Novel near-infrared spectroscopy-intravascular ultrasound-based deep-learning methodology for accurate coronary computed tomography plaque quantification and characterization.
Anantharaman RamasamyHessam SokootiXiaotong ZhangEvangelia TzoroviliRetesh BajajPieter KitslaarAlexander BroersenRajiv AmerseyAjay JainMick OzkorJohan H C ReiberJouke DijkstraPatrick W SerruysJames C MoonAnthony MathurAndreas BaumbachRyo ToriiFrancesca PuglieseChristos V BourantasPublished in: European heart journal open (2023)
The DL methodology developed for CCTA analysis from co-registered NIRS-IVUS and CCTA data enables rapid and accurate assessment of lesion morphology and is superior to expert analysts (Clinicaltrials.gov: NCT03556644).
Keyphrases
- computed tomography
- deep learning
- coronary artery
- coronary artery disease
- magnetic resonance imaging
- high resolution
- positron emission tomography
- electronic health record
- big data
- artificial intelligence
- clinical practice
- heart failure
- contrast enhanced
- magnetic resonance
- pet ct
- image quality
- dual energy
- loop mediated isothermal amplification
- sensitive detection