Title :
Weighted component-based tensor distance applied to graph-based segmentation of cardiac DT-MRI
Author :
Jin Kyu Gahm ; Kung, Geoffrey L. ; Ennis, Daniel B.
Author_Institution :
Dept. of Comput. Sci., Univ. of California, Los Angeles, Los Angeles, CA, USA
Abstract :
We propose a new weighted component-based tensor distance that linearly combines tensor shape (three tensor invariants) and orientation distances. Moreover the weighted component-based tensor distance allows users to easily adjust relative contributions of the distance components toward an optimal single distance for a particular application. We apply the weighted component-based tensor distance to graph-based multi-label segmentation of DT-MRI of infarcted hearts. We evaluate it using a synthetic tensor field that reflects important myocardial tensor field attributes, and three experimentally measured DT-MRI datasets from post-infarct porcine hearts.
Keywords :
biodiffusion; biomedical MRI; cardiology; image segmentation; medical image processing; DT-MRI dataset measurement; cardiac DT-MRI; diffusion tensor magnetic resonance imaging; graph-based multilabel segmentation; myocardial tensor field attribute; post-infarct porcine heart segmentation; synthetic tensor field; tensor invariant distance; tensor orientation distance; tensor shape distance; weighted component-based tensor distance; Diffusion tensor imaging; Heart; Image segmentation; Measurement; Shape; Signal to noise ratio; Tensile stress;
Conference_Titel :
Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-4673-6456-0
DOI :
10.1109/ISBI.2013.6556522