Various methods and systems are provided for correcting transmit attenuation of an amplifier of a transmit radio frequency (RF) coil for use in a magnetic resonance imaging (MRI) system. In one example, a method includes setting a reference value of transmit attenuation for an amplifier of a transmit radio frequency (RF) coil, acquiring a three-dimensional B.sub.1 field map with the transmit attenuation set at the reference value, determining a plurality of mean flip angles for a plurality of slice locations in a pre-scan imaging volume from the B.sub.1 field map, determining a transmit attenuation correction value for each of the slice locations based on a prescribed flip angle and the mean flip angle determined for the respective slice location, correcting the reference value of transmit attenuation with the transmit attenuation correction value at each of the slice locations to obtain a final value of transmit attenuation for each of the slice locations, and performing an MRI scan with the transmit attenuation set at the value.

In a method and system for acquiring measurement data reference data for a phase correction of the measurement data, a RF excitation pulse is provided to excite spins in the object under examination, one or more RF refocusing pulses are provided to refocus the spins excited by the RF excitation pulse, measurement data is acquired by recording echo signals of refocused spins excited by the RF excitation pulse by switching readout gradients that alternate in their polarity, at least two echo signals are recorded while switching readout gradients with different polarity acquire reference data, chronologically between the providing of the RF excitation pulse and the acquisition of the measurement data, and correction data is determined for phase correction of phase errors contained in the measurement data based on the acquired reference data.

In various embodiments, the invention teaches systems and methods for magnetic resonance imaging. In some embodiments, the invention teaches systems and methods for determining the source of pain in intervertebral discs by measuring one or more physiological biomarkers associated with disc pain and/or disc degeneration.

A magnetic resonance imaging apparatus according to an embodiment executes a first imaging prior to a second imaging and includes processing circuitry. The processing circuitry receives, on a first image obtained from the first imaging, a setting of a region in which an RF (Radio Frequency) pulse is to be applied to a subject, generates a three-dimensional image based on the first image, determines, based on an imaging purpose of the second imaging, a translucent region to which translucent processing is to be performed in the three-dimensional image, and displays the translucent region, making the translucent region translucent in the three-dimensional image.

Methods for reconstructing images from undersampled k-space data using a machine learning approach to learn non-linear mapping functions from acquired k-space lines to generate unacquired target points across multiple coils are described.

Methods and systems are provided for identifying radio frequency (RF) interference without an RF room during imaging in a magnetic resonance tomography system. The method includes performing an acquisition, wherein scanning of a k-space along a trajectory takes place and an angle of rotation α exists between a scan start position of a first individual acquisition and a scan start position of a following second individual acquisition. A first image is obtained from the first individual acquisition and a second image is obtained from the second individual acquisition. One of the two images is rotated in respect of the other image about the angle of rotation α. A correlation is determined between the one rotated image and the other image, and a point of interference is identified from the correlation.

Methods and systems are provided for identifying radio frequency (RF) interference without an RF room during imaging in a magnetic resonance tomography system. The method includes performing an acquisition, wherein scanning of a k-space along a trajectory takes place and an angle of rotation α exists between a scan start position of a first individual acquisition and a scan start position of a following second individual acquisition. A first image is obtained from the first individual acquisition and a second image is obtained from the second individual acquisition. One of the two images is rotated in respect of the other image about the angle of rotation α. A correlation is determined between the one rotated image and the other image, and a point of interference is identified from the correlation.

A magnetic resonance imaging apparatus according to an embodiment includes processing circuitry configured, on a basis of one or both of (A) a parameter related to applying one of inversion and flip pulses and (B) an intensity of a slice selecting gradient magnetic field applied together with the one of the pulses in relation to selecting a slice to which the one of the pulses is applied, to determine one or both of (A) a parameter related to applying the other of the inversion and (B) flip pulses; and an intensity of the slice selecting gradient magnetic field applied together with the other of the pulses in relation to selecting a slice to which the other of the pulses is applied.

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.