A computer-implemented method for generating an artifact corrected reconstructed contrast image from magnetic resonance imaging (MRI) data is provided. The method includes inputting into a trained deep neural network both a synthesized contrast image derived from multi-delay multi-echo (MDME) scan data or the MDME scan data acquired during a first scan of an object of interest utilizing a MDME sequence and a composite image, wherein the composite image is derived from both the MDME scan data and contrast scan data acquired during a second scan of the object of interest utilizing a contrast MRI sequence. The method also includes utilizing the trained deep neural network to generate the artifact corrected reconstructed contrast image based on both the synthesized contrast image or the MDME scan data and the composite image. The method further includes outputting from the trained deep neural network the artifact corrected reconstructed contrast image.

The present disclosure relates to magnetic resonance imaging technology for simultaneously measuring a plurality of magnetic resonance imaging parameters. According to one embodiment of the present disclosure, a magnetic resonance imaging apparatus includes a data collector for alternately collecting a steady-state-free-precession (SSFP)-FID signal and an SSFP-ECHO signal within a time of repetition to obtain AUSFIDE (alternating unbalanced SSFP-FID & SSFP-ECHO) image data; a data processor for reconstructing a magnitude image and a phase image for each of the SSFP-FID signal and the SSFP-ECHO signal in the AUSFIDE (alternating unbalanced SSFP-FID & SSFP-ECHO) image data and processing the AUSFIDE (alternating unbalanced SSFP-FID & SSFP-ECHO) image data using the reconstructed magnitude images and phase images; and a parameter measuring device for measuring a plurality of magnetic resonance imaging parameters using a plurality of echo data based on the processed AUSFIDE (alternating unbalanced SSFP-FID & SSFP-ECHO) image data.

In a method for determining imaging parameters for a Magnetic Resonance (MR) image, a set of image sequence parameters of the imaging sequence is determined, a frequency offset of off-resonant tissue potentially present in the object under examination is determined, an allowed maximum position shift of the off-resonant tissue along a slice selection direction is determined, a rotation angle which leads to the allowed maximum shift for the off-resonant tissue is determined based on the determined set of image sequence parameters, and the determined rotation angle is provided to the MR imaging system to allow the MR imaging system to generate the MR image using the determined rotation angle in the imaging sequence.

A method for creating calibration data for processing accelerated measurement data of an object to be examined using a magnetic resonance system. The method includes recording measurement data sets using an acquisition acceleration method, recording calibration data sets, and determining processed measurement data sets from the accelerated measurement data sets using the calibration data sets so that effects of the acquisition acceleration method used are eliminated in the processed measurement data sets. The recording of the calibration data sets includes an application of at least one attenuation method for attenuating signals causing phase errors.

An MRI apparatus includes a scanner configured to apply an RF pulse to an object and processing circuity configured to: set a first pulse sequence in which acquisition of a first set of MR signals is started after a first delay time from application of a first excitation pulse, and a second pulse sequence in which acquisition of a second set of MR signals is started after a second delay time from application of a second excitation pulse, the second delay time being different from the first delay time; acquire first and second sets of MR signals by causing the scanner to apply the first and second pulse sequences to the object; generate a combined dataset by averaging a first dataset based on the first set of MR signals and a second dataset based on the second set of MR signals; and reconstruct an MR image based on the combined dataset.

In a computer-implemented method of training a machine learning based processor, the processor can be trained to derive image data from signal data sets of multiple spin echo sequences. The trained processor can be configured to perform image processing for Magnetic Resonance Imaging (MRI) to derive the image data.

A system and method are provided for producing at least one of an image or a map of a subject includes controlling a magnetic resonance imaging (MRI) system to perform a pulse sequence that includes a phase increment of an RF pulse selected to induce a phase difference between two echoes at different echo times (TE). The method also includes controlling the MRI system to acquire MR data corresponding to at least the two echoes at different TEs, deriving a static magnetic field (B0) map of the MRI system using the MR data corresponding to the two echoes, and using the B0 map and MR data from at least one of the two echoes, generate a map of T2 of the subject.

Phase-incrementing MRSI (pi-MRSI) method has resolved overlapping biomarker images in the presence of a read-gradient. On a Bruker 9.4T MRI spectrometer, the pi-SEE-HSelMQC sequence was implemented. The choline-selective and lactate CH-selective RF pulses were phase incremented by 10° in opposite signs, synchronized with the phase-encoding steps. The lactate and choline images from a yogurt phantom displayed opposite image offsets without image overlapping. In vivo one-dimensional pi-SEE-HSelMQC CSI images of lactate and choline, acquired from the MDA-MB-231 human breast cancer xenograft in a nude mouse, as well as two-dimensional pi-SEE-HSelMQC imaging of lactate and choline acquired from the PC3 human prostate cancer xenograft in a nude mouse, also had opposite image offsets, shifted away from the spurious residual water signals in the image center. The pi-SEE-HSelMQC method completely suppresses lipid and water with potential clinical applications in disease diagnosis and therapeutic interventions.

Disclosed is a medical imaging system (100, 300). The execution of machine executable instructions (120) causes a processor (104) to: receive (200) measured magnetic resonance imaging data (122) descriptive of a first region of interest (307) of a subject (318); receive (202) a B0 map (124), a T1 map (126), a T2 map (128), and a magnetization map (130) each descriptive of a second region of interest (309) of the subject; receive (204) pulse sequence commands (132); calculate (206) a simulated magnetic resonance image (136) of an overlapping region of interest (311) using at least the B0 map, the T1 map, the T2 map, the magnetization map, and the pulse sequence commands as input to a Bloch equation model (134); and reconstruct (208) a corrected magnetic resonance image from the measured magnetic resonance imaging data for the overlapping region of interest by solving an inverse problem. The inverse problem comprises an optimization of a cost function and a regularization term formed from the simulated magnetic resonance image.

According to one embodiment, an MRI apparatus includes a data acquiring unit and processing circuitry. The data acquiring unit acquires MR signals for imaging according to data acquiring conditions for acquiring MR signals multiple times following one excitation. The data acquiring unit also acquires reference MR signals for phase correction of real space data for imaging. The real space data are generated based on the MR signals for imaging. The processing circuitry is configured to calculate a phase error, in a real space region, of reference real space data and generate MR image data based on the MR signals for imaging with the phase correction of the real space data for imaging based on the calculated phase error. The reference real space data are generated based on the reference MR signals. The real space region is determined based on conditions of acquiring the reference MR signals or the like.