A magnetic resonance imaging apparatus according to an embodiment includes sequence controlling circuitry and processing circuitry. The sequence controlling circuitry is configured to execute (i) a first pulse sequence in which a spatially selective Inversion recovery (IR) pulse and a spatially non-selective IR pulse are applied, and subsequently an acquisition is performed and (ii) a second pulse sequence in which the spatially non-selective IR pulse is applied without applying the spatially selective IR pulse, and subsequently an acquisition is performed, while varying the first TI period, with respect to a plurality of first TI periods. The processing circuitry is configured to calculate a second TI period to be used in a third pulse sequence and a fourth pulse sequence, based on data obtained from the first pulse sequence and the second pulse sequence. The sequence controlling circuitry executes (iii) the third pulse sequence in which the spatially selective IR pulse and the spatially non-selective IR pulse are applied, and subsequently an acquisition is performed and (iv) the fourth pulse sequence in which the spatially non-selective IR pulse is applied without applying the spatially selective IR pulse, and subsequently an acquisition is performed. The processing circuitry generates a magnetic resonance image of an imaged region based on data obtained from the third pulse sequence and the fourth pulse sequence.

Techniques for compensating magnetic resonance imaging (MRI) data for artefacts caused by motion of a subject being imaged. The techniques include obtaining spatial frequency data obtained by using a magnetic resonance imaging (MRI) system to perform MRI on a patient, the spatial frequency data including first spatial frequency data and second spatial frequency data; determining a transformation using a first image obtained using the first spatial frequency data and a second image obtained using the second spatial frequency data; determining a residual spatial phase; correcting, using the transformation, second spatial frequency data and the residual spatial phase, to obtain corrected second spatial frequency data and a corrected residual spatial phase; and generating a magnetic resonance (MR) image using the corrected second spatial frequency data and the corrected residual spatial phase.

Systems and methods are provided for performing automated reconstruction of a dynamic MRI dataset that is acquired without a fixed temporal resolution. On one or more image quality metrics (IQMs) are obtained by processing a subset of the acquired dataset. In one example implementation, at each stage of an iterative process, one or more IQMs of the image subset is computed, and the parameters controlling the reconstruction and/or the strategy for data combination are adjusted to provide an improved or optimal image reconstruction. Once the IQM of the image subset satisfies acceptance criteria based on an estimate of the overall temporal fidelity of the reconstruction, the full reconstruction can be performed, and the estimate of the overall temporal fidelity can be reported based on the IQM at the final iteration.

The invention provides for a magnetic resonance imaging system (100, 300, 100) for acquiring magnetic resonance data (110, 1104) from a subject (118) within an imaging zone (108). The magnetic resonance imaging system comprises a memory (136) for storing machine executable instructions (160, 162, 164, 166, 316) and pulse sequence data (140, 1102). The pulse sequence data comprises instructions for controlling the magnetic resonance imaging system to acquire magnetic resonance data according to a magnetic resonance imaging method. The magnetic resonance imaging system further comprises a processor (130) for controlling the magnetic resonance imaging system. Execution of the machine executable instructions causes the processor to: acquire (1200) the magnetic resonance data by controlling the magnetic resonance imaging system with the pulse sequence data; calculate (1202) a B0 inhomogeneity map (148) by analyzing the magnetic resonance data according to the magnetic resonance imaging method, calculate (1204) a B1 phase map (150) and/or a B1 amplitude map (1106) by analyzing the magnetic resonance data according to the magnetic resonance imaging method; and calculate (1206) a second derivative (1110) of the B1 phase map and/or a second derivative of the B1 magnitude map 1 and/or a second derivative of the B0 in homogeneity map in at least one predetermined direction. The second derivative is calculated using a corrected voxel size in the at least one predetermined direction, wherein the corrected voxel size is calculated using a correction factor calculated from the derivative of the B0 inhomogeneity map.

The disclosure is directed to an Echo-Planar-Imaging (EPI) magnetic resonance imaging techniques combined with a variable-density undersampling scheme. The technique comprises generating an RF pulse, applying a switched frequency-encoding read out gradient in a variable time interval, and applying simultaneously an intermittently blipped low-magnitude phase-encoding gradient with a variable value of an integral of the phase-encoding gradient. The aforementioned steps are carried out such that the k-space is at least partially undersampled and the time interval of one read out gradient is varied depending on the integral of the phase encoding gradient, such that a ratio between the variable time interval of the read out gradient and the integral of the corresponding phase encoding gradient is kept above or at a predetermined constant value, which is related to a predetermined criteria of image quality.

A magnetic resonance imaging (MRI) system and method for acquiring magnetic resonance (MR) images using a pulse sequence implementing driven equilibrium and quadratic phase cycling techniques is provided. The method includes, during a pulse repetition period of a pulse sequence and using a quadratic phase cycling scheme, applying a first RF pulse to deflect a net magnetization vector associated with the subject from a longitudinal plane into a transverse plane; after applying the first RF pulse, applying a first sequence of RF pulses each of which flips the net magnetization vector by approximately 180 degrees within the transverse plane; and after applying the first sequence of RF pulses, applying a second RF pulse to deflect the net magnetization vector from the transverse plane to the longitudinal plane.

The present disclosure is directed to MRI techniques. The techniques include occupying a central region of a first k-space with full sampling along a Cartesian trajectory, occupying a peripheral region of the first k-space with undersampling along a non-Cartesian trajectory; acquiring sensitivity distribution information of receiving coils; based on a sensitivity distribution chart, merging the Cartesian data of the central region according to multiple channels to obtain a third k-space; based on the sensitivity distribution chart, applying parallel imaging and compressed sensing to the undersampled non-Cartesian trajectory to reconstruct an image, obtaining a second k-space by transformation, and when the second k-space and third k-space are synthesized, using a central region of the second k-space to replace the third k-space of a corresponding region to obtain a k-space suitable for image reconstruction.

A magnetic resonance imaging apparatus according to an embodiment includes sequence controlling circuitry and processing circuitry. The sequence controlling circuitry is configured to execute (i) a first pulse sequence in which a spatially selective Inversion recovery (IR) pulse and a spatially non-selective IR pulse are applied, and subsequently an acquisition is performed and (ii) a second pulse sequence in which the spatially non-selective IR pulse is applied without applying the spatially selective IR pulse, and subsequently an acquisition is performed, while varying the first TI period, with respect to a plurality of first TI periods. The processing circuitry is configured to calculate a second TI period to be used in a third pulse sequence and a fourth pulse sequence, based on data obtained from the first pulse sequence and the second pulse sequence. The sequence controlling circuitry executes (iii) the third pulse sequence in which the spatially selective IR pulse and the spatially non-selective IR pulse are applied, and subsequently an acquisition is performed and (iv) the fourth pulse sequence in which the spatially non-selective IR pulse is applied without applying the spatially selective IR pulse, and subsequently an acquisition is performed. The processing circuitry generates a magnetic resonance image of an imaged region based on data obtained from the third pulse sequence and the fourth pulse sequence.

For reconstruction of an image in MRI, unsupervised training (i.e., data-driven) based on a scan of a given patient is used to reconstruct model parameters, such as estimating values of a contrast model and a motion model based on fit of images generated by the models for different readouts and times. The models and the estimated values from the scan-specific unsupervised training are then used to generate the patient image for that scan. This may avoid artifacts from binning different readouts together while allowing for scan sequences using multiple readouts.

A system may transform sensor data from a sensor domain to an image domain using data-driven manifold learning techniques which may, for example, be implemented using neural networks. The sensor data may be generated by an image sensor, which may be part of an imaging system. Fully connected layers of a neural network in the system may be applied to the sensor data to apply an activation function to the sensor data. The activation function may be a hyperbolic tangent activation function. Convolutional layers may then be applied that convolve the output of the fully connected layers for high level feature extraction. An output layer may be applied to the output of the convolutional layers to deconvolve the output and produce image data in the image domain.