Abstract: A method and system for reconstructing magnetic resonance (MR) images, the method including the steps of: receiving an under-sampled MR image, the under-sampled MR image being transformed from under-sampled k-spaced data; classifying intensity of each pixel in the under-sampled MR image to one of a plurality of predetermined quantized values of intensity by using a neural network; and generating a reconstructed MR image based on the classified quantized value of the intensity for each pixel in the under-sampled MR image.

Abstract: The application relates to a battery pack case and a battery pack. The battery pack case includes: a bottom plate and a side plate connected with the bottom plate, the bottom plate and the side plate surround to form an accommodating portion configured to accommodate a unit cell; the bottom plate is provided with a plurality of first grooves and a plurality of second grooves opening toward the accommodating portion, the plurality of first grooves are spaced apart from each other, the plurality of second grooves are spaced apart from each other, and the first grooves and the second grooves are arranged to cross each other. The bottom plate of the battery pack itself has good rigidity, is not prone to warp deformation, and can prevent the overflow of structural glue from contaminating the wiring harness or electrical components.

Abstract: A method and system for reducing or removing motion artefacts in magnetic resonance (MR) images, the method including the steps of: receiving a motion corrupted MR image; determining a corrected intensity value for each pixel in the motion corrupted MR image by using a neural network; and generating a motion corrected MR image based on the determined corrected intensity values for the pixels in the motion corrupted MR image.

Abstract: A method and system for reconstructing magnetic resonance (MR) images, the method including the steps of: receiving an under-sampled MR image, the under-sampled MR image being transformed from under-sampled k-spaced data; classifying intensity of each pixel in the under-sampled MR image to one of a plurality of predetermined quantized values of intensity by using a neural network; and generating a reconstructed MR image based on the classified quantized value of the intensity for each pixel in the under-sampled MR image.

Abstract: A method and system for reducing or removing motion artefacts in magnetic resonance (MR) images, the method including the steps of: receiving a motion corrupted MR image; determining a corrected intensity value for each pixel in the motion corrupted MR image by using a neural network; and generating a motion corrected MR image based on the determined corrected intensity values for the pixels in the motion corrupted MR image.

Abstract: Method for susceptibility weighted magnetic resonance imaging of vasculature, the method comprising the following steps: —acquiring multi-echo data containing a time-of-flight signal in at least the first echo (S1); —identifying voxels belonging to arteries from the data (S2); and—generating corresponding information on artery presence (S3); The invention further relates to a corresponding system (10) for susceptibility weighted magnetic resonance imaging of vasculature.

Abstract: The present invention relates to a method for side-band suppression in a Magnetic Resonance imaging, MRI, system (100), the method comprising providing a first multiband RF pulse for simultaneously exciting at least two slices in a subject (118) at a first and a second frequency band (301,303) and to acquire using the MRI system (100) signals (307, 308) from the excited two slices and at least one additional signal (309) at a third frequency band (305), the additional signal (309) resulting from a sideband excitation of a slice different from the two slices; using the first multiband RF pulse for determining the additional signal (309); deriving a pre-compensating term from the first multiband RF pulse and the additional signal (309), adding the pre-compensating term to the first multiband RF pulse to obtain a second multiband RF pulse, thereby replacing the first multiband RF pulse by the second multiband RF pulse for suppressing at least part of the additional signal (309).

Abstract: An object (10) placed in an examination volume of a MR device (1) is subject to an imaging sequence including multi-slice RF pulses for simultaneously exciting two or more spatially separate image slices. MR signals are received in parallel via a set of RF coils (11, 12, 13) having different spatial sensitivity profiles within the examination volume. An MR image is reconstructed for each image slice from the acquired MR signals. MR signal contributions from the different image slices are separated on the basis of the spatial sensitivity profiles of the RF coils (11, 12, 13). Side-band artifacts, namely MR signal contributions from regions excited by one or more side-bands of the multi-slice RF pulses, are suppressed in the reconstructed MR images on the basis of the spatial sensitivity profiles of the RF coils (11, 12, 13).

Abstract: A method of parallel MR imaging includes subjecting the portion of the body (10) to an imaging sequence of at least one RF pulse and a plurality of switched magnetic field gradients. The MR signals are acquired in parallel via a plurality of RF coils (11, 12, 13) having different spatial sensitivity profiles within the examination volume. The method further includes deriving an estimated ghost level map from the acquired MR signals and from spatial sensitivity maps of the RF coils (11, 12, 13), and reconstructing a MR image from the acquired MR signals, the spatial sensitivity maps, and the estimated ghost level map.

Abstract: A magnetic resonance imaging (MRI) system (600) obtains magnetic resonance (MR) images of a volume. The MRI system includes at least one controller (610) configured to perform a preparation scan (103, 301) to acquire preparation echo phase information (105, PEPI) for a plurality of dynamics of a scan (300); output a plurality of pulse sequences (200), each pulse sequence is configured for a corresponding dynamic of the plurality of dynamics of the scan and includes a navigator sequence (204) and an image sequence (206); acquire navigation and image information (111, 117) for each corresponding pulse sequence of the plurality of pulse sequences; and/or form corrected image information (125) by correcting echo phase information in accordance with the preparation echo phase information, correcting at least one of gradient delay or frequency offset of the image information in accordance with the navigation information.

Abstract: An object (10) in an examination volume of a MR device (1) is imaged with improved susceptibility weighted contrast. The imaging includes the steps of: a) generating at least two echo signals at different echo times by subjecting the object (10) to an imaging sequence of RF pulses and switched magnetic field gradients; b) acquiring the echo signals; c) repeating steps a) and b) for a plurality of phase encoding steps; d) reconstructing an intermediate MR image for each echo time from the acquired echo signals; and e) generating a susceptibility weighted MR image by computing, for each voxel of the susceptibility weighted MR image, a non-linear combination of the voxel values of the intermediate MR images at the respective image position. The non-linear combination emphasizes lower voxel magnitude values more than higher voxel magnitude values.

Abstract: The invention relates to a method of parallel MR imaging. The method comprises the steps of: a) subjecting the portion of the body (10) to an imaging sequence of at least one RF pulse and a plurality of switched magnetic field gradients, wherein MR signals are acquired in parallel via a plurality of RF coils (11, 12, 13) having different spatial sensitivity profiles within the examination volume, b) deriving an estimated ghost level map from the acquired MR signals and from spatial sensitivity maps of the RF coils (11, 12, 13), c) reconstructing a MR image from the acquired MR signals, the spatial sensitivity maps, and the estimated ghost level map. Moreover, the invention relates to a MR device (1) and to a computer program for a MR device (1).

Abstract: Method for susceptibility weighted magnetic resonance imaging of vasculature, the method comprising the following steps: —acquiring multi-echo data containing a time-of-flight signal in at least the first echo (S1); —identifying voxels belonging to arteries from the data (S2); and —generating corresponding information on artery presence (S3); The invention further relates to a corresponding system (10) for susceptibility weighted magnetic resonance imaging of vasculature.

Abstract: The invention relates to a method of MR imaging of an object (10) placed in an examination volume of a MR device (1). The method comprises the steps of: subjecting the object (10) to an imaging sequence comprising multi-slice RF pulses for simultaneously exciting two or more spatially separate image slices, acquiring MR signals, wherein the MR signals are received in parallel via a set of RF coils (11, 12, 13) having different spatial sensitivity profiles within the examination volume, and reconstructing a MR image for each image slice from the acquired MR signals, wherein MR signal contributions from the different image slices are separated on the basis of the spatial sensitivity profiles of the RF coils (11, 12, 13), and wherein side-band artefacts, namely MR signal contributions from regions excited by one or more side-bands of the multi-slice RF pulses, are suppressed in the reconstructed MR images on the basis of the spatial sensitivity profiles of the RF coils (11, 12, 13).

Abstract: The present invention relates to a method for side-band suppression in a Magnetic Resonance imaging, MRI, system (100), the method comprising providing a first multiband RF pulse for simultaneously exciting at least two slices in a subject (118) at a first and a second frequency band (301,303) and to acquire using the MRI system (100) signals (307, 308) from the excited two slices and at least one additional signal (309) at a third frequency band (305), the additional signal (309) resulting from a sideband excitation of a slice different from the two slices; using the first multiband RF pulse for determining the additional signal (309); deriving a pre-compensating term from the first multiband RF pulse and the additional signal (309), adding the pre-compensating term to the first multiband RF pulse to obtain a second multiband RF pulse, thereby replacing the first multiband RF pulse by the second multiband RF pulse for suppressing at least part of the additional signal (309).

Abstract: The invention provides for a medical apparatus (300, 400) for generating a corrected magnetic resonance image (326, 502, 600, 700).

Abstract: The invention relates to a method of MR imaging of an object (10) placed in the examination volume of a MR device (1). It is an object of the invention to provide a method of MR imaging with improved susceptibility weighted contrast. The method of the invention comprises the steps of: a) generating at least two echo signals at different echo times by subjecting the object (10) to an imaging sequence of RF pulses and switched magnetic field gradients; b) acquiring the echo signals; c) repeating steps a) and b) for a plurality of phase encoding steps; d) reconstructing an intermediate MR image for each echo time from the acquired echo signals; and e) generating a susceptibility weighted MR image by computing, for each voxel of the susceptibility weighted MR image, a non-linear combination of the voxel values of the intermediate MR images at the respective image position, wherein the non-linear combination emphasizes lower voxel magnitude values more than higher voxel magnitude values.

Abstract: A magnetic resonance imaging (MRI) system (600) for obtaining magnetic resonance (MR) images of a volume. The MRI system may include at least one controller (610) which may be configured to perform a preparation scan (103, 301) to acquire preparation echo phase information (105, PEPI) for a plurality of dynamics of a scan (300); output a plurality of pulse sequences (200) each of which is configured for a corresponding dynamic of the plurality of dynamics of the scan and comprises a navigator sequence (204) and an image sequence (206); acquire navigation and image information (111, 117) for each corresponding pulse sequence of the plurality of pulse sequences; and/or form corrected image information (125) by correcting echo phase information of the image information in accordance with the preparation echo phase information, correcting at least one of gradient delay and frequency offset of the image information in accordance with the navigation information.