An MRI system coil insert 2 for use within a bore B of a main MRI system 1, the coil insert 2 comprising at least one gradient coil, for creating a spatially varying magnetic field along a respective axis and being arranged to be electrically driven at an ultrasonic frequency.

The present disclosure relates to a method comprising: providing a trained machine learning model. The trained machine learning model is configured for reconstructing images from input data. The method comprises: receiving (201) a multidimensional array comprising M dimensional acquired data; determining (205) a subset of values of at least one K selected dimension of the array; for each value of the subset determining (207) a M−K dimensional array comprising the acquired data corresponding to the value, resulting in a set of M−1 dimensional arrays; inputting (209) the set of M−K dimensional arrays to the trained machine learning model, and receive a reconstructed image from the trained machine learning model.

Disclosed herein is a method of training a neural network (214) to perform a SENSE magnetic resonance imaging reconstruction. The method comprises receiving (100) initial training data, wherein the initial training data comprises sets of initial training complex channel images each paired with a predetermined number of initial ground truth images. The method further comprises generating (102) additional training data by performing data augmentation on the initial training data such that the data augmentation comprises adding a distinct phase offset to each of the set of initial training complex channel images during generation of the sets of additional training complex channel images. The method further comprises inputting (104) the sets of additional training complex channel images into the neural network and receiving in response a predetermined number of output training images and performing deep learning using the output training images.

The disclosure relates to techniques for determining an acquisition order identified with an acquired magnetic resonance data set, which comprises a total number of slices, using a simultaneous multislice technique.

A method may include obtaining a plurality of imaging signals collected by applying a wave encoding gradient to a region of interest (ROI) of a subject. The method may also include obtaining a plurality of auxiliary signals associated with the ROI. The method may also include obtaining a point spread function corresponding to the wave encoding gradient. The method may also include determining, based on the plurality of auxiliary signals, temporal information relating to at least one temporal dimension of the ROI. The method may also include determining, based on the plurality of auxiliary signals, the plurality of imaging signals, and the point spread function, spatial information relating to at least one spatial dimension of the ROI. The method may also include generating at least one target image of the ROI based on the temporal information and the spatial information.

Method for operating an MR device to acquire MR data slices, wherein in a sequence section of an MR sequence, MR signals of at least two slices are measured simultaneously, and an acquisition order having an association of slices to respective sequence sections of a repetition sequence covering all slices of an associated concatenation is determined using an ordering rule. A crosstalk criterion is evaluated for the acquisition order by checking whether a first slice acquired in a last sequence section of the repetition sequence is directly adjacent to a second slice acquired in a first sequence section of the same repetition sequence. If the crosstalk criterion is fulfilled, the acquisition order is adapted according to an adaptation rule such that a larger temporal acquisition distance between the acquisition of the first and the second slices is provided.

The present disclosure is directed to systems and methods of multiphase pseudo-continuous arterial spin labeling.

A technology is provided for multi-component and/or multi-configuration imaging with coding, signal composition, signal model, structure model, structure model learning, decoding, reconstruction, performance prediction and performance enhancement. A magnetic resonance imaging example comprises acquiring signal samples in accordance with a coding scheme and a k-space sampling scheme, identifying a structure model in a data assembly formed using an extraction operation, and generating a result consistent with both the acquired signal samples and the identified structure model.

The present techniques relate to a techniques for performing cardiac perfusion imaging in order to detect perfusion defects in the myocardium. The present techniques relate to methods for performing cardiac perfusion imaging by performing at least two image acquisitions using different, customizable saturation delay times, which improves the ability to detect defects.

A magnetic resonance imaging apparatus according to an embodiment includes a static magnetic field magnet, a plurality of radio frequency coils, and processing circuitry. The static magnetic field magnet generates a static magnetic field having a magnetic field strength that changes spatially. The plurality of radio frequency coils receive a nuclear magnetic resonance signal generated from a subject by an influence of a radio frequency pulse transmitted to the subject, the subject being placed in the static magnetic field having a magnetic field strength that changes spatially. The processing circuitry controls each of the plurality of radio frequency coils to receive the nuclear magnetic resonance signal at each of a plurality of frequencies tuned according to at least a distribution of the static magnetic field.