Deep learning to detect left ventricular structural abnormalities in chest X-rays.
Shreyas BhaveVictor RodriguezTimothy PoteruchaSimukayi MutasaDwight AberleKathleen M CapaccioneYibo ChenBelinda DsouzaShifali DumeerJonathan GoldsteinAaron HodesJay LebMatthew LungrenMitchell MillerDavid MonokyBenjamin NavotKapil WattamwarAnoop WattamwarKevin ClerkinDavid OuyangEuan AshleyVeli K TopkaraMathew MaurerAndrew J EinsteinNir UrielShunichi HommaAllan SchwartzDiego JaramilloAdler J PerottePierre A EliasPublished in: European heart journal (2024)
Deep learning analysis of CXRs can accurately detect the presence of certain structural abnormalities and may be useful in early identification of patients with LV hypertrophy and dilation. As a resource to promote further innovation, 71 589 CXRs with adjoining echocardiographic labels have been made publicly available.
Keyphrases
- deep learning
- left ventricular
- artificial intelligence
- convolutional neural network
- mitral valve
- left atrial
- heart failure
- machine learning
- hypertrophic cardiomyopathy
- acute myocardial infarction
- pulmonary hypertension
- cardiac resynchronization therapy
- aortic stenosis
- ejection fraction
- coronary artery disease
- aortic valve