Techniques are disclosed for use in magnetic resonance imaging (MRI) for exciting spins of a first material and spins of a second material. A first spin echo signal is acquired when the excited spins include a first phase difference, which is given by Δ, and a second spin echo signal is acquired when the excited spins of the first material and the excited spins of the second material include a second phase difference, which is given by −Δ. An absolute value of Δ lies within the interval ]0,π[. A first image for the first material and/or a second image for the second material is generated by a computing unit depending on the first spin echo signal and the second spin echo signal.

Disclosed herein is a medical system (100, 300, 500). The execution of machine executable instructions (112) causes a computational system (104) to: receive (200) a baseline anatomical measurement (114) descriptive of a clinical magnetic resonance image of a subject (318); receive (202) scan metadata (116) descriptive of the clinical magnetic resonance image of the subject; send (204) scan parameters via a network connection (350) to a low-field magnetic resonance imaging system (301); receive (206) subsequent k-space data (122) from the low-field magnetic resonance imaging system via the network connection in response to sending the scan parameters; reconstruct (208) a subsequent magnetic resonance image (124) from the subsequent k-space data; determine (210) a subsequent anatomical measurement (128) in response to inputting the subsequent magnetic resonance image into the segmentation module; and provide (212) a warning signal (132) if the subsequent anatomical measurement varies from the baseline anatomical measurement by more than a predetermined amount.

The invention relates to a method of MR imaging of an object (10). It is an object of the invention to enable MR imaging in the presence of motion of the imaged object, wherein full use is made of the acquired MR signal and a high-quality MR image essentially free from motion artefacts is obtained. The method of the invention comprises the steps of: generating MR signals by subjecting the object (10) to an imaging sequence comprising RF pulses and switched magnetic field gradients; acquiring the MR signals as signal data over a given period of time (T); subdividing the period of time into a number of successive time segments (SO, S1, S2, . . . Sn); deriving a geometric transformation (DVF1, DVF2, . . . DVFn) in image space for each pair of consecutive time segments (S0, S1, S2, . . . Sn), which geometric transformation (DVF1, DVF2, . . . DVFn) reflects motion occurring between the two time segments of the respective pair; and reconstructing an MR image from the signal data, wherein a motion compensation is applied according to the derived geometric transformations (DVF1, DVF2, . . . DVFn). Moreover, the invention relates to an MR device (1) and to a computer program for an MR device (1).

Magnetic resonance elastography (“MRE”), or other imaging-based elastography techniques, generate estimates of the mechanical properties, such as stiffness and damping ratio, of tissues in a subject. A machine learning approach, such as an artificial neural network, is implemented to perform an inversion of displacement data in order to generate the estimates of the mechanical properties.

A method and apparatus for generating a T1 or T2 map for a three-dimensional (3D) image volume of a subject. The method includes acquiring first, second, and third 3D images of the image volume of the subject. Signal evolutions of voxels through the first to third 3D images by comparing voxel intensity levels of corresponding voxel locations in the first, second, and third 3D images. A simulation dictionary representing the signal evolutions for a number of different tissue parameter combinations is obtained. The T1 or T2 map is generated by comparing the determined signal evolutions to entries in the dictionary and by finding, for each of the determined signal evolutions, the entry in the dictionary that best matches the determined signal evolution.

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 present disclosure relates to a method for correcting chemical shift artifacts, CSA, which arise in the magnetic resonance DIXON method when using bipolar readout gradients (fast DIXON MR) to capture the in-phase and opposed-phase echoes.

Distortion generated in an image is effectively corrected in imaging using an EPI sequence such as DWI without extending an imaging time. After one excitation RF pulse of EPI is applied, a navigator scan in which the polarity of the phase encoding is opposite to that of the main scan is performed continuously to the main scan, and the distortion of the image by using the navigator scan data obtained by the navigator scan is corrected. In a case of multi-shot, phase information obtained from the navigator scan data for each shot is used to perform phase correction and multi-shot reconstruction on the main scan data of each shot.

Systems and methods are provided for the denoising of images in the presence of broadband noise based on the detection and/or estimation of in-band noise. According to various example embodiments, an estimate of broadband noise that lies within the imaging band is made by detecting or characterizing the out-of-band noise that lies outside of the imaging band. This estimated in-band noise may be employed for denoise the detected imaging waveform. According to other example embodiments, a reference receive circuit that is sensitive to noise within the imaging band, but is isolated from the imaging energy, may be employed to detect and/or characterize the noise within the imaging band. The estimated reference noise may be employed to denoise the detected in-band imaging waveform.