Assessment of global cardiac function in MSCT imaging using fuzzy connectedness segmentation

Fleureau, Julien; Garreau, Mireille; Simon, Jean‐Marc; Hachemani, Rachid; Boulmier, Dominique

doi:10.1109/cic.2008.4749144

Cited by 9 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The slices are chosen due to the presence of outlier segmentations. The different segmentation entries are selected inside a database that contains the results obtained by different research teams [14,15,16,17,18,19] for some parameters which are not necesseraly the optimal ones. The corresponding contours of the different entries are given respectively in Fig.5 for the first slice (denoted by slice 1) and in Fig.7 for the second slice (denoted by slice 2).…”

Section: Cardiac Mr Imagesmentioning

confidence: 99%

A mutual reference shape based on information theory

Jehan‐Besson

Tilmant

Cesare

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

International audienceIn this paper, we propose to consider the estimation of a refer-ence shape from a set of different segmentation results using both active contours and information theory. The reference shape is defined as the minimum of a criterion that benefits from both the mutual information and the joint entropy of the input segmentations and called a mutual shape. This energy criterion is here justified using similarities between informa-tion theory quantities and area measures, and presented in a continuous variational framework. This framework brings out some interesting evaluation measures such as the speci-ficity and sensitivity. In order to solve this shape optimization problem, shape derivatives are computed for each term of the criterion and interpreted as an evolution equation of an active contour. Some synthetical examples allow us to cast the light on the difference between our mutual shape and an average shape. Our framework has been considered for the estimation of a mutual shape for the evaluation of cardiac segmentation methods in MRI

show abstract

Section: Cardiac Mr Imagesmentioning

confidence: 99%

A mutual reference shape based on information theory

Jehan‐Besson

Tilmant

Cesare

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Combining multi-detector and gantry high rotation speed, Multi-Slice CT (MSCT) allows dynamic cardiac acquisition with a high spatial resolution. In order to segment the left endocardium over the cardiac cycle, we use a segmentation method based on a fuzzy connectedness algorithm [16], the results have been visually validated by a medical expert. The segmented surfaces are then reconstructed.…”

Section: B Ct Data Segmentationmentioning

confidence: 99%

Dynamic registration of cardiac US and CT data using Fourier descriptors and Dynamic Time Warping

Tavard¹,

Simon²,

Hernández³

et al. 2012

2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA)

Self Cite

View full text Add to dashboard Cite

Cardiac Resynchronization Therapy (CRT) can be optimized by the fusion of anatomical, functional and electrical information in a unified framework in order to identify the most effective pacing sites. The aim of this work is to perform a registration between dynamic CT and ultrasound (US) images (2D speckle tracking mode). The proposed registration approach is based on a contour to surface scheme, decomposed in four steps: (1) the temporal synchronization of data; (2) the segmentation of the left ventricle endocardial surface from the 3D+t CT data; (3) the segmentation and tracking of the myocardium from the 2D+t US data; (4) the registration of US contour with the CT surface. The originality of the method relies on the use of Fourier descriptors and Dynamic Time Warping (DTW) to handle different spatial and temporal resolutions as well as dissimilar cardiac rhythms between CT and US data. An evaluation on simulated data is described as well as results obtained on three patient databases.

show abstract

“…Un seuillage choisi par l'utilisateur est appliqué sur cette carte et permet de ne conserver que les structures d'intérêt. Ces méthodes ont montré leur intérêt pour la segmentation du VG en imagerie scanner cardiaque [17]. Dans les méthodes de « graph-cuts » [18], l'utilisateur doit sélectionner deux régions appartenant l'une à l'objet et l'autre au fond pour initialiser une procédure de minimisation d'énergie basée sur un algorithme de coupure de graphe.…”

Section: Introductionunclassified

Segmentation 3D multi-objets d’images scanner cardiaques : une approche multi-agents

Fleureau¹,

Garreau²,

Boulmier³

et al. 2009

IRBM

Self Cite

View full text Add to dashboard Cite

Nous proposons une nouvelle méthode de segmentation permettant une détection multi-objets, semi-interactive et à caractère générique, appliquée à l'extraction de structures cardiaques en imagerie scanner multibarettes. L'approche proposée repose sur l'élaboration d'un schéma multi-agents combiné à une méthode de classification supervisée qui permet l'introduction d'a priori dans le processus de segmentation ainsi que des temps de calcul rapides. Le système multi-agents proposé est centralisé autour d'un agent communiquant qui contrôle une population d'agents situés dans l'image dont le rôle est d'assurer la segmentation au moyen d'interactions de type coopératif et compétitif. La méthode proposée a été testée sur plusieurs bases de données patient. Quelques résultats représentatifs sont finalement présentés et discutés. AbstractWe propose a new technique for general purpose, semi-interactive and multi-object segmentation in N-dimensional images, applied to the extraction of cardiac structures in MultiSlice Computed Tomography (MSCT) imaging. The proposed approach makes use of a multi-agent scheme combined with a supervised classification methodology allowing the introduction of a priori information and presenting fast computing times. The multi-agent system is organised around a communicating agent which manages a population of situated agents which segment the image through cooperative and competitive interactions. The proposed technique has been tested on several patient data sets. Some typical results are finally presented and discussed.

show abstract

Assessment of global cardiac function in MSCT imaging using fuzzy connectedness segmentation

Cited by 9 publications

References 11 publications

A mutual reference shape based on information theory

A mutual reference shape based on information theory

Dynamic registration of cardiac US and CT data using Fourier descriptors and Dynamic Time Warping

Segmentation 3D multi-objets d’images scanner cardiaques : une approche multi-agents

Contact Info

Product

Resources

About