Infarct segmentation of the left ventricle using graph-cuts

Rashed Karim, Zhong Chen, Samantha Obom, Ying-Liang Ma, Prince Acheampong, Harminder Gill, Jaspal Gill, C. Aldo Rinaldi, Mark O'Neill, Reza Razavi, Tobias Schaeffter, Kawal S. Rhode

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)


Delayed-enhancement magnetic resonance imaging (DE-MRI) is an effective technique for imaging left ventricular (LV) infarct. Existing techniques for LV infarct segmentation are primarily threshold-based making them prone to high user variability. In this work, we propose a segmentation algorithm that can learn from training images and segment based on this training model. This is implemented as a Markov random field (MRF) based energy formulation solved using graph-cuts. A good agreement was found with the Full-Width-at-Half-Maximum (FWHM) technique.
Original languageEnglish
Title of host publicationStatistical Atlases and Computational Models of the Heart. Imaging and Modelling Challenges
Subtitle of host publicationSTACOM 2012
EditorsOscar Camara, Tommaso Mansi, Mihaela Pop, Kawal Rhode, Maxime Sermesant, Alistair Young
Place of PublicationBerlin, Heidelberg
Number of pages9
ISBN (Electronic)978-3-642-36961-2
ISBN (Print)978-3-642-36960-5
Publication statusPublished - Apr 2013

Publication series

NameLecture Notes in Computer Science

Cite this