Accelerated MRI by SPEED with generalized sampling schemes

Improving accelerated MRI by deep learning with sparsified complex data

PURPOSE

To obtain high-quality accelerated MR images with complex-valued reconstruction from undersampled k-space data.

METHODS

The MRI scans from human subjects were retrospectively undersampled with a regular pattern using skipped phase encoding, leading to ghosts in zero-filling reconstruction. A complex difference transform along the phase-encoding direction was applied in image domain to yield sparsified complex-valued edge maps. These sparse edge maps were used to train a complex-valued U-type convolutional neural network (SCU-Net) for deghosting. A k-space inverse filtering was performed on the predicted deghosted complex edge maps from SCU-Net to obtain final complex images. The SCU-Net was compared with other algorithms including zero-filling, GRAPPA, RAKI, finite difference complex U-type convolutional neural network (FDCU-Net), and CU-Net, both qualitatively and quantitatively, using such metrics as structural similarity index, peak SNR, and normalized mean square error.

RESULTS

The SCU-Net was found to be effective in deghosting aliased edge maps even at high acceleration factors. High-quality complex images were obtained by performing an inverse filtering on deghosted edge maps. The SCU-Net compared favorably with other algorithms.

CONCLUSION

Using sparsified complex data, SCU-Net offers higher reconstruction quality for regularly undersampled k-space data. The proposed method is especially useful for phase-sensitive MRI applications.

Improving image quality for skipped phase encoding and edge deghosting (SPEED) by exploiting several sparsifying transforms

PURPOSE

To improve the image quality of skipped phase encoding and edge deghosting (SPEED) by exploiting several sparsifying transforms.

METHODS

The SPEED technique uses a skipped phase encoding (PE) step to accelerate MRI scan. Previously, a difference transform (DT) along PE direction is used to obtain sparse ghosted-edge maps, which were modeled by a double layer ghost model and was then deghosted by a least square error solution. In this work, it is hypothesized that enhanced sparsity, and thus improved image quality may be achievable with other sparsifying transforms, including discrete wavelet transform (DWT), discrete cosine transform (DCT), DWT combined with DT, and DCT combined with DT.

RESULTS

For images of human subjects, SPEED with DWT or DCT can yield higher image quality than DT only, especially for those images with low contrast. Reconstruction error can be further reduced if DWT or DCT are combined with DT.

CONCLUSION

Image sparsity can be enhanced with more advanced transforms, leading to higher reconstruction quality in SPEED imaging that is desirable for practical MRI applications.