43 results about "Inversion recovery" patented technology

The invention relates to the technical field of medical image auxiliary diagnosis, in particular to a nuclear magnetic resonance image auxiliary diagnosis method and system based on multi-modal fusion. The method comprises the following steps: step 1, synchronously acquiring a three-dimensional T1 weighted structure image, a T2 weighted fluid attenuation inversion recovery image and diffusion weighted imaging data of a subject, carrying out spatial registration by taking the T1 weighted image as a reference, and executing skull stripping and gray scale standardization; 2, individualized brain region segmentation is carried out based on a brain anatomical map, the lesion sensitivity weight of each modal is calculated for each segmented brain region, and the weight is obtained by quantifying the following parameters; step 3, extracting multi-modal image features in each brain region; and 4, inputting the fusion features of the whole brain region into a multi-task classifier. The standardization and alignment of the multi-mode MRI image in the space and gray level are realized, and the problems of space mismatch and feature interference among different modes are effectively solved.

The invention relates to a nuclear magnetic resonance image classification diagnosis method for adult diffuse glioma. The method comprises the following specific steps: step 1, respectively acquiring T2-fluid attenuation inversion recovery T2-FLAIR and contrast enhancement T1 weighted imaging CE-T1WI magnetic resonance images of glioma labeled by a doctor according to histological and genomics information; step 2, carrying out data preprocessing operation on the T2-FLAIR image data and the CE-T1WI image data; step 3, each pair of T2-FLAIR and CE-T1WI images after preprocessing is sent to a decision tree diagnosis model, and an Attention-DenseNet model is used for learning and extracting the characteristics of the T2-FLAIR and CE-T1WI images; 4, obtaining a prediction result based on a plurality of independently trained Attention-DenseNet models, fusing the outputs of the plurality of models by adopting a voting mechanism or a weighted average strategy, and generating a final classification decision; and 5, sending the obtained final classification to a platform, and making final diagnosis based on a classification result.

Exemplary system, method and computer accessible medium can be provided for creating or providing a (e.g., direct) visualization of an anatomical structure (e.g., subcortical anatomy). For example, it is possible to receive a magnetic resonance image, and apply a power regularization convolutional neural network to the MRI. In this manner, it is possible to generate the visualization of the anatomical structure. It is also possible to receive a fast gray matter acquisition T1 inversion recovery (FGATIR) MRI and apply a power regularization convolutional neural network to the FGATIR MRI in order to generate the visualization of the anatomical structure. Further, it is also possible to receive a FGATIR MRI and apply a convolutional neural network to the FGATIR MRI so as to generate the visualization of the anatomical structure.

The invention provides a magnetic resonance center frequency determination method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the signal collection of a spin echo sequence and an inversion recovery sequence of a target tissue, and obtaining a spin echo signal and an inversion echo signal; carrying out wave crest data extraction on the spin echo signal to obtain spin wave crest data; and determining the magnetic resonance center frequency of the target tissue according to the spin wave crest data and the inversion echo signal. According to the magnetic resonance center frequency determination method, the center frequency is determined based on two echo signals including a spin echo signal and a reverse echo signal, the reverse echo signal can suppress a fat signal, and the spin echo signal collects an oil-water peak signal which does not suppress the fat signal. The magnetic resonance center frequency of the target tissue determined based on the two echo signals with different properties is more accurate.

The invention relates to a special device and method for calibrating a relaxation time measurement result of a medical magnetic resonance imaging (MRI) system. The special device comprises a relaxation time standard die body, an optical fiber temperature measurement system and a control computer. The relaxation time standard die body is composed of a die body shell, a sealing cover and a relaxation time standard unit. The relaxation time standard unit is composed of reagent bottles, and the optical fiber temperature measuring probe is inserted into the relaxation time standard die body. According to the method, T1 and T2 standard values of a relaxation time standard substance under different static magnetic field intensities are calibrated by using a magnetic resonance spectroscopy method, and a relaxation time measurement result of an MRI system is calibrated by using the calibrated relaxation time standard substance. And adopting a reversal recovery sequence to calibrate T1, and adopting a CPMG sequence to calibrate T2. The device and the method can be used for calibrating the relaxation time measurement result of the MRI system, so that the accuracy and the consistency can be improved, and the clinical application is promoted.

Systems and methods are provided for estimating a navigation map for multi-shot phase navigation image reconstruction. Techniques described herein include acquiring a reference image of a subject, calculating a navigation map for a multi-shot MR image of the subject using the reference image, and reconstructing the multi-shot MR image by applying the navigation map to segments of the multi-shot MR image. The MR image and the reference image may be, for example, a T1 weighted image, a T2 weighted image, a liquid attenuation inversion recovery (FLAIR) image, a DWI image, a water separation image, a fat separation image, a fat suppression image, a phase contrast image, or a blood contrast image. The reference image may be of a different type than the MR image, and / or acquired from the same or different sequence as the MR image. The navigation map may correct for motion-induced phase differences of excitation variations in the multi-excitation MR image.

The application relates to a magnetic resonance imaging method, device, computer equipment, storage medium and computer program product. The method comprises the following steps: in a first cardiac cycle, a characteristic electrocardio signal of a detection object is identified, a first sequence pulse is applied to the detection object after a preset delay time of identifying the characteristic electrocardio signal, and the first sequence pulse is used for reversing a longitudinal magnetization vector of the detection object; after the first sequence pulse is applied, a second sequence pulse of a target phase mode is applied to the detection object after a recovery time, and an initial cardiac imaging set is acquired, wherein the target phase mode is one of at least two different phase modes, and different target phase modes correspond to different positions of artifacts in the initial cardiac imaging sets; and the initial cardiac imaging sets obtained in each first cardiac cycle are subjected to first registration processing to obtain a cardiac imaging. The method can effectively weaken the artifacts in cardiac delayed enhancement imaging, and does not increase additional operations and additional scanning time.

A low field magnetic resonance imaging (MRI) stroke identification sequence uses an inversion recovery sequence. TE is set to the minimum or near-minimum value achievable by a system to minimize an impact of T2 effect on a signal S. Additionally, it selects combinations of TR values and corresponding TI values to make signal from cerebral hemorrhage appear as high signal, and signals from cerebral infarct tissue and cerebral parenchyma appear as isointense or low signal. This allows for rapid and accurate determination of hemorrhagic stroke and, by utilizing low-field magnetic resonance, enhances the accessibility for patients.

The invention discloses intelligent diagnosis equipment for brain small vasculopathy MRI image enhancement, which comprises a multi-mode MRI image acquisition module, an examination bed is arranged on one side of the multi-mode MRI image acquisition module, the multi-mode MRI image acquisition module is used for acquiring multi-sequence MRI original images of a patient with brain small vasculopathy, and the multi-sequence MRI original images at least comprise T1 weighted imaging T1WI, T2 weighted imaging T2WI and liquid attenuation inversion recovery sequence FLAIR images; the invention belongs to the technical field of medical equipment, and aims at solving the problems that in the prior art, a traditional MRI image is limited in resolution and is interfered by noise and artifacts, the signal difference between a focus and normal brain tissue is not obvious, and missed diagnosis is prone to occurring. The method has the advantages that the space-channel attention mechanism of the intelligent image enhancement module is fused with the multi-modal features, the signal difference between the tiny focus and the normal brain tissue is remarkably enhanced, noise and artifact interference are weakened, the detection rate of the tiny focus is greatly increased, and the missed diagnosis risk is effectively reduced.

The invention relates to a magnetic resonance image reconstruction method and device, computer equipment and a storage medium, and the method comprises the steps: applying a phase-sensitive inversion recovery pulse sequence to a to-be-imaged object, collecting a magnetic resonance signal of the to-be-imaged object, and obtaining a to-be-processed image according to the magnetic resonance signal; removing a background first-order phase in the to-be-processed image to obtain a first dephasing image; according to the first dephasing image and a preset recognition model, removing a target background zero-order phase in the first dephasing image to obtain a second dephasing image; and extracting a real part component of the second dephasing image to obtain a target magnetic resonance image. By using the magnetic resonance image reconstruction method provided by the invention, the quality of the obtained target magnetic resonance image can be improved.

The invention discloses a dynamic magnetic resonance delay enhancement imaging method. The method comprises the following steps: for a target part, acquiring k-space data by using a phase-sensitive inversion recovery sequence and rearranging the k-space data to obtain rearranged data; and inputting the rearranged data into a trained image reconstruction model to obtain a reconstructed image, the image reconstruction model being constructed based on a deep balance model and being used for learning a mapping relationship between the rearranged undersampled data and the reconstructed image. According to the method, segmented k-space data is divided into multiple times of high-acceleration acquisition, artifacts caused by heart movement are remarkably reduced, and a high-quality PSIR image is reconstructed from undersampled data by combining a deep expansion network with a deep balance model.

The invention provides an imaging signal acquisition method and system of multiple acquisition modules based on inversion recovery pulses, electronic equipment, a storage medium and a computer program product. The imaging signal acquisition method comprises the steps that an inversion recovery pulse is applied to a first layer of a target space position at a first moment, so that at least two acquisition modules sequentially acquire imaging signals of the first layer after first inversion recovery time, and the first inversion recovery time is the inversion recovery time of the first acquisition module; under the condition that the first inversion recovery time meets a first preset condition and the interval time between two adjacent acquisition modules does not meet a second preset condition, determining a first target layer number meeting the execution of interlayer staggered acquisition; and applying inversion recovery pulses to the layers of the first target layer number in sequence within the first inversion recovery time, so that the at least two acquisition modules acquire imaging signals of the corresponding layers in sequence after the first inversion recovery time.

The present disclosure may include a communication module configured to perform communication with an imaging device that captures an image of an acute cerebral infarction patient; and a processor configured to receive the image of the acute cerebral infarction patient from the imaging device through the communication module, classify the image into a first image corresponding to a liquid attenuation inversion recovery image and a second image corresponding to a diffusion-weighted image, acquire the first image and the second image, align the first image and the second image with respect to an MNI region corresponding to an activated region of a brain, detect an infarction region in the second image, and output a probability prediction value for the occurrence time of acute cerebral infarction based on the first image, the second image, and the infarction region.

A magnetic resonance imaging method and a magnetic resonance imaging system is provided. The method is used to acquire, in a plurality of consecutive time units, magnetic resonance signals representing one or more layers of an anatomical region of interest of a subject and generate a magnetic resonance image. The method includes: determining an effective repetition time of an (N−1)th time unit; determining the position of an inversion recovery pulse in an Nth time unit based on the effective repetition time of the (N−1)th time unit, wherein N is an integer greater than 1; transmitting, in the Nth time unit, a scan sequence generated based on the position of the inversion recovery pulse, and acquiring a magnetic resonance signal representing an anatomical region of interest of a subject; and reconstructing a magnetic resonance image at least based on the magnetic resonance signal.

The invention discloses a brain multi-modal image data processing method and device. The method comprises the steps of obtaining a brain multi-modal image sequence of a target object; fusing the three-dimensional contrast-agent-free angiography with the plaque internal hemorrhage image sequence and the time leap method imaging image sequence to obtain cerebrovascular image data; cerebrovascular image data is used as a tree root node and a trunk node, hemodynamic parameter data in a phase contrast angiography sequence is used as a branch node for representing a blood supply state, and neural structure parameter data in a diffusion magnetic resonance imaging sequence is used as a branch node for representing a neural structure. Physical and chemical parameter data in the liquid attenuation inversion recovery sequence are used as leaf nodes for representing functional metabolism, hemodynamic parameter data in the magnetic resonance brain perfusion imaging sequence are refined to a pixel level and then are used as leaf nodes for representing metabolic activity, and a brain biological characteristic tree of the target object is constructed. According to the method, the brain multi-modal image data can be quantitatively analyzed.

Disclosed is a method of characterizing a cardiac lesion using an image comprising: a black blood image generated from signals acquired during black blood late gadolinium enhanced magnetic resonance acquisition (ACQ1); a bright blood image is generated from signals acquired during bright blood late gadolinium enhanced magnetic resonance acquisition, the bright blood acquisition step (ACQ2) being different from the inversion recovery sequence. The method comprises: computer segmenting the bright blood image to generate localization data defining a set of at least one wall of the cardiac muscle; the computer extracts the set of at least one wall characterizing a cardiac lesion from the set of at least one wall defining the myocardium from the positioning data of the set of at least one wall according to the black blood image and the positioning data.

The application provides a kind of magnetic resonance image feature extraction method, system, equipment and feature application method, it is related to image feature extraction technical field, the application includes obtaining the magnetic resonance imaging data of sample to be measured;According to magnetic resonance T1 weighted image, magnetic resonance imaging liquid attenuation inversion recovery sequence image and diffusion magnetic resonance image, construct the structure broken link network of sample to be measured;According to resting state functional magnetic resonance imaging, construct the functional broken link network of sample to be measured;According to structure broken link network and functional broken link network, construct individual injury degree network;The one-dimensional vector obtained by converting the upper triangular value on the matrix of individual injury degree network is used as the feature extraction result of the magnetic resonance image of sample to be measured.The application can accurately and reasonably extract the characteristics of magnetic resonance image by constructing structure broken link network and functional broken link network, to improve the precision of model classification.

This application relates to the technical field of image recognition, and provides a method for evaluating a diffusion weighted imaging (DWI)-fluid attenuated inversion recovery (FLAIR) mismatch, an apparatus, a medium, and a product. The method includes: obtaining a DWI image and a FLAIR image of a target object; applying a first image segmentation model to segment the DWI image to obtain a first image segmentation result; applying a second image segmentation model to segment the FLAIR image to obtain a second image segmentation result; registering the second image segmentation result onto the first image segmentation result to obtain a registered second image segmentation result; and applying a Dice metric to evaluate a degree of mismatch between the first image segmentation result and the registered second image segmentation result. This application can improve efficiency of determining whether DWI and FLAIR are matched.

The invention discloses a cerebral apoplexy hemorrhage and ischemia identification scoring method and device based on a low-field-intensity nuclear magnetic imaging, and relates to the technical field of clinical medicines.The method comprises the steps that a 0.23-T diffusion weighted imaging image and a 0.23-T hematoma enhancement inversion recovery sequence image of a patient are obtained; inputting a 0.23-T diffusion weighted imaging image and a 0.23-T hematoma enhancement inversion recovery sequence image of the patient into the trained integrated model of stroke focus segmentation and hemorrhagic and ischemic stroke identification scoring; predicting a focus segmentation mask in a 0.23-T diffusion weighted imaging image of the patient, a focus segmentation mask in a 0.23-T hematoma enhancement inversion recovery sequence image, and probability scores of hemorrhagic and ischemic stroke of the patient; the integrated model is used for predicting a focus segmentation mask in a 0.23-T diffusion weighted imaging image, a focus segmentation mask in a 0.23-T hematoma enhancement inversion recovery sequence image, and probability scores of hemorrhagic and ischemic stroke. The accuracy of stroke risk identification can be improved.

The present invention relates to a stroke differentiation sequence using low-field magnetic resonance imaging, and a device with the differentiation sequence. An inversion recovery sequence is used, and a TE uses the minimum or near-minimum TE value achievable by a system, thereby minimizing the impact of T2 effect on a signal S; moreover, a combination of a TR value and a corresponding TI value is selected, such that the signal of intracerebral hemorrhage is hyperintense, and the signals of cerebral infarct tissue and brain parenchyma are isointense or hypointense, thereby quickly and accurately identifying hemorrhagic stroke; and low-field magnetic resonance imaging is used, thereby achieving higher accessibility for patients.

The invention relates to a longitudinal relaxation time constant determination method and device and magnetic resonance imaging equipment, and the method comprises the steps: obtaining a plurality of first amplitude images corresponding to a plurality of inversion recovery moments; wherein the sizes of the plurality of first amplitude images are the same; determining an amplitude image with the minimum amplitude at a preset target position point in the plurality of first amplitude images as a target amplitude image; selecting an image except the target amplitude image in the plurality of first amplitude images as a second amplitude image; and determining a longitudinal relaxation time constant of the target position point according to the second amplitude image. According to the invention, the problem of inaccurate calculation of the longitudinal relaxation time constant in the prior art is solved.

The present application relates to a magnetic resonance imaging method, apparatus, computer device, and storage medium. The method comprises: transmitting a first inversion recovery pulse, executing an imaging sequence during the longitudinal magnetization relaxation interval of the first inversion recovery pulse to acquire a first set of magnetic resonance signals from multiple slices, and executing a reference sequence to acquire reference signals from multiple slices; transmitting a second inversion recovery pulse, executing an imaging sequence during the longitudinal magnetization relaxation interval of the second inversion recovery pulse to acquire a second set of magnetic resonance signals from multiple slices, thereby obtaining a first set of magnetic resonance images and a second set of magnetic resonance images; acquiring a first image and a second image of each slice after deallapping based on the reference signal, the first set of magnetic resonance images, and the second set of magnetic resonance images; and acquiring relaxation parameter values ​​of the subject based on the first image and the second image of each slice after deallapping. This method can reduce magnetic resonance scanning time.

A neurovascular age prediction system based on white matter and a method thereof are disclosed. An analysis device generates an individual space periventricular area mask and an individual space deep white matter mask by nonlinear space counterpoint technology and MNI152 brain template, and reversely transforms individual coordinates into a transition matrix, performs white matter hyperintensity (WMH) signal image processing on the T1 weighted image and the T2 fluid attenuated inversion recovery (FLAIR) image to generate a T1 weighted WMH signal image and a T2 FLAIR WMH signal image, then converts the Ti WMH signal image and the T2 FLAIR WMH signal image into logarithms of a periventricular white matter volume and a deep WMH volume based on the individual space periventricular area mask and the individual space deep white matter mask, and substitutes the logarithms into a neurovascular age prediction model to obtain a neurovascular age prediction result.

The application discloses an optimization method, device, equipment and medium for magnetic resonance imaging, and relates to the field of magnetic resonance imaging. The method comprises the following steps: acquiring a reference longitudinal relaxation time of an imaging magnetic resonance device with a preset main magnetic field strength; constructing a linkage fitting function between TR and TI parameters based on the reference longitudinal relaxation time, taking the maximum difference value between an image signal of a hemorrhagic focus and an image signal of healthy brain parenchyma as a target; determining a target TI according to a target TR and the linkage fitting function; optimizing scanning parameters of the magnetic resonance device by using a minimum effective echo time, the target TR and the target TI; acquiring an initial magnetic resonance image, which is obtained by scanning a stroke patient by using the magnetic resonance device with the optimized parameters; and enhancing the initial magnetic resonance image by using a nonlinear stretching function to obtain a stroke triage enhanced inversion recovery image. The application can improve the image contrast of the magnetic resonance imaging.

The present application relates to the technical field of image recognition. Disclosed are a DWI-FLAIR mismatch evaluation method, and an apparatus, a medium and a product. The method comprises: acquiring a diffusion-weighted image and a fluid-attenuated inversion recovery image of a target object; using a first image segmentation model to segment the diffusion-weighted image to obtain a first image segmentation result; using a second image segmentation model to segment the fluid-attenuated inversion recovery image to obtain a second image segmentation result; registering the second image segmentation result to the first image segmentation result to obtain a registered second image segmentation result; and using a Dice index to evaluate the degree of mismatch between the first image segmentation result and the registered second image segmentation result. The present application can improve the efficiency of evaluating whether DWI matches FLAIR.

The invention relates to the technical field of medical image diagnosis, in particular to a black blood T2 weighted fast spin echo imaging method and system under a free breathing condition. According to the black blood imaging method based on reverse dual inversion recovery (RDIR) and single excitation fast spin echo (SS-FSE), artificial intelligence assisted compressed sensing (ACS) is introduced to improve the reconstruction quality. The slice selective reversal pulse is moved forward to the previous cardiac cycle, so that myocardial signal loss is effectively reduced; scanning time can be remarkably shortened and motion artifacts can be reduced by adopting single excitation. And in combination with the ACS, a high-resolution T2 weighted black blood image can be obtained under high and under-sampling conditions, and the method is particularly suitable for edema evaluation of children under free breathing.

This invention relates to the field of intelligent medical image analysis technology, and in particular to a deep learning-based method and system for stroke image segmentation. The method includes: acquiring diffusion-weighted, apparent diffusion coefficient, and fluid attenuation inversion recovery images to form a dataset; obtaining standardized images and quality grades through resampling and intensity normalization; training a prior model with normal samples to generate a potential distribution centroid library and quality calibration curve; alternately updating the deformation field and anomaly editing field of the images to be segmented to generate candidate probability maps; zeroing the anomaly editing field to generate counterfactual healthy images; and combining differential evidence and contralateral mirror evidence to output lesion masks and suspicious region masks, thereby improving cross-quality stability and verifiability.

A method of analysing MRI images is described. The method comprising acquiring at least three medical MR images of a subject; analysing the at least three medical MR images to determine a water T1 map; applying a field strength correction and an iron correction to the determined water T1 map to generate a corrected water T1 map; generating one or more simulated MRI images based on the water T1 map; fitting the one or more simulated MR images to determine a standard cT1 image for the subject.

The invention discloses a magnetic resonance liquid attenuation T2 quantitative imaging method and system, and relates to magnetic resonance imaging. The method aims at rapidly obtaining the FLA-T2 graph without cerebrospinal fluid signal interference. The method comprises the following steps of: recovering a multi-echo-chain multi-overlapping echo sequence IR-METMOLED by adopting single-scanning inversion, setting sampling parameters, acquiring IR-METMOLED signals of an actual imaging object in a magnetic resonance imager, and preprocessing to obtain an actual acquisition image; the method comprises the following steps: generating a pairing training sample of a simulated IR-METMOLED image and a simulated FLA-T2 image, and training a neural network; and inputting the real part and the imaginary part of the preprocessed actually-acquired image into the trained neural network for reconstruction to obtain an FLA-T2 image of an actually-imaged object. According to the method, the limitation of the echo chain length on the echo time can be eliminated, meanwhile, the interference of cerebrospinal fluid signals is eliminated, and the FLA-T2 graph can be quickly obtained under the condition that the signal complexity is not increased.

The invention relates to a magnetic resonance imaging method and a magnetic resonance imaging system, and the method comprises the steps: obtaining an initial inversion recovery scanning sequence which comprises an inversion module and an imaging collection module; obtaining first gradient coding position information of a set tissue of the target scanning part according to an imaging acquisition module; according to the first gradient coding position information, gradient coding parameters of an inversion module are determined, and a target inversion recovery scanning sequence is obtained; and scanning the target scanning part according to the target inversion recovery scanning sequence to obtain a magnetic resonance image. By adopting the method, the problem that a fat inhibition method cannot have a relatively good inhibition effect in various occasions can be solved.