the model by integrating fiber constraints in order to improve the retrieval of cardiac deformations from cinetic magnetic resonance imaging (cineMRI). Evaluation conducted until now on cine MRI sequences shows an improvement of the recovery of the motion in images that present a low level of obvious rotation.

Driving dynamic cardiac model adaptation with MR-tagging displacement information

The dynamic deformable elastic template (DET) model has been previously introduced for the retrieval of personalized anatomical and functional models of the heart from dynamic cardiac image sequences. Dynamic DET model is a finite element deformable model, for which the minimum of the energy must satisfy a simplified equation of Dynamics. In this paper, we extend its scope to the retrieval of cardiac deformation within tagged magnetic imaging, using precomputed displacement fields as prior data to drive the model. Evaluation conducted on simulated sequences shows the performance of the model to track heart motion as a function of the quantity and quality of prior displacement information.