18 results about "Coil sensitivity" patented technology

Image reconstruction systems and methods include providing a sensitivity map of a coil of a magnetic resonance imaging (MRI) system to a neural network. The systems and methods also include providing interleaved k-space data to the neural network, where the interleaved k-space data includes partial k-space data interleaved with zero or synthetic k-space data to provide an extended field of view (FOV) that is different than a FOV utilized during acquisition of the partial k-space data, where the partial k-space data is obtained during a scan of a region of interest of the MRI system. The systems and methods also include outputting a final reconstructed MR image from the neural network based at least on the sensitivity map and the interleaved k-space data, where the final reconstructed MR image includes the FOV utilized during the acquisition of the partial k-space data.

This invention discloses a rapid online dynamic magnetic resonance imaging (MRI) reconstruction method based on subspace tracking, relating to the field of medical image processing technology. The method includes: Step 1, obtaining a coil sensitivity map from pre-scanned full-sample data and constructing an encoding operator using an undersampling template; Step 2, decomposing the image into two components and sequentially solving for the component values ​​corresponding to each frame, thereby rapidly acquiring the image of the current frame. This method can be applied to interventional procedures guided by MRI images. It achieves rapid scanning through undersampling and rapid reconstruction of undersampling data using the proposed online reconstruction algorithm. Physicians can promptly determine the position of catheters, guidewires, or puncture needles during intervention based on the rapidly reconstructed MRI image.

The invention relates to a magnetic resonance imaging method and device. The method comprises the following steps: performing magnetic resonance scanning on a target object according to a preset sampling track to obtain multi-phase original scanning data of the target object; the original scanning data of different periods comprises scanning data of different slice layers of the target object; determining a coil sensitivity graph according to the original scanning data of each phase, and reconstructing the original scanning data of each phase according to the coil sensitivity graph to obtain a multi-phase scanning image of the target object; and performing magnetic resonance imaging based on the multi-phase scanning image. According to the method, the static high-definition imaging requirement and the dynamic high-definition imaging requirement can be met at the same time through one scanning process, and the multi-phase scanning image obtained through reconstruction can be suitable for various different imaging modes, so that magnetic resonance images in different imaging modes are obtained; the magnetic resonance imaging efficiency can be improved, and the magnetic resonance imaging effect can also be improved.

In a method for measuring brain free water content, in response to an RF excitation field generated on the basis of a magnetic resonance fingerprinting sequence and applied to the brain, an equilibrium magnetization mixed term (M0) signal is acquired from radiation emitted by each excited voxel of the brain, to obtain an M0 value of each voxel of the brain; a receive coil sensitivity (RP) value of each voxel of the brain is acquired; the M0 value of each voxel of the brain is divided by the RP value of the corresponding voxel to obtain a proton density (PD) value of each voxel of the brain; a PD value of cerebrospinal fluid is taken to be a reference PD value; and the PD value of each voxel of the brain is divided by the reference PD value to obtain the free water content of each voxel of the brain. The method advantageously increases the speed and accuracy of measurement of brain free water content.

A method for reconstructing a motion-corrected magnetic resonance image of a subject. The method comprises receiving a motion trajectory comprising a series of motion states; determining similarities across the motion states and forming groups of motion states, such that each group contains motion states that are similar to each other, and determining a single group motion state representing each group; for each group of motion states, computing a single transformation operator and building a group-specific NuFT forward model, in which a mismatch between the coil sensitivity maps and the magnetic resonance image caused by a motion of the subject during the acquisition is reduced by operating the transformation operator on the coil sensitivity maps and / or on the magnetic resonance image; and reconstructing the motion-corrected magnetic resonance image by minimizing the data consistency error between the received k-space data and the group-specific NuFT forward models, wherein each NuFT forward model comprises the image, the coil sensitivity maps, a non-uniform Fourier Transformation, and a phase factor corresponding to the motion state held by the subject at the time of acquiring the corresponding subset of k-space data.

The invention discloses a magnetic resonance image reconstruction method, device and equipment, a medium and a product. The method comprises the following steps: determining a coil sensitivity mapping image set according to k space data to be reconstructed corresponding to a magnetic resonance image set to be reconstructed; according to the coil sensitivity mapping image set, performing zero-filling reconstruction on the to-be-reconstructed k space data to obtain an initial magnetic resonance reconstruction image set; determining a target magnetic resonance reconstruction image set corresponding to the magnetic resonance image set to be reconstructed according to the initial magnetic resonance reconstruction image set, the coil sensitivity mapping image set and a pre-trained target image reconstruction model; wherein the target image reconstruction model comprises a space-time convolutional network and a data consistency layer, the space-time convolutional network comprises a space-time deformation convolutional layer, and the embodiment of the invention improves the reconstruction effect of the magnetic resonance image.

A method for generating a motion-corrected magnetic resonance image dataset of a body region of a subject, the method comprising receiving magnetic resonance data acquired of the body region; receiving information on the body region covered by the magnetic resonance image dataset; weighting at least part of the received magnetic resonance data by reducing the signal originating from parts of the body region that are expected to have undergone non-rigid and / or independent motion during the acquisition, thereby producing weighted magnetic resonance data; and estimating the motion-corrected image dataset by minimizing the data consistency error between the magnetic resonance data acquired in the imaging protocol and a forward model described by an encoding matrix, wherein the encoding matrix includes motion parameters, Fourier encoding, and optionally subsampling and / or coil sensitivities of a multi-channel coil array, wherein the estimation includes at least one step of estimating motion parameters from the weighted magnetic resonance data.

Embodiments of the present application provide a dynamic magnetic resonance image reconstruction method, device and equipment, the method comprising: acquiring dynamic magnetic resonance raw data of a target object by using a center-periphery alternating acquisition mode; performing channel compression on the raw data to obtain compressed data; extracting a time basis function, a coil sensitivity map and down-sampling data based on the compressed data; constructing an optimization expression of a spatial basis function according to the time basis function, the coil sensitivity map, the down-sampling data and a down-sampling mask, taking a weighted sum of a reconstruction error and a difference between adjacent frames as an optimization target; eliminating the time dimension in the process of solving the optimization expression of the spatial basis function based on a conjugate gradient descent algorithm to obtain an optimal solution of the spatial basis function; and reconstructing a dynamic magnetic resonance image of the target object according to the optimal solution of the spatial basis function and the time basis function. Not only the reconstruction speed is improved, but also the reconstruction quality is improved.

The invention discloses a magnetic resonance training data generation method and system based on GPU acceleration Bloch simulation and combined with modal transformation, and relates to medical imaging. The method comprises the following steps: establishing a multi-parameter virtual object library, and defining voxel-level T1, T2, PD and B0 / B1 distribution and coil sensitivity; according to an input sequence and acquisition parameters, time domain simulation is carried out by adopting GPU parallel Bloch solution, and non-ideal factors are injected as required; reconstructing to obtain k space and image domain data and generating paired labels; target comparison, organs and scenes are expanded through rule-driven or data-driven modal transformation; samples and metadata are packed to support traceability and verification. The system is composed of a parameter configuration module, a virtual object library module, a GPU simulation module, a reconstruction module, a modal transformation module and a data set management module. On the premise that physical consistency is guaranteed, data generation efficiency and diversity are remarkably improved, and the method is suitable for downstream tasks such as reconstruction, artifact suppression and quantitative imaging.

The invention discloses a magnetic resonance fast imaging method for multi-coil weighting and sensitivity estimation joint reconstruction based on deep learning, and relates to magnetic resonance image fast reconstruction. Magnetic resonance structure image data is used as model training data to obtain a full-sampling image, a real coil sensitivity image is used as a training label, and a training set is k-space random noise addition and simulation under-sampling to obtain under-sampling noise addition image data and an under-sampling sensitivity image; designing a channel weighted sensitivity estimation joint reconstruction deep learning network; constructing a network loss function; solving optimal parameters of the model network by utilizing the training set; and inputting to-be-reconstructed data into the network for reconstruction, and outputting a reconstructed image. A channel weighting algorithm and a coil sensitivity estimation module are introduced, the robustness of the network under the condition of a low signal-to-noise ratio of a coil is enhanced, a sensitivity image containing high-frequency information is generated, the quality of a reconstructed image is improved, the clinical scanning acceleration multiple is improved, the reconstruction speed is high, the noise robustness is high, the denoising effect is good, and the reconstruction quality is high.

The present application relates to a system and method of magnetic resonance imaging. The method includes acquiring at least two target k-space datasets by populating k-space with target magnetic resonance signals acquired by at least two coils of a magnetic resonance imaging device along a spiral trajectory. The method includes acquiring a coil sensitivity of each of the at least two coils. The method includes acquiring a point spread function corresponding to the spiral trajectory. The method includes generating a target image based on an objective function.

The application discloses a reconstruction method of planar echo imaging, comprising the following steps: S1, collecting planar echo data and multi-echo gradient echo data of a region to be imaged respectively; S2, performing inverse geometric correction on the multi-echo gradient echo data to generate corrected data; and S3, performing image reconstruction according to the corrected data and the planar echo data to generate an imaging image. The application has the beneficial effect that the correction of the planar echo image is realized by collecting multi-echo gradient echo data and calculating a B0 field, the problem of possible artifacts in the calibration process of the planar echo imaging in the prior art is avoided, and the image of the planar echo imaging is clearer. Meanwhile, the multi-echo gradient echo data is used for coil sensitivity correction, the scanning speed is higher, and the calibration time can be effectively shortened.

Systems and methods for image reconstruction for parallel MR imaging are disclosed that receive a k-space single-coil measurement dataset that includes at least two k-space single-coil measurement sets, transforming the k-space single-coil measurement dataset to an estimated CSM using a coil sensitivity estimation module, and transforming the k-space single-coil measurement dataset and the estimated CSM into a final MR image using an MRI reconstruction module. In some aspects, the coil sensitivity estimation module and MRI reconstruction module include deep learning neural networks trained without the use of ground truth data.

The invention relates to a method of MR imaging which addresses the interplay of patient-induced artifacts, operational complexity, and the need for precise imaging of clinically relevant areas. The method comprises: acquiring MR imaging data from a patient's anatomy by executing at least one (pre-) scan to generate an image of the anatomy and to extract information including at least one of coil sensitivity distribution, B0 field distribution, B1 field distribution, spatial distribution of flow characteristics, spatial distribution of motion characteristics; identifying an anatomic structure or region of interest within the imaged anatomy; automatically adapting settings of an MR scanner used and / or parameters of an MR imaging sequence or protocol taking the extracted information into account for enhancing image quality or diagnostic utility for the identified anatomic structure or region of interest; and acquiring further MR imaging data from the patient's anatomy using the MR imaging sequence or protocol with the adapted settings and / or parameters to generate one or more optimized images of the identified anatomic structure or region of interest. Moreover, the invention relates to an MR imaging system and to a computer program.

The application discloses an imaging method and device based on parallel imaging, a storage medium and a terminal, relates to the technical field of image data processing, and mainly aims to solve the problem of poor image data accuracy of existing magnetic resonance imaging. The method comprises the following steps: acquiring a first phase encoding interval of parallel imaging pre-scanning, and performing parallel imaging pre-scanning based on a target magnetic resonance sequence and the first phase encoding interval to obtain first imaging data; determining a second phase encoding interval of parallel imaging formal scanning corresponding to the first phase encoding interval, and performing parallel imaging formal scanning based on the target magnetic resonance sequence and the second phase encoding interval to obtain second imaging data; acquiring coil sensitivity information based on the first imaging data, and acquiring a magnetic resonance image based on at least the second imaging data and the coil sensitivity information.

Disclosed herein is a method of operating a medical system (100), comprising: determining (200) initial position data (146) using a motion detection component, wherein the initial position data (146, 152) is descriptive of a subject within an imaging zone; acquiring (202) an initial coil sensitivity map (148) by controlling a magnetic resonance imaging system with coil sensitivity map pulse sequence commands; acquiring (204) imaging k-space data (150) according to a parallel imaging magnetic resonance imaging protocol by controlling the magnetic resonance imaging system with imaging pulse sequence commands; determining (206) subsequent position data (152) using the motion detection component; acquiring (208) at least one subsequent coil sensitivity map (154) by controlling the magnetic resonance imaging system with the coil sensitive map pulse sequence commands if the subsequent position data varies by more than a predetermined change since acquisition of a most recent coil sensitivity map; reconstructing (212) a magnetic resonance image (160, 402) based on the imaging k-space data and the at least one subsequent coil sensitivity map. A medical system is further presented, comprising a computational system configured to perform the method.

The invention relates to a fat pressing method and device for magnetic resonance diffusion imaging based on water-fat separation, and the method comprises the steps: adjusting the bandwidth corresponding to a target excitation pulse and a target refocusing pulse, so as to change the position of a main peak fat layer excited and refocused in initial magnetic resonance imaging, and inhibit the main peak fat; moving a preset signal reading window to collect diffusion and non-diffusion imaging signals of single excitation or multiple excitation corresponding to the signal reading window at different moving time; constructing a corresponding diffusion imaging signal model, simplifying the diffusion imaging signal model, solving the non-diffusion imaging signal model through a water-fat separation algorithm to obtain a water graph, a fat graph, a magnetic field non-uniformity graph and a relaxation time graph corresponding to the non-diffusion imaging signal model, and calculating a coil sensitivity graph corresponding to the non-diffusion imaging signal model; and solving a diffusion imaging signal model to obtain a diffusion-weighted water map, a fat map and a phase difference between excitation so as to finish inhibition of olefin peak fat.

Systems, methods, and apparatuses associated with processing complex-valued MRI data using machine learning (ML) models are described herein. The ML models can be learned based on synthetically generated MRI training data and by applying one or more meta-learning techniques. The MRI training data can be generated by adding phase information to real-valued MRI data and / or by converting single-coil MRI data to multi-coil MRI data based on coil sensitivity maps. The meta-learning process can include using a portion of the training data to conduct a first round of learning to determine updated model parameters and using a remaining portion of the training data to test the updated model parameters. A loss associated with the testing can then be determined and used to refine the model parameters. The ML models learned using these techniques can be employed for various tasks, including, for example, MRI image reconstruction and / or denoising.