Disclosed herein is a medical system (100, 300) comprising a memory (110) storing machine executable instructions (120) and an image generating neural network (122). The image generating neural network is configured for outputting synthetic magnetic resonance image data (128) in response to receiving reference magnetic resonance image data (126) as input. The synthetic magnetic resonance image data is a simulation of magnetic resonance image data acquired according to a first configuration of a magnetic resonance imaging system when the reference magnetic resonance image data is acquired according to a second configuration of the magnetic resonance imaging system. Execution of the machine executable instructions causes a computational system (106) to: receive (200) measured k-space data (124) acquired according to the first configuration of the magnetic resonance imaging system; receive (202) the reference magnetic resonance image data; receive (204) the synthetic magnetic resonance image data by inputting the reference magnetic resonance image data into the image generating neural network; and reconstruct (206) corrected magnetic resonance image data (132) from the measured k-space data and the synthetic magnetic resonance image data.

Techniques are provided for determining a magnetic resonance imaging (MRI) image using multiple measurement data sets that form a propeller pattern. Partial MRI images are reconstructed for each measurement data set. The partial MRI images are then combined.

A magnetic resonance imaging method, a magnetic resonance imaging system, and a computer-readable storage medium are provided. The magnetic resonance imaging method comprises: acquiring a plurality of portions of a k-space by using a plurality of sets of imaging sequences to obtain a plurality of k-space data sets, each set of imaging sequences comprising a pre-dephasing gradient pulse and a plurality of phase encoding gradients applied after the pre-dephasing gradient pulse, wherein the pre-dephasing gradient pulses in the plurality of sets of imaging sequences have a standard area difference in order when sorted according to the sizes of area values, and the standard area difference is 2/N of the area of any phase encoding gradient, where N is the number of sets of the plurality of sets of imaging sequences; respectively reconstructing a magnetic resonance image from each of the plurality of k-space data sets; and processing the plurality of k-space data sets to obtain a magnetic resonance image.

A magnetic resonance imaging system and method, and a computer-readable storage medium are provided. The magnetic resonance imaging method includes: acquiring a plurality of k-space data sets by using a plurality of imaging sequences, each imaging sequence comprising a pre-phase-dispersion gradient pulse and a plurality of phase encoding gradients applied after the pre-phase-dispersion gradient pulse, wherein the pre-phase-dispersion gradient pulses of the plurality of imaging sequences have a standard area difference therebetween when ordered according to area values; respectively reconstructing magnetic resonance images from the respective k-space data sets; and averaging amplitudes of the magnetic resonance images to generate a magnetic resonance image of an average amplitude.

In order to remove restriction on the number of additions in imaging for offsetting errors caused by hardware performance and/or signal fluctuation caused by a hardware control method by inverting the polarity of predetermined hardware output, the present invention executes a first imaging sequence and a second imaging sequence in which the polarity of a predetermined gradient magnetic field pulse in the first imaging sequence was inverted, adds data acquired in each imaging sequence, and then acquires addition images. In order to perform the addition, each coefficient is determined so that the total of coefficients by which first data acquired in the first imaging sequence are to be multiplied is equal to the total of coefficients by which second data acquired in the second imaging sequence are to be multiplied.

The invention relates to a method of MR imaging of an object (10) positioned in an examination volume of a MR device (1). An object of the invention is to provide a method that enables EPI imaging with improved distortion correction. The method of the invention comprises the steps of: acquiring reference MR signal data from the object (10) using a multi-point Dixon method; deriving a B.sub.0 map from the reference MR signal data; acquiring a series of imaging MR signal data sets from the object (10), wherein an instance of an echo planar imaging sequence is used for acquisition of each imaging MR signal data set; and reconstructing an MR image from each imaging MR signal data set, wherein geometric distortions in each MR image are corrected using the B.sub.0 map. Moreover, the invention relates to a MR device (1) for carrying out the method, and to a computer program to be run on a MR device (1).

Described here are systems and methods for correcting magnetic resonance data for off-resonance effects arising from the use of a multi-echo echo planar imaging (“EPI”) pulse sequence. Reference data are acquired, from which phase maps are computed in a distorted coordinate space associated with geometric distortions associated with the multi-echo EPI acquisition. Images reconstructed from the magnetic resonance data are demodulated using the distorted phase maps to produce distortion free images of the subject. Advantageously, the systems and methods can be used to reconstruct distortion free images from magnetic resonance data that is otherwise prone to image distortions from off-resonance errors, including data acquired from hyperpolarized nuclear spin species such as hyperpolarized carbon-13.

A method of reconstructing a magnetic resonance image includes receiving echo planar imaging (EPI) data, acquiring an even scan line image and an odd scan line image from k-space data of the EPI data, and reconstructing missing portions of the even scan line image and the odd scan line image.

A method and imaging system is provided that can control a magnetic gradient system and an RF system of an MRI system according to a calibration pulse sequence to acquire positive readout gradient (RO+) data and negative readout gradient (RO−) data. The RO+ data and the RQ− data are assembled to form complete image data sets for the RO+ data and the RQ™ data and the RO+ data and the RO− data are combined to generate the calibration data that is ghost-corrected, substantially free of ghost artifacts, or having reduced ghost artifacts compared to traditionally-acquired calibration data. Reconstruction coefficients are derived from the calibration data. The magnetic gradient system and the RF system are controlled according to an imaging pulse sequence to acquire image data and the image data is reconstructed into an image of the subject using the reconstruction coefficients.

A magnetic resonance imaging (MRI) apparatus for obtaining a magnetic resonance (MR) image, based on a multi-echo sequence, and a method of the MRI apparatus are provided. The MRI apparatus includes a data obtainer configured to obtain first echo data, based on an echo that is generated at a first echo time, and obtain second echo data, based on an echo that is generated at a second echo time later than the first echo time, the first echo data including a part overlapping a part included in the second echo data in a k-space. The MRI apparatus further includes an image processor configured to reconstruct the MR image, based on the first echo data and the second echo data.