A method of SENSE reconstruction including: constructing a coil sensitivity encoding matrix; inversing of the coil sensitivity encoding matrix using a QR decomposition algorithm; and multiplying an inverse of the receiver coil sensitivity encoding matrix with an under-sampled data using a central processing unit (CPU) and using a GPU residing on a host computer to further decrease computation time.

A method including: constructing coil sensitivity encoding matrix; inversing of the coil sensitivity encoding matrix using Left Inverse method; and multiplying inverse of coil sensitivity encoding matrix with an under-sampled data matrix using a GPU residing on a host computer.

A computer system that performs a sparsity technique is described. During operation, the computer system accesses or obtains information associated with non-invasive measurements performed on at least an individual, historical non-invasive measurements, and a dictionary of predetermined features or basis functions associated with the historical non-invasive measurements. Note that the non-invasive measurements and the historical non-invasive measurements may include or correspond to magnetic resonance (MR) measurements. For example, the MR measurements may include magnetic resonance imaging (MRI) scans. Then, the computer system updates the dictionary of predetermined features based at least in part on the non-invasive measurements and the historical non-invasive measurements, where the updating includes performing a minimization technique with a cost function having an L2-norm term and an L0-norm term. Next, the computer system determines weights associated with features in the updated dictionary of predetermined features based at least in part on the non-invasive measurements.

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.

During obtaining a sensitivity distribution in a k-space, data based on which the sensitivity distribution is obtained is expanded with a mirror image to create an expanded image to prevent spectrum leakage, and the sensitivity distribution is stably calculated. During obtaining the sensitivity distribution in the k-space, image data based on which the sensitivity distribution is obtained is inverted as a mirror image to be made into the expanded image, the expanded image is transformed into k-space data, and a frequency component (frequency space data) of the sensitivity distribution is calculated. A region corresponding to the original image data is clipped from the calculated frequency space data, and the sensitivity distribution is obtained.

A method for performing magnetic resonance imaging on a subject comprises obtaining undersampled imaging data, extracting one or more temporal basis functions from the imaging data, extracting one or more preliminary spatial weighting functions from the imaging data, inputting the one or more preliminary spatial weighting functions into a neural network to produce one or more final spatial weighting functions, and multiplying the one or more final spatial weighting functions by the one or more temporal basis functions to generate an image sequence. Each of the temporal basis functions corresponds to at least one time-varying dimension of the subject. Each of the preliminary spatial weighting functions corresponds to a spatially-varying dimension of the subject. Each of the final spatial weighting functions is an artifact-free estimation of the one of the one or more preliminary spatial weighting functions.

A method detects phase-encoding ghosting in a MR image of an object to be imaged and mitigates the corresponding artifact in the MR image. The method includes acquiring MRI raw data of the object by a MRI apparatus. The MRI apparatus has multiple receiver channels for acquiring the MRI raw data. An artifact map of at least one part of the object to be imaged is calculated from the MRI raw data, the artifact map is configured for highlighting artifact appearing in the MR image. An outlier mask representing detected phase-encoding artifact is created in the artifact map. The phase-encode ghosting in the MR image is mitigated by using the previously obtained artifact map and the outlier mask for obtaining an improved MR image.

Magnetic resonance imaging (MRI) systems and methods to effect improved MR image reconstruction for undersampled data acquisitions are described. The improved MR image reconstruction is performed by iteratively using compressed sensing to reconstruct an MR image based upon at least one sensitivity map by minimizing a predetermined function which is based upon the MR image and coefficients of the at least one sensitivity map, and updating the at least one sensitivity map by minimizing the predetermined function.

The invention relates to a method for acquiring a magnetic resonance image dataset of a subject, a magnetic resonance imaging system and a non-transitory computer-readable medium. The method comprises the steps: (a) determining scan conditions relating to an imaging protocol which is to be carried out on the subject; (b) based on the scan conditions and/or on predetermined reference parameters, determining whether at least one imaging preparation procedure may be omitted or accelerated to have a shortened duration; (c) depending on the determination of step (b), omitting or carrying out the least one imaging preparation procedure at the standard or at the shortened duration; (d) carrying out the imaging protocol in order to acquire the magnetic resonance image dataset.

A magnetic resonance imaging system (1) includes a denoising unit (24), and a reconstruction unit (20). The denoising unit (24) denoises a partial image and provides a spatially localized measure of a denoising effectivity. The reconstruction unit (20) iteratively reconstructs an output image from the received MR data processed with a Fast Fourier Transform (FFT), and in subsequent iterations includes the denoised partial image and the spatially localized measure of the denoising effectivity.