Login / Signup

Accelerated two-dimensional phase-contrast for cardiovascular MRI using deep learning-based reconstruction with complex difference estimation.

Julio A OscanoaMatthew J MiddioneAli B SyedChristopher M SandinoShreyas S VasanawalaDaniel B Ennis
Published in: Magnetic resonance in medicine (2022)
In a retrospective evaluation, CD-DL produced quantitative measurements of 2D PC-MRI peak velocity and total flow with <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mo>≤</mml:mo> <mml:mn>5</mml:mn> <mml:mi>%</mml:mi></mml:mrow> <mml:annotation>$$ \le 5\% $$</mml:annotation></mml:semantics> </mml:math> error in both accuracy and precision for up to 9 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mo>×</mml:mo></mml:mrow> <mml:annotation>$$ \times $$</mml:annotation></mml:semantics> </mml:math> acceleration. Clinical feasibility was demonstrated using a prospective clinical deployment of our 8 <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:semantics><mml:mrow><mml:mo>×</mml:mo></mml:mrow> <mml:annotation>$$ \times $$</mml:annotation></mml:semantics> </mml:math> undersampled acquisition and CD-DL reconstruction in a cohort of pediatric patients.
Keyphrases
  • magnetic resonance imaging
  • machine learning
  • high resolution
  • convolutional neural network