Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling.
Seyed Amir Hossein HosseiniChi ZhangSebastian WeingärtnerSteen MoellerMatthias StuberKamil UgurbilMehmet AkcakayaPublished in: PloS one (2020)
sRAKI is a database-free neural network-based reconstruction technique that may further accelerate coronary MRI with arbitrary undersampling patterns, while improving noise resilience over linear parallel imaging and image sharpness over l1 regularization techniques.
Keyphrases
- neural network
- contrast enhanced
- coronary artery disease
- coronary artery
- magnetic resonance imaging
- diffusion weighted imaging
- high resolution
- adverse drug
- climate change
- deep learning
- air pollution
- computed tomography
- social support
- magnetic resonance
- heart failure
- emergency department
- aortic stenosis
- depressive symptoms
- atrial fibrillation
- transcatheter aortic valve replacement