Title :
Automatic Quantification of Myocardial Infarction from Delayed Enhancement MRI
Author :
Valindria, Vanya V. ; Angue, Marion ; Vignon, Nicolas ; Walker, Paul M. ; Cochet, Alexandre ; Lalande, Alain
Author_Institution :
Groupe Imagerie Medicale, Univ. de Bourgogne, Dijon, France
fDate :
Nov. 28 2011-Dec. 1 2011
Abstract :
In this study, we developed a novel method for a fullyautomatic segmentation and quantification of myocardialinfarction from delay enhancement - magnetic resonanceimaging. Hyper-enhanced region corresponding to the infarctcore is separated from normal tissue via a Gaussian mixturemodel. Then, peri-infarct area is determined by spatial-weightedfuzzy clustering. No-reflow area inside the infarct core is alsodefined by an improved thresholding. Results of quantificationare presented in per-slice and global volumetric analysis, as wellas in bull´s eye of 16-segment model. Promising results have beenachieved in quantification and segmentation of myocardialinfarct. Our software could be used in clinical practice after acomplete validation.
Keywords :
Gaussian processes; biological tissues; biomedical MRI; fuzzy set theory; image enhancement; image segmentation; medical image processing; pattern clustering; Gaussian mixture model; MRI; automatic quantification; delay image enhancement; global volumetric analysis; image segmentation; image thresholding; infarct core; magnetic resonance imaging; myocardial infarction; per-slice analysis; spatial-weighted fuzzy clustering; tissue; Heart; Helium; Image segmentation; Magnetic resonance imaging; Manuals; Myocardium; Silicon; MRI; Myocardium; automatic; viability;
Conference_Titel :
Signal-Image Technology and Internet-Based Systems (SITIS), 2011 Seventh International Conference on
Conference_Location :
Dijon
Print_ISBN :
978-1-4673-0431-3
DOI :
10.1109/SITIS.2011.83