Refine
Has Fulltext
- yes (14)
Is part of the Bibliography
- yes (14)
Document Type
- Journal article (14)
Language
- English (14)
Keywords
- MRI (3)
- Magnetic resonance imaging (3)
- Oxygen (2)
- Pulmonary imaging (2)
- magnetic resonance imaging (2)
- Aorta (1)
- Asthma (1)
- Atherosclerosis (1)
- Brassica napus (1)
- Breathing (1)
- C-13-metabolic flux analysis (1)
- CSI (1)
- Chronic obstrusive pulmonary disease (1)
- Cystic fibrosis (1)
- Diagnostic medicine (1)
- EP Procedures (1)
- Functional magnetic resonance imaging (1)
- GRAPPA (1)
- H-1-NMR spectroscopy (1)
- Hypertonic (1)
- Lipid (1)
- MR guidance (1)
- MRI criteria (1)
- Measurement (1)
- Medicine (1)
- Medizin (1)
- Mouse models (1)
- NMR (1)
- NMR-spectroscopy (1)
- Physics (1)
- Plants (1)
- Protons (1)
- Pulmonary function (1)
- Quantum chronodynamics (1)
- RAKI (1)
- RNA-SEQ (1)
- Seeds (1)
- Stiffness (1)
- Systole (1)
- Time measurement (1)
- ablation (1)
- accumulation (1)
- aorta (1)
- blood (1)
- body weight (1)
- brain images (1)
- calcium fluoride nanoparticles (1)
- camelina-sativa (1)
- cardiac ventricles (1)
- catheter tip (1)
- central carbon metabolism (1)
- central metabolism (1)
- children (1)
- clinically isolated syndromes (1)
- coconut cocos-nucifera (1)
- complex‐valued machine learning (1)
- contact force (1)
- data augmentation (1)
- deep learning (1)
- developing oilseeds (1)
- developmental signaling (1)
- diagnosis (1)
- disease (1)
- embryo (1)
- emulsions (1)
- field (1)
- fluorine (1)
- flux balance analysis (1)
- gene-expression data (1)
- guidelines (1)
- heart rate (1)
- heterotrophic arabidopsis cells (1)
- high-throughput (1)
- in vivo imaging (1)
- infants (1)
- infarction (1)
- infection (1)
- lesion size (1)
- lipid biosynthesis (1)
- macrophages (1)
- magnetic resonance imaging (MRI) (1)
- maize kernels (1)
- metabolism (1)
- model (1)
- mouse (1)
- multifunctional nanoparticles (1)
- multimodal imaging (1)
- myocardial infarction (1)
- non-triggered (1)
- oil storage (1)
- oilseeds (1)
- optimization (1)
- parallel imaging (1)
- phase-contrast CMR (1)
- photoluminescence (1)
- prefrontal cortex (1)
- pulse-wave velocity (1)
- radial (1)
- radiofrequency ablation (1)
- registration (1)
- retrospective (1)
- robust (1)
- saccharomyces cerevisiae (1)
- safety (1)
- seed (1)
- seeds (1)
- self-gating (1)
- surgical and invasive medical procedures (1)
- targeted metabolite profiling (1)
- temperature (1)
- tissue (1)
- vascular surgery (1)
- ventilation (1)
- wires (1)
Institute
Sonstige beteiligte Institutionen
To evaluate an iterative learning approach for enhanced performance of robust artificial‐neural‐networks for k‐space interpolation (RAKI), when only a limited amount of training data (auto‐calibration signals [ACS]) are available for accelerated standard 2D imaging.
Methods
In a first step, the RAKI model was tailored for the case of limited training data amount. In the iterative learning approach (termed iterative RAKI [iRAKI]), the tailored RAKI model is initially trained using original and augmented ACS obtained from a linear parallel imaging reconstruction. Subsequently, the RAKI convolution filters are refined iteratively using original and augmented ACS extracted from the previous RAKI reconstruction. Evaluation was carried out on 200 retrospectively undersampled in vivo datasets from the fastMRI neuro database with different contrast settings.
Results
For limited training data (18 and 22 ACS lines for R = 4 and R = 5, respectively), iRAKI outperforms standard RAKI by reducing residual artifacts and yields better noise suppression when compared to standard parallel imaging, underlined by quantitative reconstruction quality metrics. Additionally, iRAKI shows better performance than both GRAPPA and standard RAKI in case of pre‐scan calibration with varying contrast between training‐ and undersampled data.
Conclusion
RAKI benefits from the iterative learning approach, which preserves the noise suppression feature, but requires less original training data for the accurate reconstruction of standard 2D images thereby improving net acceleration.