Title :
Using cine MR images to evaluate myocardial infarct transmurality on delayed enhancement images
Author :
El-Berbari, Racha ; Kachenoura, Nadjia ; Redheuil, Alban ; Block, I. ; Mousseaux, Elie ; Frouin, Frédérique
Author_Institution :
INSERM, Paris
Abstract :
Evaluating myocardial viability is an important prognostic factor in the follow-up of infarctions. Delayed enhancement (DE) perfusion images in MRI have been shown to be very valuable in the evaluation of myocardial viability. Visual interpretation is the most commonly used method. This study aims to segment the (DE) images prior to the estimation of the extent of infarcted tissue. Segmenting the myocardium using cine contraction images presents a high contrast between cavity and myocardium. After the segmentation, the fuzzy c-mean clustering algorithm was applied to estimate segmental transmurality using a conventional five point scale, which was then compared to the visual classification provided by the experts. Results on 14 patients (224 segments) showed an absolute agreement of 81% and a relative agreement (with one point difference) of 93%
Keywords :
biomedical MRI; cardiology; fuzzy set theory; haemorheology; image enhancement; image segmentation; medical image processing; muscle; pattern clustering; statistical analysis; cavity; cine MR images; cine contraction images; delayed enhancement images; delayed enhancement perfusion images; fuzzy c-mean clustering algorithm; image segmentation; infarctions; myocardial infarct transmurality; myocardial viability; myocardium; Cardiology; Clustering algorithms; Coronary arteriosclerosis; Delay; Image segmentation; Magnetic resonance imaging; Myocardium; Signal resolution; Spatial resolution; Ultrasonic imaging;
Conference_Titel :
Biomedical Imaging: Nano to Macro, 2006. 3rd IEEE International Symposium on
Conference_Location :
Arlington, VA
Print_ISBN :
0-7803-9576-X
DOI :
10.1109/ISBI.2006.1624873
