Login / Signup

Inter-observer variability of expert-derived morphologic risk predictors in aortic dissection.

Martin J WilleminkDomenico MastrodicasaMohammad H MadaniMarina CodariLeonid L ChepelevGabriel MistelbauerKate HannemanMaral OuzounianDaniel OcazionezRana O AfifiJoan M LacomisLuigi LovatoDavide PaciniGianluca FolesaniRicarda HinzpeterHatem AlkadhiArthur E StillmanAnna M SailerValery L TurnerVirginia HinostrozaKathrin BäumlerAnne S ChinNicholas S BurrisD Craig MillerMichael P FischbeinDominik Fleischmann
Published in: European radiology (2022)
• Clinical fashion manual measurements of aortic CTA imaging features showed poor inter-observer reproducibility. • A standardized workflow with standardized training resulted in substantial improvements with excellent inter-observer reproducibility. • Robust ground truth labels obtained manually with excellent inter-observer reproducibility are key to develop reliable machine learning models.
Keyphrases
  • aortic valve
  • aortic dissection
  • machine learning
  • high resolution
  • heart failure
  • artificial intelligence
  • mass spectrometry
  • coronary artery
  • left ventricular
  • atrial fibrillation
  • fluorescence imaging