Login / Signup

Comparison of left ventricular strains and torsion derived from feature tracking and DENSE CMR.

Gregory J WehnerLinyuan JingChristopher M HaggertyJonathan D SueverJing ChenSean M HamletJared A FeindtW Dimitri MojsejenkoMark A FogelBrandon K Fornwalt
Published in: Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance (2018)
Compared to DENSE as a reference standard, feature tracking was inaccurate for quantification of apical and basal LV circumferential strains, longitudinal strain, torsion, and dyssynchrony. Feature tracking was only accurate for quantification of mid LV circumferential strain. Moreover, feature tracking is unnecessary for quantification of whole-slice strains (e.g. base, apex), since simplified processing of only ED and ES contours yields very similar results to those derived from feature tracking. Current feature tracking technology therefore has limited utility for quantification of cardiac mechanics.
Keyphrases
  • machine learning
  • left ventricular
  • deep learning
  • escherichia coli
  • emergency department
  • neural network
  • mitral valve
  • coronary artery disease
  • left atrial