An apparatus for controlling at least one gradient coil of a magnetic resonance imaging (MRI) system. The apparatus may include at least one computer hardware processor; and at least one computer-readable storage medium storing processor executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform a method. The method may include receiving information specifying at least one target pulse sequence; determining a corrected pulse sequence to control the at least one gradient coil based on the at least one target pulse sequence and a hysteresis model of induced magnetization in the MRI system caused by operation of the at least one gradient coil; and controlling, using the corrected gradient pulse sequence, the at least one gradient coil to generate one or more gradient pulses for imaging a patient.

Images are reconstructed from k-space data using a model-based image reconstruction that prospectively and simultaneously accounts for multiple non-idealities in accelerated single-shot-EPI acquisitions. In some implementations, nonlinear regularization (e.g., sparsity regularization) is also incorporated to mitigate noise amplification. The reconstructed images have reduced distortions and noise amplification effects relative to those images that are processed using conventional post-reconstruction techniques to correct for non-idealities.

Determining parameter values in image points of an examination object in an MR system by an MRF technique. Comparison signal waveforms, established using predetermined recording parameters, and each assigned to predetermined values of the parameters to be determined, are loaded. An image point time series of the examination object is acquired with an MRF recording method such that the acquired image point time series are comparable with the loaded comparison signal waveforms. A signal comparison of a section of the respective signal waveform of the acquired one image point time series is carried out with a corresponding section of loaded comparison signal waveforms to establish similarity values. The values of the parameters to be determined on the basis of the most similar comparison signal waveforms determined are determined, and then stored or output.

In a method for generation of a homogenization field suitable for homogenization of magnetic resonance data of an examination object, first magnetic resonance data from an examination region of the examination object is provided, a trained function is provided, a homogenization field is extracted by processing the first magnetic resonance data by way of the trained function, and the homogenization field is provided.

In a method for compensating stray magnetic fields in a magnetic resonance imaging system with two or more examination areas: a value for a predefined first magnetic field to be applied in a first examination area, in addition to a basic magnetic field is provided; information defining a predefined sequence control pulse to be applied in a second examination area is provided; a stray magnetic field in the second examination area resulting from application of the first magnetic field in the first examination area is determined; a compensated sequence control pulse for the second examination area is calculated from the predefined sequence control pulse and the determined stray magnetic field; and the compensated sequence control pulse is applied to the second examination area.

A method for designing gradient coils includes the following steps: a) defining an imaging volume as an ellipsoid; b) defining an elliptic-cylindrical surface enclosing the said ellipsoid; c) defining the current density at each point of the surface by a series of basis functions and corresponding coefficients expressed in elliptic cylindrical coordinates; d) describing the magnetic field generated at a generic point by the above defined current density integrated all over the said entire elliptic-cylindrical surface; e) determining the values of the coefficients of the basis functions by solving the inverse function for describing the magnetic field; f) generating a discrete winding patter of a gradient coil by using a stream function method from the continuous current density and by using a series of scattered contours of the stream function as the design of the winding patters according to a set total number of windings.

In one embodiment, an MRI apparatus includes a scanner and processing circuitry. The scanner includes at least two gradient coils. The processing circuitry is configured to cause the scanner to acquire k-space data for correction in a band-shaped two-dimensional k-space along a readout direction, or in a columnar three-dimensional k-space along a readout direction, while changing rotation angles, wherein each of the rotation angles corresponds to the readout direction, generate correction data for correcting an error due to a gradient magnetic field generated by the gradient coils, by using the acquired k-space data for correction, cause the scanner to acquire k-space data for reconstruction, based on a radial acquisition method, while correcting the gradient magnetic field by using the correction data, and generate an image by reconstructing the acquired k-space data for reconstruction.

The invention provides for a medical imaging system (100, 300). The execution of the machine executable instructions (110) causes a processor (102) to: receive (200) multiple diffusion weighted images (112) of a subject (318), wherein the multiple diffusion weighted images each have an assigned b-value, wherein the multiple diffusion weighted images each have an assigned diffusion weighting direction, wherein for a region of interest (309) there is at least one corresponding voxel (506) in each of the multiple diffusion weighted images; construct (202) a set of equations (114) for each of the at least one corresponding voxel, wherein the set of equations is constructed from an apparent diffusion equation for the assigned diffusion weighting direction of each of the multiple diffusion weighted images; solve (204) the set of equations for each voxel for the b.sub.0 value as an optimization; and construct (206) a image using the b.sub.0 value for each voxel.

For k-space trajectory infidelity correction, a model is machine trained to correct k-space measurements in k-space. K-space trajectory infidelity correction uses deep learning. Trajectory infidelity is corrected from a k-space point of view. Since the image artifacts arise from k-space acquisition distortion, a machine learning model is trained to correct in k-space, either changing values of k-space measurements or estimating the trajectory shifts in k-space.

In a method for generating an image data set and a reference image data set: a first raw data set is provided that is acquired with a MR system and that includes measurement signals at read-out points in k-space that lie on a first k-space trajectory; a second raw data set is provided that is acquired with the same MR system and at the same examination object at read-out points that lie on a second, different k-space trajectory that is different from the first k-space trajectory; image data sets are reconstructed from the first raw data set; a reference image data set is reconstructed from the second raw data set; the reference image data set is compared with each image dataset to generate respective similarity values; and an image data set is selected having a greatest similarity value.