Login / Signup

Scan-specific artifact reduction in k-space (SPARK) neural networks synergize with physics-based reconstruction to accelerate MRI.

Yamin ArefeenOnur BekerJaejin ChoHeng YuElfar AdalsteinssonBerkin Bilgic
Published in: Magnetic resonance in medicine (2021)
SPARK synergizes with physics-based acquisition and reconstruction techniques to improve accelerated MRI by training scan-specific models to estimate and correct reconstruction errors in k-space.
Keyphrases
  • neural network
  • computed tomography
  • contrast enhanced
  • magnetic resonance imaging
  • diffusion weighted imaging
  • patient safety
  • emergency department
  • adverse drug
  • virtual reality