Split Slice Training Augmentation and Hyperparameter Tuning of RAKI Networks for Simultaneous Multi-Slice Reconstruction

TL;DR

This paper explores split-slice augmentation and hyperparameter tuning to enhance the performance of RAKI networks in simultaneous multi-slice MRI reconstruction, aiming to improve unaliasing accuracy.

Contribution

It introduces split-slice augmentation and systematic hyperparameter tuning methods specifically for RAKI networks, advancing MRI reconstruction techniques.

Findings

Split-slice augmentation improves RAKI network performance.

Hyperparameter tuning further enhances unaliasing accuracy.

Combined methods lead to better multi-slice reconstruction results.

Abstract

Split-slice augmentation for simultaneous multi-slice RAKI networks positively impacts network performance. Hyperparameter tuning of such reconstruction networks can lead to further improvements in unaliasing performance.