Systems and methods for generative adversarial networks (GANs) to remove artifacts from undersampled magnetic resonance (MR) images are described. The process of training the GAN can include providing undersampled 3D MR images to the generator model, providing the generated example and a real example to the discriminator model, applying adversarial loss, L2 loss, and structural similarity index measure loss to the generator model based on a classification output by the discriminator model, and repeating until the generator model has been trained to remove the artifacts from the undersampled 3D MR images. At runtime, the trained generator model of the GAN can be generate artifact-free images or parameter maps from undersampled MRI data of a patient.

The present disclosure provides a system and method for magnetic resonance imaging. The method may include obtaining first k-space data collected from a subject in a non-Cartesian sampling manner. The method may also include generating second k-space data by regridding the first k-space data. The method may further include generating third k-space data by calibrating the second k-space data, wherein a calibrated field of view (FOV) corresponding to the third k-space data is constituted by a central portion of an intermediate FOV corresponding to the second k-space data. The method may still further include reconstructing, using at least one of a compressed sensing algorithm or a parallel imaging algorithm, a magnetic resonance (MR) image of the subject based at least in part on the third k-space data.

A computer implemented method of treatment targeting includes receiving magnetic resonance (MR) images of a subject including a target region, generating at least one contour of at least one surrogate element apart from the target region in the MR images, and determining a location of the target region in each of the MR images based on a location of the at least one contour in the MR images.

This specification describes systems and methods for using Zero Echo Time (ZTE) magnetic resonance imaging (MRI) sequences for applications to functional MRI (fMRI). In some examples, a system for functional magnetic resonance imaging includes a magnetic resonance imaging (MRI) scanner and a control console implemented on at least one processor. The control console is configured for executing, using the MRI scanner, a zero echo time (ZTE) pulse sequence; acquiring, using the MRI scanner, magnetic resonance data in response to the ZTE pulse sequence; and constructing at least one MRI image using the magnetic resonance data and measuring tissue oxygenation (PtO2)-related T1 changes as a proxy of neural activity changes of a subject using the at least one MRI image.

A medical image processing apparatus according to the present embodiment includes processing circuitry. The processing circuitry inputs a first magnetic resonance image reconstructed with super-resolution processing on magnetic resonance data and a second magnetic resonance image obtained by imaging the same object as that of the first magnetic resonance image and with artifacts suppressed compared with the first magnetic resonance image, to a leaned model, the learned model being configured to output a third magnetic resonance image having the same resolution as that of the first magnetic resonance image and with the artifacts suppressed, generates the third magnetic resonance image based on the first magnetic resonance image and the second magnetic resonance image, using the learned model.

Techniques for determining a functional magnetic resonance data set of an imaging region of a brain of a patient are disclosed in which blood oxygenation level dependent functional magnetic resonance imaging is used. The techniques include using a plurality of reception coils, and acquiring magnetic resonance signals using parallel imaging and a magnetic resonance sequence defining a k-space trajectory, wherein undersampling in at least two k-space directions is performed. The techniques further include reconstructing the functional magnetic resonance data set from the magnetic resonance signals and sensitivity information regarding the plurality of reception coils using a reconstruction technique for undersampled magnetic resonance data, wherein the k-space trajectory is chosen to allow controlled aliasing in all three spatial dimensions including the readout direction.

A system and method for performing accelerated k-space shift correction calibration scans for non-Cartesian trajectories is provided. The method can include applying an MRI sequence, performing a calibration scan based on the MRI sequence using the non-Cartesian trajectory to acquire k-space shift data, wherein one or more partitions are skipped during the calibration scan, interpolating the skipped one or more partitions using the k-space shift data from adjacent partitions, and calibrating the MRI system using the k-space shift data and the interpolated k-space shift data. In some embodiments, an acceleration factor Acc can be defined and the calibration scan acquires k-space shift data for only one partition in every Acc partitions.

A method for 3D oscillating-gradient prepared gradient spin-echo imaging and a device. The imaging method comprises the following steps: first, using a global saturation module to destroy previous residual transverse magnetization; second, embedding a pair of trapezoidal cosine oscillating gradients into a 90°.sub.x-180°.sub.y-90°.sub.−x radiofrequency pulse by a diffusion encoding module, to separate diffusion encoding from signal acquisition; then, using a fat saturation module to suppress a fat signal; finally, acquiring a signal by means of gradient spin-echo readout, and correcting phase errors among multiple excitations by multiplexed sensitivity-encoding reconstruction. Compared with a 2D plane echo-based oscillating gradient diffusion sequence used on a 3T clinical system, a 3D oscillating-gradient prepared gradient spin-echo sequence effectively reduces the imaging time, improves the signal to noise ratio, and is beneficial to clinical transformation of time-dependent diffusion MRI technology

The present disclosure discloses a magnetic resonance imaging method based on a blade sequence. The method can include acquiring 3-D data collected by a surface coil, determining a corresponding plurality of kernel data of each blade from the 3-D data according to the position information of each blade, collecting a corresponding plurality of slices of aliasing K-space data of each blade, performing convolution operations for the corresponding plurality of slices of aliasing K-space data of each blade and the corresponding plurality of kernel data of each blade to obtain a corresponding plurality of unaliasing K-space data of each blade, and reconstructing images for the corresponding plurality of unaliasing K-space data of different blades to obtain a plurality of unaliasing images. The present disclosure further describes a magnetic resonance imaging device for realizing the method and a computer-readable storage medium.

A magnetic resonance (MR) imaging method of correcting motion in precorrection MR images of a subject is provided. The method includes applying, by an MR system, a pulse sequence having a k-space trajectory of a blade being rotated in k-space. The method also includes acquiring k-space data of a three-dimensional (3D) imaging volume of the subject, the k-space data of the 3D imaging volume corresponding to the precorrection MR images and acquired by the pulse sequence. The method further includes receiving a 3D MR calibration data of a 3D calibration volume, wherein the 3D calibration volume is greater than or equal to the 3D imaging volume, jointly estimating rotation and translation in the precorrection MR images based on the k-space data of the 3D imaging volume and the calibration data, correcting motion in the precorrection images based on the estimated rotation and the estimated translation, and outputting the motion-corrected images.