In order to improve fat saturation in magnetic resonance technology (MRT) methods, a method for spectral saturation that includes specifying or ascertaining a first resonance frequency of a first substance and a first saturation frequency for a second substance is provided. A saturation pulse that causes no saturation of the first substance at the first resonance frequency is generated. The saturation pulse has a first spectral peak for saturation of the second substance at the first saturation frequency and a second spectral peak at a second saturation frequency. This allows a widening of a spectral saturation bandwidth of a dynamic saturation.

Systems, methods, and computer program products are provided for segmenting a brain tumor from various MRI sequencing techniques. A plurality of MRI sequences of a head of a patient are received. Each MRI sequence includes a T1-weighted with contrast image, a Fluid Attenuated Inversion Recovery (FLAIR) image, a T1-weighted image, and a T2-weighted image. Each image of the plurality of MRI sequences is registered to an anatomical atlas. A plurality of modified MRI sequences are generated by removing a skull from each image in the plurality of MRI sequences. A tumor segmentation map is determined by segmenting a tumor within a brain in each image in the plurality of modified MRI sequences. The tumor segmentation map is applied to each of the plurality of MRI sequences to thereby generate a plurality of labelled MRI sequences

In a method for automatic control of an examination sequence in magnetic resonance (MR) system during recording of MR signals in an examination segment of a person being examined, which has two tissue components with two different MR resonant frequencies, an examination sequence for examination of the examination segment is determined. Further, whether the examination sequence includes an imaging sequence in which one of the two tissue components is to be suppressed and for which at least two different suppression options exist to reduce the one of the two tissue components during the recording of the MR signals is determined. In response to the determination that the examination sequencing included the imaging sequence, the method can include determining a sequence parameter of the examination for the imaging sequence; and selecting one of the at least two suppression options as a function of the sequence parameter determined for the imaging sequence.

A T1-weighted turbo-spin-echo magnetic resonance imaging system configured to capture data associated with a subject's heart during a time period and produce MR images has a dark-blood preparation module, a data capture module, and an image reconstruction module. The dark-blood preparation module performs dark-blood preparation through double inversion during some, but not all of the heartbeats within the time period. The data capture module configured performs data readouts to capture imaging data of an imaging slice during every heartbeat in which dark-blood preparation is performed. The data capture module also performs a steady state maintenance step during every heartbeat in which dark-blood preparation is not performed in order to maintain maximum T1-weighting. The image reconstruction module configured to reconstruct a T1-weighted image based on the imaging data.

To provide a technique with which a FLAIR image and a T1-weighted image can be acquired in a short scan time, a magnetic resonance imaging apparatus comprises: an RF driver unit 121 for driving an RF coil unit 103; a gradient coil driver unit 122 for driving a gradient coil unit 102; and a controller unit 124 connected to the RF coil driver unit 121 and gradient coil driver unit 122, for controlling them so that an imaging sequence ISc having a duration of 1TR for generating echoes from a body part being imaged is repetitively executed, where the imaging sequence ISc has a first sequence part SQ1 including an inversion pulse 11 and an FSE sequence 12, and a second sequence part SQ2 including an inversion pulse 21 and a GRE sequence 22.

In a method for recording a PET image data set, an overall recording area is moved continuously through the FOV at a constant movement speed, an attenuation map of the overall recording area being used to reconstruct the PET image data record from the PET raw data. The magnetic resonance data of a slice of the patient currently located within the FOV and movement status information relating to a cyclical movement of the patient are recorded simultaneously with recording the PET raw data. A movement status class is assigned to the PET raw data and the magnetic resonance data in each case. Using the magnetic resonance data assigned to the different movement status classes, attenuation maps of the patient are determined for the different movement status classes and applied to the PET raw data assigned to the corresponding movement status class to reconstruct the PET image data set.

Techniques are disclosed based on balanced steady state free precession sequence. The techniques include determining a readout gradient of climbing period, platform period, and descent period, and performing a balanced steady state free precession sequence in which the readout gradient is applied in the readout direction, the analog-to-digital conversion module for collecting k-space data is activated during the climbing period maintained in the on state during the platform period, and deactivated during the descent period. The technique includes converting the k-space data collected by the analog-to-digital conversion module into uniform k-space data and generating a magnetic resonance image based on the uniform k-space data. The techniques yield more running time of the readout gradient for data acquisition, reduce the data reading time, and shorten the scanning time. The techniques also reduce the accumulated phase of the field non-uniformity in the echo interval to reduce black band artifacts.

The disclosed technology relates to a method and device for generating a fat suppression magnetic resonance image. The method includes: inputting, by an imaging device, a magnetic resonance image to an encoder of a neural network to extract features of the magnetic resonance image; and generating, by a generator of the neural network, a T2-weighted fat suppression image based on the features, in which the neural network is trained according to a result of discriminating, by a discriminator of the neural network, a loss due to a generation of a T2-weighted fat suppression image and as a result of reconstructing, by a decoder, the magnetic resonance image input to the encoder using a Bloch equation before the magnetic resonance image is input.

A subject S to which .sup.17O gas has been administered is placed within a fixed uniform static magnetic field of an NMR apparatus 1. The subject is irradiated, through proton coupling, with an excitation pulse produced using a pulse sequence having a short cycle time of 20.4 msec or less, preferably 10.4 msec or less, and more preferably 5.6 msec or less. An NMR signal generated due to .sup.17O nuclei of .sup.17O water produced within the subject by oxygen metabolism of the .sup.17O gas being excited by irradiation with the excitation pulse is detected with high sensitivity and is processed in accordance with a prescribed imaging sequence in which an MRS sequence is used.

A method for correcting TOF MR data, including providing a coil sensitivity map for an examination region of an examination object, providing the TOF MR data of the examination region, and generating corrected TOF MR image data comprising multiplying the TOF MR data by an inverse of the coil sensitivity map.