A system and method of generating a graphical representation of a network of a subject human brain. The method comprises receiving, via a user interface, a selection of the network of the subject brain; determining, based on an MRI image of the subject brain and one or more identifiers associated with the selection, one or more parcellations of the subject brain (405); determining, using three-dimensional coordinates associated with each parcellation, corresponding tracts in a diffusion tensor image of the brain (425); and generating a graphical representation of the selected network (430), the graphical representation including at least one of (i) one or more surfaces representing the one or more parcellations, each surface generated using the coordinates, and (ii) the determined tracts.

The present disclosure provides a system for MRI. The system may obtain MRI scan data of a subject by directing an MRI scanner to perform an MRI scan on the subject according to a first gradient waveform. The system may also determine a second gradient waveform based on the first gradient waveform and a gradient waveform determination model. The gradient waveform determination model may have been trained according to a machine learning algorithm. The system may further generate a target reconstruction image of the subject based on the second gradient waveform and the MRI scan data.

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 method to compensate for chemical shift displacement includes, prior to applying an imaging pulse sequence to acquire MRI data of a subject, applying a first saturation pulse within a slice location of an imaging volume of the subject in which the MRI data is to be acquired, wherein the first saturation pulse results in a first chemical shift displacement between water and fat in a first spatial saturation band. The method also includes, prior to applying the imaging pulse sequence, subsequently applying a second saturation pulse within the slice location, wherein the second saturation pulse results in a second chemical displacement between the water and the fat in a second spatial saturation band that results in a final spatial saturation band being free of chemical shift displacement after application of the second saturation pulse, the second chemical shift displacement being different from the first chemical shift displacement.

The present invention relates to the generation of artificial IRM images of the liver. The invention also relates to a method, a system and a computer program product for generating MRI images of the liver.

An MRI apparatus according to an embodiment includes sequence controlling circuitry, in a first transition period, repeating application of a first MT pulse and acquisition of a first MR signal to a first frequency region being a part of a k-space; in the first steady state, repeating application of the first MT pulse and acquisition of a second MR signal to a second frequency region of the k-space, frequency in second frequency region being lower than frequency in the first frequency region; and in a second transition period, repeating application of a second MT pulse and acquisition of a third MR signal to a third frequency region being another part of the k-space, frequency in the third frequency region being higher than the frequency in the second frequency region, and processing circuitry generating one MR image on basis of the first, second, and third MR signal.

Neural network based systems, methods, and instrumentalities may be used to remove motion artifacts from magnetic resonance (MR) images. Such a neural network based system may be trained to perform the motion artifact removal tasks without reference (e.g., without using paired motion-contaminated and motion-free MR images). Various training techniques are described herein including one that feeds the neural network with pairs of MR images with different levels of motion contamination and forces the neural network learn to correct the motion contamination by transforming a first image of a contaminated pair into a second image of the contaminated pair. Other neural network training techniques are also described with an aim to reduce the reliance on training data that is difficult to obtain.

Embodiments facilitate generation of a prediction of long-term survival (LTS) or short-term survival (STS) of Glioblastoma (GBM) patients. A first set of embodiments discussed herein relates to training of a machine learning classifier to determine a prediction for LTS or STS based on a radiographic-deformation and textural heterogeneity (r-DepTH) descriptor generated based on radiographic images of tissue demonstrating GBM. A second set of embodiments discussed herein relates to determination of a prediction of disease outcome for a GBM patient of LTS or STS based on an r-DepTH descriptor generated based on radiographic imagery of the patient.

A system for displaying and interacting with magnetic resonance imaging (MRI) data acquired using an MRI system includes an image reconstruction module configured to receive the MRI data and to reconstruct a plurality of images using the MRI data, an image rendering module coupled to the image reconstruction module and configured to generate at least one multidimensional image based on the plurality of images and a user interface device coupled to the image rendering module and located proximate to a workstation of the MRI system. The user interface device is configured to display the at least one multidimensional image in real-time and to facilitate interaction by a user with the multidimensional image in a virtual reality or augmented reality environment.

The present disclosure relates to quantitative magnetic resonance imaging. A time series of magnetic resonance images of an examination region are assigned to different time points following an excitation is acquired by means of a magnetic resonance device, a signal evolution varying with respect to time is determined from the magnetic resonance images for each pixel from the magnetic resonance data of all of the magnetic resonance images and, by comparison of the signal evolution with comparison evolutions stored in a database, at least one quantitative result value on which the comparison evolution exhibiting the greatest agreement is based is assigned to a respective pixel.