Search

Purpose: The aim of this work is to introduce a single model-based deep network that can provide high-quality reconstructions from undersampled parallel MRI data acquired with multiple sequences, acquisition settings and field strengths. Methods: A single unrolled architecture, which offers good reconstructions for multiple acquisition settings, is introduced. The proposed scheme adapts the model to each setting by scaling the CNN features and the regularization parameter with appropriate weights. The scaling weights and regularization parameter are derived using a multi-layer perceptron model from conditional vectors, which represents the specific acquisition setting. The perceptron parameters and the CNN weights are jointly trained using data from multiple acquisition settings, including differences in field strengths, acceleration, and contrasts. The conditional network is validated using datasets acquired with different acquisition settings. Results: The comparison of the adaptive framework, which trains a single model using the data from all the settings, shows that it can offer consistently improved performance for each acquisition condition. The comparison of the proposed scheme with networks that are trained independently for each acquisition setting shows that it requires less training data per acquisition setting to offer good performance. Conclusion: The Ada-MoDL framework enables the use of a single model-based unrolled network for multiple acquisition settings. In addition to eliminating the need to train and store multiple networks for different acquisition settings, this approach reduces the training data needed for each acquisition setting.

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.

Simultaneous multi-slice (SMS) imaging accelerates MRI data acquisition by exciting multiple image slices simultaneously. Overlapping slices are then separated using a mathematical model. Several parameters used in SMS reconstruction impact the quality of final images. Therefore, finding an optimal set of reconstruction parameters is critical to ensure that SMS acceleration does not significantly degrade resulting image quality. Gradient-echo echo planar imaging (EPI) data were acquired with a range of SMS acceleration factors from volunteers. Images were collected using two head coils (a 48-channel array and a smaller 32-channel array). Data from these coils were reconstructed offline using a range of coil compression factors and reconstruction kernel parameters. A hybrid space (ky-x), externally-calibrated coil-by-coil slice unaliasing approach was used for image reconstruction. The resulting SMS images were compared with identical EPI data acquired without SMS. A functional MRI (fMRI) experiment was also performed and group analysis results were compared between data sets reconstructed with different coil compression levels. The 32-channel coil with smaller dimensions outperformed the larger 48-channel coil in our experiments. Generally, a large calibration region and small kernel sizes in ky direction improved image quality. Use of regularization in the kernel fitting procedure had a notable impact. With optimal selection of other hyperparameters in the hybrid space SMS unaliasing algorithm, coil compression caused small reduction in quality in SMS accelerated images. Similarly, group analysis of fMRI results did not show a significant influence of coil compression on resulting image quality. Hyperparameters used in SMS reconstruction need to be fine-tuned once the experimental factors such as the RF receive coil and SMS factor have been determined., Comment: 22 pages, 7 figures