SEGMENTING TAGGED CARDIAC MRI DATA USING A LOCAL VARIANCE FILTER

Authors

  • Tomáš Oberhuber Department of Mathematics, Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague, Trojanova 13, Praha 2, 120 00
  • Slavomír Kučera Department of Mathematics, Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague, Trojanova 13, Praha 2, 120 00
  • Jakub Loucký Department of Mathematics, Faculty of Nuclear Sciences and Physical Engineering, Czech Technical University in Prague, Trojanova 13, Praha 2, 120 00
  • Lucie Súkupová Department of Radiology, Institute for Clinical and Experimental Medicine, Vídeňská 1958/9, Praha 4, 140 21
  • Jaroslav Tintěra Department of Radiology, Institute for clinical and experimental medicine, Vídenská 1958/9, Praha 4, 140 21

DOI:

https://doi.org/10.14311/AP.2014.54.0214

Abstract

We present a new method for segmenting tagged MRI data. It is based on the observation that the tagging grid vanishes almost immediately inside the ventricles because of the blood flow. Segmentation can be therefore driven by the intensity of the tagging grid. We estimate the intensity using a local variance filter. The main segmentation is computed by the graph-cuts method, though other segmentation methods can also be used. We compare the results obtained by our method with manual segmentation.

Downloads

Download data is not yet available.

Downloads

Published

2014-06-27

How to Cite

Oberhuber, T., Kučera, S., Loucký, J., Súkupová, L., & Tintěra, J. (2014). SEGMENTING TAGGED CARDIAC MRI DATA USING A LOCAL VARIANCE FILTER. Acta Polytechnica, 54(3), 214–220. https://doi.org/10.14311/AP.2014.54.0214

Issue

Vol. 54 No. 3 (2014)

Section

Articles