To acquire a higher-quality image with high-speed imaging in an MRI apparatus or the like to which compressed sensing is applied. Included are: an observation unit that does not observe, when any one of two points being point-symmetric with respect to the origin is observed, the other point in observation of a high frequency component of a K-space of the MRI apparatus; and a reconstruction unit that reconstructs an image from a component of the K-space observed by the observation unit. The reconstruction process of the reconstruction unit includes an image correction process based on an observation pattern of the observation unit.

A method may include acquiring MR signals by an MR scanner and generating image data in a k-space according to the MR signals. The method may also include classifying the image data into a plurality of phases. Each of the plurality of phases may have a first count of spokes. A spoke may be defined by a trajectory for filling the k-space. The method may also include classifying the plurality of phases of the image data into a plurality of groups and determining reference images based on the plurality of groups. Each of the reference images may correspond to the at least one of the phases of the image data. The method may further include reconstructing an image sequence based on the reference images and the plurality of phases of the image data.

An efficient method of scanning is provided that may be used for treatment, analysis, inspection and testing physical objects and spaces. High precision, resolution and throughput of scanning are achieved by employing a dual motion of probing devices and scanned objects. A probing device spins with high speed about an axis of spinning directed towards a scanned object. Concurrently, the spinning axis is set in a relatively slow motion with respect to the scanned object. Both the spinning of the probing and the motion of the spin axis are implemented in a controlled and predetermined way to achieve objectives of scanning. Accordingly, arbitrary large and shaped objects may be efficiently scanned with high precision and throughput.

A magnetic resonance device (1), having a main magnet unit (2) with a cylindrical patient aperture (3), wherein at least one radial gradient coil (9) is provided in the patient aperture (3) which generates a gradient field having, at least in regions, a radial gradient in relation to its own central axis parallel to the longitudinal axis of the patient aperture (3), the radial gradient coil (9) being embodied as a cylinder coil.

Techniques are disclosed for acquiring at least two measurement datasets, each consisting of measurement data. The two measurement datasets are recorded at points in time at which spins of a first spin species present in the examination object have different phase positions from spins of a second spin species present in the examination object. Moreover, the two measurement datasets are recorded in each case while switching readout gradients of different polarity, and thus the desired measurement datasets may be recorded faster than conventional approaches.

Suppressing artifacts in MRI image acquisition data includes alternatives to phase cycling by using a Convolutional Neural Network to suppress the artifact-generating echos. A U-NET CNN is trained using phase-cycled artifact-free images for ground truth comparison with received displacement encoded stimulated echo (DENSE) images. The DENSE images include data from a single acquisition with both stimulated (STE) and T1-relaxation echoes. The systems and methods of this disclosure are explained as generating artifact-free images in the ultimate output and avoiding the additional data acquisition needed for phase cycling and shortens the scan time in DENSE MRI.

A variable density Cartesian sampling method that allows retrospective adjustment of temporal resolution, providing added flexibility for real-time applications where optimal temporal resolution may not be known in advance. The methods provide for a computationally efficient sampling methods where a first step includes producing a uniformly random sampling pattern using a golden ratio on a grid, and the second step is applying a nonlinear stretching operation to create a variable density sampling pattern. Diagnostic quality images may be recovered at different temporal resolutions.

In a method and system for the generation of measurement data required k-space is read out in the readout direction in k-space rows such that at least a first k-space row of the k-space rows does not cover the k-space to be read out in the readout direction in full and at least a second k-space row of the k-space rows covers the k-space to be read out in locations in the readout direction at which the first k-space row does not cover the k-space to be read out. Measurement data that is missing in the k-space is completed in this way on the basis of recorded echo signals stored as measurement data.

A method for motion correction of Magnetic Resonance (MR) images is provided. The method includes acquiring a k-space dataset for an object using an MR scanner, detecting or identifying corrupted k-space data from the acquired k-space dataset, extracting the corrupted k-space data from the acquired k-space dataset, recovering the corrupted k-space data, combining uncorrupted k-space data of the acquired k-space dataset with the recovered k-space data to form a full k-space dataset, and reconstructing an image for the object based on the full k-space dataset. A magnetic resonance imaging system for correcting corrupted k-space data of an entire k-space dataset is also provided.

An exemplary system, method, and computer-accessible medium for generating a Cartesian equivalent image(s) of a portion(s) of a patient(s), can include, for example, receiving non-Cartesian sample information based on a magnetic resonance imaging (MRI) procedure of the portion(s) of the patient(s). and automatically generating the Cartesian equivalent image(s) from the non-Cartesian sample information using a deep learning procedure(s). The non-Cartesian sample information can be Fourier domain information. The non-Cartesian sample information can be undersampled non-Cartesian sample information. The MRI procedure can include an ultra-short echo time (UTE) pulse sequence The UTE pulse sequence can include a delay(s) and a spoiling gradient. The Cartesian equivalent image(s) can be generated by reconstructing the Cartesian equivalent image(s). The Cartesian equivalent image(s) can be reconstructed using a sampling density compensation with a tapering of over a particular percentage of a radius of a k-space, where the particular percentage can be about 50%.