Abstract: A magnetic resonance (MR) imaging (MRI) system (100, 1500), includes at least one controller (110, 1510) configured to: perform a multi-shot image acquisition process to acquire MR information for at least one multi-shot image set; train a convolution kernel including data on at least a portion of the MR information obtained without the use of the gradient or by using a self-training process. The convolution kernel includes convolution data. The MR information obtained with the use of a gradient for at least two of the image shots of the at least one multi-shot image set is iteratively convolved with the trained convolution kernel. The synthetic k-space data for the at least two image shots of the at least one multi-shot image set is projected into image space. The projected synthetic k-space data that are projected into the image space to form image information.

Abstract: Reduction of artifacts caused by inter-shot motion in multi-shot MRI (e.g. DWI). To this end, the invention teaches a magnetic resonance (MR) imaging (MRI) system (100, 1500), including at least one controller (110, 1510) configured to: perform a multi-shot image acquisition process to acquire MR information for at least one multi-shot image set; train a convolution kernel comprising data on at least a portion of the MR information obtained without the use of the gradient or by using a self-training process, the convolution kernel including convolution data; iteratively convolve the MR information obtained with the use of a gradient for at least two of the image shots of the at least one multi-shot image set with the trained convolution kernel; project the synthetic k-space data for the at least two image shots of the at least one multi-shot image set into image space; and average the projected synthetic k-space data that are projected into the image space to form image information.

Abstract: The present invention proposes a fast GeneRalized Autocalibrating Partially Parallel Acquisition (GRAPPA) image reconstruction algorithm for magnetic resonance imaging. The algorithm simplifies data fitting and channel merging in the process of reconstruction into a one-step linear calculation. Parameters needed to perform the linear calculation step can be pre-calculated and stored, thereby greatly increasing the image reconstruction speed and solving the problem of the relatively long image reconstruction time needed by prior art GRAPPA algorithms. Also, the algorithm can employ a weighting matrix to conveniently compare signal-to-noise ratio losses of images brought by different types of reconstruction methods in image domain and frequency domain.

Abstract: In a K-space SENSitivity Encoding (KSENSE) magnetic resonance parallel imaging method the sensitivity distribution of MR reception coils; is calculated and based on the sensitivity of the coils, signals from the respective coil merging channels are merged. The merged data are used to perform k-space data fitting and optimal fitting parameters are found. The fitting parameters are used to remove artifacts in the reconstructed image.

Abstract: In a K-space SENSitivity Encoding (KSENSE) magnetic resonance parallel imaging method the sensitivity distribution of MR reception coils; is calculated and based on the sensitivity of the coils, signals from the respective coil merging channels are merged. The merged data are used to perform k-space data fitting and optimal fitting parameters are found. The fitting parameters are used to remove artifacts in the reconstructed image.

Abstract: The present invention proposes a fast GeneRalized Autocalibrating Partially Parallel Acquisition (GRAPPA) image reconstruction algorithm for magnetic resonance imaging. The algorithm simplifies data fitting and channel merging in the process of reconstruction into a one-step linear calculation. Parameters needed to perform the linear calculation step can be pre-calculated and stored, thereby greatly increasing the image reconstruction speed and solving the problem of the relatively long image reconstruction time needed by prior art GRAPPA algorithms. Also, the algorithm can employ a weighting matrix to conveniently compare signal-to-noise ratio losses of images brought by different types of reconstruction methods in image domain and frequency domain.