9 results about "Parallel magnetic resonance imaging" patented technology

The invention discloses a single-coil multi-layer parallel magnetic resonance imaging method based on multiple excitation in a low field, and the method comprises the steps: achieving the multi-layer parallel excitation through a multi-band pulse, and carrying out the 0-pi phase modulation of the multi-band pulse; constructing a fast spin echo sequence of secondary phase modulation; performing imaging by using the fast spin echo sequence subjected to secondary phase modulation; and reconstruction is carried out through an odd-even echo classification method, and a scanning result graph is obtained. Aiming at the common problem of low signal to noise ratio of low-field magnetic resonance imaging in practical application, based on hardware characteristics of a single coil of low-field magnetic resonance equipment and actual requirements of repeated scanning, a series of SMS related technologies such as an FSE fast spin echo sequence, Hadamard pulse coding, multi-band pulse and secondary phase modulation are combined; and the signal-to-noise ratio of the low-field FSE sequence is effectively improved.

The invention relates to a regularization-based parallel magnetic resonance imaging reconstruction method and a regularization-based parallel magnetic resonance imaging reconstruction system, which are used for realizing parallel magnetic resonance imaging reconstruction with high generalization, high stability and high convergence. The method comprises the steps of obtaining a to-be-reconstructed MRI image and an undersampling observation image, and obtaining an objective function of a typical ill-conditioned inverse problem according to the to-be-reconstructed MRI image and the undersampling observation image; setting regularization parameters in the objective function of the typical ill-conditioned inverse problem by adopting a deep learning technology to obtain an objective function fused with deep learning enhancement; and solving the fusion deep learning enhanced target function to obtain a final reconstructed MRI image.

A computer-implemented method for evaluating an image data set that is based on a medical imaging method, including: acquiring the image data set; acquiring a body region depicted in the image data set; processing the image data set using a processing algorithm, wherein at least one processing parameter of the processing algorithm is specified depending on the determined body region; and / or checking a trigger condition, whose fulfillment depends on whether, for at least one area of image data, which is reconstructed depending on the image data set, local geometric factors of the parallel magnetic resonance imaging used as the medical imaging method indicate a sufficiently strong local reduction in the signal-to-noise ratio, wherein an anatomical feature is assigned to the respective area depending on the body region and the image data set when the trigger condition is fulfilled.

The application relates to an improved ESPIRiT reconstruction method based on outer product effectiveness and dictionary learning, and belongs to the technical field of magnetic resonance imaging. ESPIRiT is a parallel magnetic resonance imaging technology for estimating multiple sets of sensitivity maps to realize image reconstruction by using K-space calibration information. The application is based on an ESPIRiT model, combines an SOUPDIL regular term containing an L0 norm, and proposes an improved ESPIRiT reconstruction algorithm based on SOUPDIL, named SOUPDIL-ESPIRiT, uses FISTA technology for solving, and realizes parallel magnetic resonance imaging reconstruction through two steps of dictionary learning and image updating. Experimental results show that the application can better promote image sparsity, eliminate image reconstruction noise and artifacts, significantly improve the precision of the reconstructed image, and has the ability of better retaining image texture details and edge contour information.

The present invention relates to a fast parallel imaging reconstruction method based on SIDWT and iterative self-consistency, and belongs to the field of magnetic resonance imaging technology. Parallel magnetic resonance imaging reconstruction has been a research hotspot in recent years. Based on the SIDWT transform, the present invention introduces the L1 norm regularization term of the transform coefficient into the iterative self-consistency parallel imaging reconstruction model in the K-space domain, and proposes an efficient reconstruction method named fSIDWT‑SPIRiT. This method aims at complex optimization problems containing data consistency terms, calibration consistency terms and L1 norm regularization terms. The data consistency terms and calibration consistency terms are first merged, and then the projected fast iterative thresholding method (projected Fast Iterative Shrinkage‑Thresholding Algorithm, pFISTA) is used to solve them. Experimental results show that the proposed fSIDWT‑SPIRiT method not only provides higher image reconstruction quality, but also effectively improves the convergence speed and reduces the image reconstruction time.

The present application relates to a kind of parallel magnetic resonance imaging fast reconstruction method based on transform learning and structured low rank model, belong to magnetic resonance imaging technical field.The present application is based on SAKE (Simultaneous Auto-calibrating and K-space Estimation) reconstruction framework, combined with joint sparse transform learning (Joint Transform Learning, JTL) regular term proposes a kind of parallel magnetic resonance imaging fast reconstruction model, named JTLSAKE.The proposed method is solved using alternating direction method of multipliers (alternating direction method of multipliers, ADMM), and introduces optimized gradient method (Optimized Gradient Method, OGM) to improve convergence speed, finally using graphics processing unit (Graphics Processing Unit, GPU) to accelerate.Experiment compares the parallel imaging JTL-PLORAKS model combined with JTL regular term.The experimental results show that JTLSAKE can obtain the reconstruction quality comparable with JTL-PLORAKS, and reconstruction speed is increased by 85 times.

Disclosed herein is a method comprising: receiving (200) an initial pulse sequence command (122); receiving (202) calibration data (124); receiving (204) a volume of interest (126); receiving (206) a slice thickness (128) of the at least one slice stack; and receiving (208) a stack-related stack orientation (130) of the at least one slice stack. The method further includes performing, for a slice, the following: determining (210) a field of view (132) for the slice using the volume of interest, the slice thickness, and the stack orientation of the stack of slices; determining (212) a readout direction (136) for the slice and a phase encoding direction for the slice using the calibration data to optimize image metrics within the slice; and constructing (214) a slice-specific pulse sequence command (140) by modifying the initial pulse sequence command using the field of view, the readout direction, and the phase encoding direction. A system for performing the method is disclosed.

A computer-implemented method for evaluating an image data set (22) based on a medical imaging procedure, comprising the steps of: - obtaining the image data set (22), - obtaining a body region (23) represented by the image data set (22), and - processing the image data set (22) by a processing algorithm (24), wherein at least one processing parameter (25, 26) of the processing algorithm (24) is specified depending on the determined body region (23), and / or - checking a trigger condition (46), the fulfillment of which depends on whether, for at least one area (49) of image data (47) reconstructed depending on the image data set (22), local geometry factors (48) of a parallel magnetic resonance imaging used as the medical imaging procedure indicate a sufficiently strong local reduction of the signal-to-noise ratio.where, upon fulfillment of the trigger condition (46), an anatomical feature (51-55) is assigned to the respective area (49) depending on the body region (23) and the image data set.

Disclosed herein is a method comprising: receiving (200) initial pulse sequence commands (122); receiving (202) calibration data (124); receiving (204) a volume of interest (126); receiving (206) a slice thickness (128) for at least one stack of slices; and receiving (208) a stack dependent stack orientation (130) for the at least one stack of slices. The method further comprises performing the following for slices: determining (210) a field of view (132) for a slice using the volume of interest, the slice thickness, and the stack orientation of the stack of slices; determining (212) a readout direction (136) for the slice and a phase encoding direction for the slice using the calibration data to optimize an image metric within the slice; and constructing (214) slice specific pulse sequence commands (140) by modifying the initial pulse sequence commands using the field of view, the readout direction, and the phase encoding direction. Systems are disclosed performing the method.