TY  - JOUR
A1  - Dawood, Peter
A1  - Breuer, Felix
A1  - Stebani, Jannik
A1  - Burd, Paul
A1  - Homolya, István
A1  - Oberberger, Johannes
A1  - Jakob, Peter M.
A1  - Blaimer, Martin
T1  - Iterative training of robust k‐space interpolation networks for improved image reconstruction with limited scan specific training samples
JF  - Magnetic Resonance in Medicine
N2  - 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.
KW  - complex‐valued machine learning
KW  - data augmentation
KW  - deep learning
KW  - GRAPPA
KW  - parallel imaging
KW  - RAKI
Y1  - 2023
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-312306
VL  - 89
IS  - 2
SP  - 812
EP  - 827
ER  -