Split‐slice training and hyperparameter tuning of RAKI networks for simultaneous multi‐slice reconstruction

Abstract

Simultaneous multi-slice acquisitions are essential for modern neuroimaging research, enabling high temporal resolution functional and high-resolution q-space sampling diffusion acquisitions. Recently, deep learning reconstruction techniques have been introduced for unaliasing these accelerated acquisitions, and robust artificial-neural-networks for k-space interpolation (RAKI) have shown promising capabilities. This study systematically examines the impacts of hyperparameter selections for RAKI networks, and introduces a novel technique for training data generation which is analogous to the split-slice formalism used in slice-GRAPPA. Methods: RAKI networks were developed with variable hyperparameters and with and without split-slice training data generation. Each network was trained and applied to five different datasets including acquisitions harmonized with Human Connectome Project lifespan protocol. Unaliasing performance was assessed through L1 errors computed between unaliased and calibration frequency-space data. Results: Split-slice training significantly improved network performance in nearly all hyperparameter configurations. Best unaliasing results were achieved with three layer RAKI networks using at least 64 convolutional filters with receptive fields of 7 voxels, 128 single-voxel filters in the penultimate RAKI layer, batch normalization, and no training dropout with the split-slice augmented training dataset. Networks trained without the split-slice technique showed symptoms of network over-fitting. Conclusions: Split-slice training for simultaneous multi-slice RAKI networks positively impacts network performance. Hyperparameter tuning of such reconstruction networks can lead to further improvements in unaliasing performance.

Residual RAKI: A hybrid linear and non-linear approach for scan-specific k-space deep learning

“…One of the advantages of RAKI-type methods have been its scan-specific nature, allowing them to be used in the absence of large training databases ( Arefeen et al, 2022 ; Hosseini et al, 2020b ; Kim et al, 2019 ; Nencka et al, 2021 ; Zhang et al, 2019a , 2018a ). Recently, several other studies have aimed to develop alternative scan-specific deep learning methods.…”

“…RAKI showed improvements in image quality and noise reduction compared to conventional PI methods using linear k-space interpolation. The scan-specific design allows RAKI to be employed when massive fully sampled training data are not available, such as coronary MRI ( Hosseini et al, 2020b ) and highly accelerated simultaneous multi-slice/multi-band (SMS/MB) MRI ( Nencka et al, 2021 ; Zhang et al, 2019a , 2018a ). It has also been applied to algorithms that rely on completion of locally low-rank k-space neighborhoods ( Kim et al, 2019 ), and in approaches that utilize the whole sub-sampled k-space for reconstruction ( Zhang et al, 2019d ).…”

Deep Learning and Its Application to Function Approximation for MR in Medicine: An Overview

“…Parallel imaging in k-space can be implemented as an ANN with three layers. 105,106 This method serves a similar purpose as nonlinear generalized autocalibrating partially parallel acquisition (GRAPPA), 107 which was an extension of GRAPPA 108 using a kernel method for nonlinear mapping. The ANN approximated a function that received undersampled multichannel k-space data as the input and produced full-sampled k-space data as the output.…”

A Review of Convolutional Neural Network Development in Computer Vision

“…At the same time, the function of neurons in the hidden layer is set to 0, which brings sparseness and makes it easy for the network to obtain sparse representation, reduce the number of parameters [50], and reduce overfitting. [51,52] Experiments show that ReLU has better performance than Sigmoid, and can be better to solve the gradient vanishing problem. The function formula of the ReLU is(6).…”