Infarct segmentation of the left ventricle using graph-cuts

  • Authors:

  • 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

  • Affiliations:

  • Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom,Department of Cardiology, Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom;Department of Cardiology, Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom,Department of Cardiology, Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom,Department of Cardiology, Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom;Division of Imaging Sciences and Biomedical Engineering, King's College London, United Kingdom

  • Venue:
  • STACOM'12 Proceedings of the third international conference on Statistical Atlases and Computational Models of the Heart: imaging and modelling challenges
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

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.