Abstract: The present disclosure relates to a medical imaging method, comprising: receiving (201) a set of subject parameters descriptive of a subject; in response to inputting (203) the set of subject parameters into a trained deep neural network, DNN, receiving (205) from the trained DNN a predicted task; presenting the task to the subject; controlling (207) an MRI system (700) for acquiring fMRI data from the subject in response to the predicted task performed by the subject during the acquisition.

Abstract: Disclosed herein is a medical system (100, 300) comprising a memory (110) storing machine executable instructions (120) and an image generating neural network (122). The image generating neural network is configured for outputting synthetic magnetic resonance image data (128) in response to receiving reference magnetic resonance image data (126) as input. The synthetic magnetic resonance image data is a simulation of magnetic resonance image data acquired according to a first configuration of a magnetic resonance imaging system when the reference magnetic resonance image data is acquired according to a second configuration of the magnetic resonance imaging system.

Abstract: The invention provides for a medical imaging system (100, 400) comprising a memory (110) storing machine executable instructions (120) and a configured artificial neural network (122). The medical imaging system further comprises a processor (104) configured for controlling the medical imaging system. Execution of the machine executable instructions causes the processor to receive (200) magnetic resonance imaging data (124), wherein the magnetic resonance imaging data is BOLD functional magnetic resonance imaging data descriptive of a time dependent BOLD signal (1100) for each of a set of voxels. Execution of the machine executable instructions further causes the processor to construct (202) a set of initial signals (126) by reconstructing the time dependent BOLD signal for each of the set of voxels using the magnetic resonance imaging data.

Abstract: The invention relates to a method of MR imaging of an object positioned in an examination volume of a MR device (1). It is an object of the invention to enable efficient silent ZTE imaging with self-refocusing. The method of the invention comprises the steps of:—specification of a set of radial k-space spokes to cover a spherical k-space volume;—selection of subsets of a predetermined number of spokes from the specified set so that the concatenation of the spokes contained in each of the subsets forms a closed trajectory in k-space, wherein the selection of the subsets involves optimizing a cost function;—subjecting the object (10) to a zero echo time imaging sequence, wherein each of the subsets of spokes is acquired as a sequence of gradient echo signals; and—reconstructing an MR image from the acquired spokes. Moreover, the invention relates to a MR device and to a computer program for a MR device.

Abstract: The invention relates to a method of MR imaging of an object (10) positioned in an examination volume of a MR device (1). It is an object of the invention to enable efficient and high-quality non-Cartesian MR imaging, even in situations of strong B0 inhomogeneity. In accordance with the invention, the method comprises: —subjecting the object to an imaging sequence comprising at least one RF excitation pulse and modulated magnetic field gradients, —acquiring MR signals along at least one non-Cartesian k-space trajectory, —reconstructing an MR image from the acquired MR signals, and —detecting one or more mal-sampling artefacts caused by B0 inhomogeneity induced insufficient k-space sampling in the MR image using a deep learning network. Moreover, the invention relates to a MR device (1) and to a computer program.

Abstract: The invention relates to a method of Dixon-type MR imaging. The object (10) is subjected to at least two shots of an imaging sequence, each shot comprising an excitation RF pulse followed by a series of refocusing RF pulses, wherein at least a pair of phase encoded echoes, a first echo at a first echo time and a second echo at a second echo time, is generated in each time interval between two consecutive refocusing RF pulses. Two sets of echo signal pairs, a first set and a second set, are acquired using in bipolar pairs of readout magnetic gradients in two respective shots of the imaging sequence. The bipolar pair of readout magnetic field gradients in the acquisition of the second set has an opposite polarity to that of the bipolar pair of readout magnetic field gradients in the acquisition of the first set.

Abstract: Disclosed herein is a medical system (100, 300) comprising a memory (110) storing machine executable instructions (120) and an image generating neural network (122). The image generating neural network is configured for outputting synthetic magnetic resonance image data (128) in response to receiving reference magnetic resonance image data (126) as input. The synthetic magnetic resonance image data is a simulation of magnetic resonance image data acquired according to a first configuration of a magnetic resonance imaging system when the reference magnetic resonance image data is acquired according to a second configuration of the magnetic resonance imaging system.

Abstract: The invention relates to a method of MR imaging. It is an object of the invention to provide an improved B1 mapping method that is less affected by T1 relaxation. The invention proposes that a first stimulated echo imaging sequence (25) is generated comprising at least two preparation RF pulses (?) radiated during a first preparation period (21) and a sequence of reading RF pulses (?) radiated during a first acquisition period (22) temporally subsequent to the first preparation period (21). A first set of FID signals (IFID) and a first set of stimulated echo signals (ISTE) are acquired during the first acquisition period (22). A second stimulated echo imaging sequence (27) is generated comprising again at least two preparation RF pulses (?) radiated during a second preparation period (21) and a sequence of reading RF pulses (?) radiated during a second acquisition period (22) temporally subsequent to the second preparation period (21).

Abstract: Abstract: Disclosed herein is a medical system comprising a memory (110) storing machine executable instructions (120) and a trained neural network (122). The trained neural network is configured to output corrected magnetic resonance image data (130) in response to receiving as input a set of magnetic resonance images (126) each having a different spatially constant frequency off-resonance factor.

Abstract: Disclosed herein is a method of training a neural network (214) to perform a SENSE magnetic resonance imaging reconstruction. The method comprises receiving (100) initial training data, wherein the initial training data comprises sets of initial training complex channel images each paired with a predetermined number of initial ground truth images. The method further comprises generating (102) additional training data by performing data augmentation on the initial training data such that the data augmentation comprises adding a distinct phase offset to each of the set of initial training complex channel images during generation of the sets of additional training complex channel images. The method further comprises inputting (104) the sets of additional training complex channel images into the neural network and receiving in response a predetermined number of output training images and performing deep learning using the output training images.

Abstract: The invention relates to a method of MR imaging of an object positioned in an examination volume of a MR device (1). It is an object of the invention to enable efficient silent ZTE imaging with self-refocusing. The method of the invention comprises the steps of:—specification of a set of radial k-space spokes to cover a spherical k-space volume;—selection of subsets of a predetermined number of spokes from the specified set so that the concatenation of the spokes contained in each of the subsets forms a closed trajectory in k-space, wherein the selection of the subsets involves optimizing a cost function;—subjecting the object (10) to a zero echo time imaging sequence, wherein each of the subsets of spokes is acquired as a sequence of gradient echo signals; and—reconstructing an MR image from the acquired spokes. Moreover, the invention relates to a MR device and to a computer program for a MR device.

Abstract: The present disclosure relates to a medical imaging method, comprising: receiving (201) a set of subject parameters descriptive of a subject; in response to inputting (203) the set of subject parameters into a trained deep neural network, DNN, receiving (205) from the trained DNN a predicted task; presenting the task to the subject; controlling (207) an MRI system (700) for acquiring fMRI data from the subject in response to the predicted task performed by the subject during the acquisition

Abstract: The invention relates to a method of MR imaging of an object (10) positioned in an examination volume of a MR device (1). It is an object of the invention to enable efficient and high-quality non-Cartesian MR imaging, even in situations of strong B0 inhomogeneity. In accordance with the invention, the method comprises: —subjecting the object to an imaging sequence comprising at least one RF excitation pulse and modulated magnetic field gradients, —acquiring MR signals along at least one non-Cartesian k-space trajectory, —reconstructing an MR image from the acquired MR signals, and —detecting one or more mal-sampling artefacts caused inhomogeneity induced insufficient k-space sampling in the MR image using a deep learning network. Moreover, the invention relates to a MR device (1) and to a computer program.

Abstract: A method of operating a magnetic resonance imaging system (10) with regard to acquiring multiple-phase dynamic contrast-enhanced magnetic resonance images, the method comprising steps of acquiring (48) a first set of magnetic resonance image data (xpre) prior to administering a contrast agent to the subject of interest (20), by employing a water/fat magnetic resonance signal separation technique, determining (52) a first image of the spatial distribution of fat (Ipre) of at least the portion of the subject of interest (20), acquiring (50) at least a second set of magnetic resonance image data (x2) of at least the portion of the subject of interest (20) after administering the contrast agent to the subject of interest (20), by employing a water/fat magnetic resonance signal separation technique, determining (54) at least a second image of the spatial distribution of fat (I2ph) of at least the portion of the subject of interest (20), applying (56) an image registration method to the second image of the spatial

Abstract: The invention provides for a medical imaging system (100, 400) comprising a memory (110) storing machine executable instructions (120) and a configured artificial neural network (122). The medical imaging system further comprises a processor (104) configured for controlling the medical imaging system. Execution of the machine executable instructions causes the processor to receive (200) magnetic resonance imaging data (124), wherein the magnetic resonance imaging data is BOLD functional magnetic resonance imaging data descriptive of a time dependent BOLD signal (1100) for each of a set of voxels. Execution of the machine executable instructions further causes the processor to construct (202) a set of initial signals (126) by reconstructing the time dependent BOLD signal for each of the set of voxels using the magnetic resonance imaging data.

Abstract: The invention provides for a method of operating a magnetic resonance imaging system for imaging a subject. The method comprises acquiring (700) tagged magnetic resonance data (642) and a first portion (644) of fingerprinting magnetic resonance data by controlling the magnetic resonance imaging system with tagging pulse sequence commands (100). The tagging pulse sequence commands comprise a tagging inversion pulse portion (102) for spin labeling a tagging location within the subject. The tagging pulse sequence commands comprise a background suppression portion (104). The background suppression portion comprises MRF pulse sequence commands for acquiring fingerprinting magnetic resonance data according to a magnetic resonance fingerprinting protocol. The tagging pulse sequence commands comprise an image acquisition portion (106).

Abstract: The invention provides for a magnetic resonance imaging system (100) for acquiring MRF magnetic resonance data (144) from a subject (118) within a region of interest (109). The magnetic resonance imaging system comprises a processor (130) for controlling the magnetic resonance imaging system and a memory (134) for storing machine executable instructions (140) and MRF pulse sequence commands (142). The MRF pulse sequence commands are configured for controlling the magnetic resonance imaging system to acquire the MRF magnetic resonance data according to a magnetic resonance fingerprinting protocol.

Abstract: The invention provides for a magnetic resonance imaging system (100) for acquiring MRF magnetic resonance data (144) from a subject (118) within a region of interest (109). The magnetic resonance imaging system comprises a processor (130) for controlling the magnetic resonance imaging system and a memory (134) for storing machine executable instructions (140) and MRF pulse sequence commands (142). The MRF pulse sequence commands are configured for controlling the magnetic resonance imaging system to acquire the MRF magnetic resonance data according to a magnetic resonance fingerprinting protocol.

Abstract: The invention provides for a magnetic resonance imaging system (100, 300, 500) with a gradient coil system (110, 112, 113) that comprises a set of gradient coils (110) configured for generating a gradient, a gradient coil amplifier (112), and a current sensor system (113) configured for measuring current sensor data (146) descriptive of the electrical current supplied to each of the set of gradient coils. Execution of the machine executable instructions causes a processor to: control (200) the magnetic resonance imaging system with the pulse sequence commands (142) to acquire magnetic resonance imaging data; record (202) the current sensor data during the acquisition of the magnetic resonance imaging data; calculate (204) a corrected k-space trajectory (150) using the current sensor data and a gradient coil transfer function (148); and reconstruct (206) a corrected magnetic resonance image (152) using the magnetic resonance imaging data and the corrected k-space trajectory.

Abstract: A medical instrument includes a magnetic resonance (MR) imaging system with an imaging zone and a gradient coil system with three orthogonal gradient coils. A processor controls the medical instrument to: repeatedly control the MR imaging system with calibration pulse sequence commands to acquire the MR calibration data for multiples slices using at least one of the three orthogonal gradient coils to generate the slice select gradient magnetic field; compute a Fourier transform of the MR calibration data for each of the voxels of the multiple slices in the phase encoding directions; compute an expansion of the Fourier transformed MR calibration data into spherical harmonics; and calculate a three-dimensional gradient impulse response function for the at least one of the three orthogonal gradient coils using the expansion into spherical harmonics.