The invention relates to a method of MR imaging of a body (10) of a patient positioned in an examination volume of an MR device (1). It is an object of the invention to provide a method that enables geometrically correct MR-only radiation therapy planning at minimum scan times. The method of the invention comprises the following steps: acquiring first MR imaging data representative of at least one region of the body (10); analyzing said first MR imaging data to delineate at least one anatomical structure within said body region; acquiring second MR imaging data of said body region using a multi-point Dixon sequence; deriving a B0 map from said second MR imaging data; analyzing said B0 map to determine at least one low fidelity region of said B0 map; performing B0 mapping to refine the B0 map using a multi-acquisition gradient echo sequence restricted to at least one region where said delineated anatomical structure and said low fidelity region overlap completely or partially; and correcting geometrical distortions in said first and/or second MR imaging data using the refined B0 map. Moreover, the invention relates to a MR device (1) for carrying out the method, and to a computer program to be executed on a MR device (1).

Object specific in-homogeneities in an MRI system are corrected. Prescan information available at the MR imaging system is determined. The prescan information includes at least object specific information of an object located in the MR imaging system from which an MR image is to be generated. The prescan information does not include a B1 map of the MRI system with the object being present in the MR imaging system. The prescan information is applied to a trained machine learning module provided at the MRI system. The trained machine learning module determines and generates shimming information as output. The shimming information is applied to a shimming module of the MR imaging system, wherein the shimming module uses the shimming information to generate a corrected magnetic field B0.

The disclosure relates to a method for generating a B.sub.0 map for a magnetic resonance examination of an examination subject, a magnetic resonance device, and a computer program product for executing the method. The method provides for the application of at least two preparatory RF pulses during a preparatory stage and at least one readout RF pulse during an acquisition stage. At least one stimulated echo signal is acquired after the readout RF pulse. A B.sub.0 map that shows the actual spatial distribution of the magnetic field strength of the main magnetic field is derived from the at least one acquired FID echo signal and the at least one acquired stimulated echo signal.

Techniques are disclosed to leverage the use of convolutional neural networks or similar machine learning algorithms to predict an underlying susceptibility distribution from MRI phase data, thereby solving the ill-posed inverse problem. These techniques include the use of Deep Quantitative Susceptibility “DeepQSM” mapping, which uses a large amount of simulated susceptibility distributions and computes phase distribution using a unique forward solution. These examples are then used to train a deep convolutional neuronal network to invert the ill-posed problem.

The present disclosure relates to a method for determining electrical properties, EP, of a target volume (708) in an imaged subject (718). The method comprises: performing a first training (201) of a deep neural network, DNN, using a first training dataset, the first training dataset comprising training B1 field maps and corresponding first EP maps, the first training resulting in a pre-trained DNN configured for generating EP maps from B1 field maps; performing a second training (203) of the pre-trained DNN using conditional generative adversarial networks, GAN, and a second training dataset, wherein the pre-trained DNN is a generator of the conditional GAN, the second training dataset comprising measured B1 maps and second EP maps, the second training resulting in a trained DNN; receiving (205) an input B1 field map of the target volume and generating an EP map of the input B1 field map using the trained DNN.

A method of analysing the magnitude of Magnetic Resonance Imaging (MRI) data is described. The method comprising: using the magnitude only of the multi-echo MRI data of images from the subject, where images are acquired at arbitrarily timed echoes including at least one echo time where water and fat are not substantially in-phase; fitting the magnitude of said multi-echo MRI data to a single signal model to produce a plurality of potential solutions for the relative signal contributions for each of the at least two species from the model, by using a plurality of different starting conditions to generate a particular cost function value for each of the plurality of starting conditions, where said cost function values are independent of a field map term for the MRI data; analysing said cost function values to calculate relative signal separation contribution for each species at each voxel of the images.

A shimming system for magnetic resonance imaging is provided, which includes: a multi-channel local shim coil unit configured to be installed on an inspection table of a magnetic resonance imaging system, where the multi-channel local shim coil unit includes a local multi-channel shim coil and a radio frequency receiving coil for receiving magnetic resonance signals, and the radio frequency receiving coil is placed inside the local multi-channel shim coil and separated by a distance from the local multi-channel shim coil; a computer control system configured to install and set software controlled by a DC power and calculate field maps and calculate optimization processes; a DC power system communicatively connected to the computer control system to control a value of current of each channel; and a housing having a semi-cylindrical configuration, where the local multi-channel shim coil is only distributed on a semi-cylindrical surface of the semi-cylindrical configuration of the housing.

During the delivery of thermal therapy, the measured temperature at each pixel in a cross-sectional temperature slice of a multi-pixel thermal image is compared to a maximum temperature limit. When the measured temperature of a pixel is higher than the maximum temperature limit for a predetermined number of consecutive cross-sectional temperature slices, the pixel is masked if the absolute value of the average difference between the measured temperature at the pixel and the measured temperatures at the pixel's neighbors is greater than a maximum temperature variation. The measured temperature of the masked pixel is ignored in subsequent cross-sectional temperature slices until the delivery of thermal therapy is complete.

A magnetic resonance imaging system is configured to be selectively operated in a default mode and an emulation mode. Execution of machine executable instructions by a processor of the magnetic resonance imaging system causes the magnetic resonance imaging system to receive a selection signal selecting the emulation mode. The magnetic resonance imaging system switches from the default mode to the emulation mode. The magnetic resonance imaging system is operated in the emulation mode using the set of emulation control parameters. The emulated magnetic resonance imaging data is acquired from the imaging zone of the magnetic resonance imaging system.

Multi-shot diffusion-weighted magnetic resonance imaging acquires multiple k-space segments of diffusion-weighted MRI data, estimates reconstructed multi-shot diffusion weighted images, and combines the estimated images to obtain a final reconstructed MRI image. The estimation of images iteratively calculates updated multi-shot images from the multiple k-space segments and current multi-shot images using a convex model without estimating motion-induced phase, constructs multiple locally low-rank spatial-shot matrices from the updated multi-shot images, and calculates current multi-shot images from spatial-shot matrices.