Provided are a method of obtaining a water-fat separation image and a magnetic resonance imaging (MRI) apparatus including a controller configured to obtain first partial k-space data, second partial k-space data, and third partial k-space data, respectively based on a first partial echo signal, a second partial echo signal, and a third partial echo signal, which are magnetic resonance signals corresponding to a plurality of echo times with respect to an object, obtain first reconstruction image data, second reconstruction image data, and third reconstruction image data with respect to the object, respectively based on the first partial k-space data, the second partial k-space data, and the third partial k-space data, and obtain first water image data, first fat image data, and first phase image data of the object, respectively based on the first reconstruction image data, the second reconstruction image data, and the third reconstruction image data, by using a Dixon technique.

A method for magnetic resonance imaging (MRI) may include cause, based on a pulse sequence, a magnetic resonance (MR) scanner to perform a scan on an object. The pulse sequence may include a steady-state sequence and an acquisition sequence that is different from the steady-state sequence. The steady-state sequence may correspond to a steady-state phase of the scan in which no MR data is acquired. The acquisition sequence may correspond to an acquisition phase of the scan in which MR data of the object is acquired. The method may also include generating one or more images of the object based on the MR data.

Systems and methods provide accelerated MR thermometry utilizing prior knowledge about the images to be reconstructed from incomplete k-space data, thereby facilitating accurate reconstruction. In various embodiments, missing data is computationally estimated using a machine learning algorithm such as a neural network, and an image is generated based on iteratively updated estimated missing information.

An exemplary system, method and computer-accessible medium for characterizing a microstructure of a prostate of a patient can be provided, which can include, for example, generating a magnetic resonance (MR) radiofrequency (RF) pulse(s) by varying (i) a diffusion time, (ii) a diffusion gradient direction, (iii) a diffusion gradient pulse width, or (iv) a diffusion gradient pulse shape, applying the MR RF pulse(s) to the prostate of the patient, receiving a resultant MR signal from the prostate of the patient that can be based on the MR RF pulse(s), determining information regarding a plurality of compartments for the prostate from the resultant MR signal by varying an echo time or a mixing time, and characterizing the microstructure for each of the compartments by applying a microstructural model(s) to each of the compartments.

Embodiments of the present invention provide a magnetic resonance imaging system and a method for obtaining magnetic resonance imaging data. The method comprises: applying a fat suppression pulse before the start of any repetition time of an imaging sequence; performing a plurality of echoes in the repetition time, wherein first image data when water and fat are in phase and second image data when water and fat are out of phase are obtained during each echo of the plurality of echoes; and obtaining fat-suppressed image data according to the first image data and the second image data.

A method for correcting magnetic resonance (MR) object movements includes performing a recording of an MR object with multiple echo trains. k-space data pertaining to an echo train regarded as impaired by an MR object movement is corrected by linking the k-space data to corresponding k-space data reconstructed from k-space data of other echo trains by a PPA method.

Methods and apparatus for operating a low-field magnetic resonance imaging (MRI) system to perform diffusion weighted imaging, the low-field MRI system including a plurality of magnetics components including a B.sub.0 magnet configured to produce a low-field main magnetic field B.sub.0, at least one gradient coil configured to, when operated, provide spatial encoding of emitted magnetic resonance signals, and at least one radio frequency (RF) component configured to acquire, when operated, the emitted magnetic resonance signals. The method comprises controlling one or more of the plurality of magnetics components in accordance with at least one pulse sequence having a diffusion-weighted gradient encoding period followed by multiple echo periods during which magnetic resonance signals are produced and detected, wherein at least two of the multiple echo periods correspond to respective encoded echoes having an opposite gradient polarity.

The invention relates to a method of Dixon-type MR imaging. It is an object of the invention to provide a method that enables efficient and reliable water/fat separation. The method of the invention comprises the following steps: subjecting an object (10) to an imaging sequence, which comprises at least one excitation RF pulse and switched magnetic field gradients, wherein two echo signals, a first echo signal and a second echo signal, are generated at different echo times (TE1, TE2), acquiring the echo signals from the object (10), reconstructing a water image and/or a fat image from the echo signals, wherein contributions from water and fat to the echo signals are separated using a two-point Dixon technique in a first region of k-space and a single-point Dixon technique in a second region of k-space, wherein the first region is different from the second region. In other words, the invention proposes an adaptive switching between a two-point Dixon technique for water/separation, applied to both the first and second echo signals, and a single-point Dixon technique applied to one of the two echo signals, i.e. the first echo signal data or the second echo signal data, depending on the position in k-space. Moreover, the invention relates to a MR device (1) and to a computer program to be run on a MR device (1).

The present disclosure relates to a 1D partial Fourier parallel magnetic resonance imaging method with a deep convolutional network and belongs to the technical field of magnetic resonance imaging. The method includes steps of: creating a sample set and a sample label set for training; constructing an initial deep convolutional network model; inputting a training sample of the sample set to the initial deep convolutional network model for forward process, comparing an output result of the forward process with an expected result in the sample label set, and performing training with a gradient descent method until a parameter of each layer which enables consistency between the output result and the expected result to be maximum is obtained; creating an optimal deep convolutional network model by using the obtained parameter of the each layer; and inputting a multi-coil undersampled image sampled online to the optimal deep convolutional network model, performing the forward process on the optimal deep convolutional network model, and outputting a reconstructed single-channel full-sampled image. The present disclosure can well remove the noise of the reconstructed image, reconstruct a magnetic resonance image with a better visual effect, and has high practical value.

The present disclosure relates to a method and a magnetic resonance imaging device for two-dimensional (2D) magnetic resonance (MR) imaging of a subject. The disclosure further relates to a corresponding computer program and a corresponding computer-readable storage medium. In one exemplary method, a k-space dataset of the subject is acquired using a simultaneous multi-slice technique. Therein, a blipped phase-encoding gradient is applied in a pseudo-random manner to achieve an incoherent undersampling at least in a k-space direction perpendicular to a slice select direction. A compressed sensing reconstruction is then performed based on the acquired k-space dataset to generate an MR image of the subject.