The present invention provides a graph-based prostate diagnosis network (GPD-Net) and a method for using the same to predict a prostate health status of a patient from a 3D magnetic resonance imaging (MRI) scan containing a plurality of 2D MRI slices. The GPD-Net only demands patient-level annotations of MRI scan for training by formulating the diagnosis task of 3D prostate MRI scan in a multi-instance learning (MIL) strategy, and regarding each 2D MRI slice in the 3D prostate MRI scan as an instance. The GPD-Net includes a plurality of importance-guided graph convolutional layers to explore the diagnostic information with the importance-based topology. The present invention provides accurate prediction of prostate diseases and achieve more reliable diagnosis from

MRI scans, therefore can effectively alleviate the workload of clinician in viewing the slices of MRI scan.

A method for producing images of a subject with a MRI system is provided. A radio frequency (RF) excitation field in combination with a slice-select magnetic gradient field along a slice-select direction is provided. At least one readout magnetic field gradient is established along a frequency-encoding direction and at least one phase encoding magnetic field gradient along a phase-encoding direction. The RF field or magnetic field gradient is manipulated along a slice-select direction in order to impart a sequence of phase shifts to the formed echo signals such that image data corresponding to an at least one adjacent slice location is incoherently aliased across a field-of-view (FOV) of a current slice location. Image data is acquired indicative of the formed echo signals. A plurality of images of the subject is reconstructed.

Techniques for generating magnetic resonance (MR) images of a subject from MR data obtained by a magnetic resonance imaging (MRI) system, the techniques including: obtaining input MR data obtained by imaging the subject using the MRI system; generating a plurality of transformed input MR data instances by applying a respective first plurality of transformations to the input MR data; generating a plurality of MR images from the plurality of transformed input MR data instances and the input MR data using a non-linear MR image reconstruction technique; generating an ensembled MR image from the plurality of MR images at least in part by: applying a second plurality of transformations to the plurality of MR images to obtain a plurality of transformed MR images; and combining the plurality of transformed MR images to obtain the ensembled MR image; and outputting the ensembled MR image.

A method for recording a magnetic resonance image data set includes providing a magnetic resonance sequence. The magnetic resonance sequence includes at least one radio-frequency pulse and a slice-selection gradient pulse applied during or before the radio-frequency pulse, which is configured as non-constant. The method includes providing at least one correction term for compensating a magnetic field change of the slice-selection gradient pulse. The magnetic field change is ascertained via a transfer characteristic of the gradient system of the magnetic resonance system. The method also includes recording at least one magnetic resonance image data set with the magnetic resonance sequence using the correction term.

In a magnetic resonance method and apparatus for determination of a measurement variable that is relevant to a function of an organ of a patient, a first longitudinal relaxation rate R.sub.1.sup.1 is determined before a contrast medium is administered to the patient. A second longitudinal relaxation rate R.sub.1.sup.2 is determined after a contrast medium is administered to the patient. A property of the contrast medium in the organ is determined based on R.sub.1.sup.1 and R.sub.1.sup.2. The measurement variable is determined based on the property of the contrast medium in the organ.

A magnetic resonance imaging apparatus according to an embodiment includes a specifying unit and an acquiring unit. The specifying unit specifies, on a basis of a detection result of target sites of a subject detected from an image on which the target sites are visualized, a first region and a second region which is different from the first region on the image. The acquiring unit acquires data of the second region by using an imaging condition which is different from an imaging condition on an imaging slice and used for acquiring data of the first region.

The present disclosure in some embodiments provides a method and an apparatus for processing MRI images wherein a plurality of slices of an object is applied with a spatial encoding gradient and a corrected gradient for applying a radial sampling, and radially sampled magnetic resonance signals of the slices are received, and MRI images are generated with the radial sampling applied over multi-bands.

A method for performing magnetic resonance imaging is provided. The method includes providing a magnetic resonance imaging system comprising: a radio frequency receive system comprising a radio frequency receive coil, and a housing, wherein the housing comprises a permanent magnet for providing an inhomogeneous permanent gradient field, a radio frequency transmit system, and a single-sided gradient coil set. The method also includes placing the receive coil proximate a target subject; applying a sequence of chirped pulses via the transmit system; applying a multi-slice excitation along the inhomogeneous permanent gradient field; applying a plurality of gradient pulses via the gradient coil set orthogonal to the inhomogeneous permanent gradient field; acquiring a signal of the target subject via the receive system, wherein the signal comprises at least two chirped pulses; and forming a magnetic resonance image of the target subject.

An MRI-based method for determining a velocity profile for a fluid flowing through a pipe, said method comprising: selecting a slice through which said fluid is flowing; selecting a pulse sequence; separating said pulse sequence into a preparation part and a readout part; applying said preparation part to said slice; waiting a predetermined time Rt; and, applying said readout part to said slice.

Techniques are disclosed for acquiring magnetic resonance data of an object with a magnetic resonance imaging apparatus. A slice group is imaged whose slices define a contiguous imaging volume and which contains a first number of slices. In a number of concatenations, the magnetic resonance data for subgroups of the slices, each containing a respective second number of slices depending on the first number of concatenations, are acquired, and shimming is performed to increase field homogeneity in the imaging volume. To define the subgroups, the imaging volume is subdivided into at least two disjoint contiguous sub-volumes, and at least two subgroups are defined for each sub-volume, each subgroup only containing non-adjacent slices in the sub-volume. During acquisition of the magnetic resonance data of each subgroup, shimming is at least restricted to the respective sub-volume.