Clustering of Aortic Vortex Flow in Cardiac 4D PC-MRI Data

Meuschke, Monique; Lawonn, Kai; Köhler, Benjamin; Preim, Uta; Preim, Bernhard

doi:https://doi.org/10.1007/978-3-662-49465-3_33

by Monique Meuschke, Kai Lawonn, Benjamin Köhler, Uta Preim, Bernhard Preim

Abstract:

This paper presents a method for clustering aortic vortical blood flow using a reliable dissimilarity measure combined with a clustering technique. Current medical studies investigate specific properties of aberrant blood flow patterns such as vortices, since a correlation to the genesis and evolution of various cardiovascular diseases is assumed. The classification requires a precise definition of spatio-temporal vortex entities, which is performed manually. This task is time-consuming for larger studies and error-prone due to inter-observer variability. In contrast, our method allows an automatic and reliable vortex clustering that facilitates the vortex classification. We introduce an efficient calculation of a dissimilarity measure that groups spatio-temporally adjacent vortices. We combine our dissimilarity measure with the most commonly used clustering techniques. Each combination was applied to 15 4D PCMRI datasets. The clustering results were qualitatively compared to a manually generated ground truth of two domain experts.

Reference:

Clustering of Aortic Vortex Flow in Cardiac 4D PC-MRI Data (Monique Meuschke, Kai Lawonn, Benjamin Köhler, Uta Preim, Bernhard Preim), In Bildverarbeitung für die Medizin 2016 (Thomas Tolxdorff, Thomas M. Deserno, Heinz Handels, Hans-Peter Meinzer, eds.), Springer Berlin Heidelberg, 2016.

Bibtex Entry:

@inproceedings{meuschke_clustering_2016,
	address = {Berlin, Heidelberg},
	title = {Clustering of {Aortic} {Vortex} {Flow} in {Cardiac} 4D {PC}-{MRI} {Data}},
	isbn = {978-3-662-49464-6},
	doi = {https://doi.org/10.1007/978-3-662-49465-3_33},
	abstract = {This paper presents a method for clustering aortic vortical blood flow using a reliable dissimilarity measure combined with a clustering technique. Current medical studies investigate specific properties of aberrant blood flow patterns such as vortices, since a correlation to the genesis and evolution of various cardiovascular diseases is assumed. The classification requires a precise definition of spatio-temporal vortex entities, which is performed manually. This task is time-consuming for larger studies and error-prone due to inter-observer variability. In contrast, our method allows an automatic and reliable vortex clustering that facilitates the vortex classification. We introduce an efficient calculation of a dissimilarity measure that groups spatio-temporally adjacent vortices. We combine our dissimilarity measure with the most commonly used clustering techniques. Each combination was applied to 15 4D PCMRI datasets. The clustering results were qualitatively compared to a manually generated ground truth of two domain experts.},
	booktitle = {Bildverarbeitung für die {Medizin} 2016},
	publisher = {Springer Berlin Heidelberg},
	author = {Meuschke, Monique and Lawonn, Kai and Köhler, Benjamin and Preim, Uta and Preim, Bernhard},
	editor = {Tolxdorff, Thomas and Deserno, Thomas M. and Handels, Heinz and Meinzer, Hans-Peter},
	year = {2016},
	pages = {182--187}
}