A multi-scale variational neural network for accelerating motion-compensated whole-heart 3D coronary MR angiography

Fuin N., Bustin A., Kustner T., Öksüz İ., Clough J., King A. P., ...More

MAGNETIC RESONANCE IMAGING, vol.70, pp.155-167, 2020 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 70
  • Publication Date: 2020
  • Doi Number: 10.1016/j.mri.2020.04.007
  • Journal Name: MAGNETIC RESONANCE IMAGING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Biotechnology Research Abstracts, CAB Abstracts, EMBASE, INSPEC, MEDLINE, Veterinary Science Database
  • Page Numbers: pp.155-167
  • Keywords: Cardiac MRI, Fast imaging, Undersampling, Variational neural network, Coronary imaging, MAGNETIC-RESONANCE ANGIOGRAPHY, IMAGE-RECONSTRUCTION, SPARSE
  • Istanbul Technical University Affiliated: Yes

Abstract

Purpose: To enable fast reconstruction of undersampled motion-compensated whole-heart 3D coronary magnetic resonance angiography (CMRA) by learning a multi-scale variational neural network (MS-VNN) which allows the acquisition of high-quality 1.2 x 1.2 x 1.2 mm isotropic volumes in a short and predictable scan time.