Machine learning for the automatic assessment of aortic rotational flow and wall shear stress from 4D flow cardiac magnetic resonance imaging.
Juan Garrido-OliverJordina AvilesMarcos Mejía CórdovaLydia Dux-SantoyAroa Ruiz-MuñozGisela Teixido-TuraGonzalo D Maso TalouXabier Morales FerezGuillermo JiménezArturo EvangelistaIgnacio Ferreira-GonzálezJose Rodriguez-PalomaresOscar CamaraAndrea GualaPublished in: European radiology (2022)
• 4D flow CMR allows for unparalleled aortic blood flow analysis but requires aortic segmentation and anatomical landmark identification, which are time-consuming, limiting 4D flow CMR widespread use. • A fully automatic machine learning pipeline for aortic 4D flow CMR analysis was trained with data of 323 patients and tested in 81 patients, ensuring a balanced distribution of aneurysm aetiologies. • Automatic assessment of complex flow characteristics such as rotational flow and wall shear stress showed good-to-excellent agreement with manual quantification.
Keyphrases
- machine learning
- deep learning
- end stage renal disease
- magnetic resonance imaging
- aortic valve
- left ventricular
- blood flow
- ejection fraction
- newly diagnosed
- chronic kidney disease
- pulmonary artery
- big data
- artificial intelligence
- prognostic factors
- computed tomography
- heart failure
- peritoneal dialysis
- magnetic resonance
- convolutional neural network
- pulmonary arterial hypertension
- patient reported
- diffusion weighted imaging