Login / Signup

Histopathological validation of semi-automated myocardial scar quantification techniques for dark-blood late gadolinium enhancement magnetic resonance imaging.

Hedwig M J M NiesSuzanne GommersGeertruida P BijvoetLuuk I B HeckmanFrits W PrinzenGaston VogelCaroline M Van De HeyningAmedeo ChiribiriJoachim E WildbergerCasper MihlRobert J Holtackers
Published in: European heart journal. Cardiovascular Imaging (2022)
The signal threshold vs. reference mean method with a threshold of 5 SDs demonstrated the most accurate semi-automated quantification of infarcted myocardium, without significant bias compared to histopathology, for both conventional bright-blood and novel dark-blood LGE.
Keyphrases
  • magnetic resonance imaging
  • machine learning
  • deep learning
  • high throughput
  • contrast enhanced
  • left ventricular
  • high resolution
  • atrial fibrillation
  • wound healing