76 results about "Mr images" patented technology

The present application provides a cardiac fibrosis diagnosis model based on multi-task attentional feature fusion. The cardiac fibrosis diagnosis model is established by the following steps: S01: image collection and labeling: obtaining cardiac magnetic resonance (MR) images as sample data, and performing manual labeling to obtain heart labels corresponding to the MR images; S02: image preprocessing, including normalization processing, data enhancement, and data clipping; S03: model establishment, including establishment of an image recovery network and establishment of an image segmentation and classification network, and executing an image recovery task; S04: model pre-training: training the image recovery network such that the encoder of the image recovery network fully learns the feature of the cardiac fibrosis image; and S05: model training. An objective of the present application is to improve the segmentation precision and diagnosis accuracy of a network model for a cardiac fibrosis image.

The invention provides a multi-mode nuclear magnetic resonance image glioma segmentation method and application thereof, and belongs to the field of medical image processing. The invention provides an M2ES-UNet network aiming at the problems of insufficient utilization of spatial features, single multi-modal fusion mechanism and cross-level semantic loss of an existing segmentation method. According to the method, multi-view anatomical information is extracted through a multi-plane feature collaboration module; utilizing an orthogonal dimension fusion convolution and modal introspection-collaboration module to respectively realize differential fusion of shallow and deep features; and the progressive jump transmission of the features is realized through a coding information smooth transmission module. According to the method, multi-plane and multi-mode complementary information can be effectively mined, the boundary precision and robustness of brain glioma segmentation are remarkably improved, and clinical diagnosis is assisted.

The invention provides a multi-modal weak supervision medical image segmentation method, and belongs to the field of medical image segmentation, and the method comprises the steps: carrying out the feature extraction of CT and MR images, and obtaining CT and MR modal feature representations; fusing same-layer features represented by CT and MR modal features under each scale; performing down-sampling and multi-layer convolution processing on the fusion feature representation; respectively decoding the enhanced feature representation, the CT modal feature representation and the MR modal feature representation to obtain a multi-modal prediction map, a CT prediction map and an MR prediction map, calculating cross entropy loss, respectively calculating multi-view CRF loss of the CT image and the MR image, obtaining intra-modal regular loss, calculating inter-modal consistency loss, adding the cross entropy, the intra-modal regular loss and the inter-modal consistency loss, and when the total loss is minimum, determining that the total loss is minimum. Obtaining a trained image segmentation model; inputting CT and MR images to be segmented into the trained image segmentation model, and outputting segmented images; the invention also provides an image segmentation system. And multi-modal image information is effectively fused and over-fitting is inhibited under a weak supervision condition.

Systems and methods for image reconstruction and quantitative MRI. Generative models such as diffusion models are used to reconstruct MR images and generative models and constrained mathematical models fit to estimate quantitative maps from the reconstructed MR images.

The application discloses a kind of fast magnetic resonance multi-sequence joint imaging method, system, equipment and medium, it is related to deep learning technical field, including the following steps: acquisition different sequence multiple undersampling MR images, wherein multiple undersampling MR images share the same public feature, each undersampling MR image enjoys respective corresponding specific feature;The mapping relationship between multiple undersampling MR images and latent variable is modeled based on latent variable model, and the optimization objective of reconstruction task in fast magnetic resonance multi-sequence joint imaging is constructed based on mapping relationship;Optimization objective is solved by depth development network.The features of multiple undersampling MR images are subdivided into intermodal shared public features and modality unique specific features, the fine decoupling of the shared and specific features of MR image, solve the problem that intermodal correlation modeling is weak, and redundant information can be effectively avoided or sequence-specific detail information is lost.

For autonomous MR scanning of a given medical test, a simplified MR scanner can be used without or with little input or control by a technical expert, e.g., by a physician, radiologist, or person trained in MR scanner operation. The MR scanner autonomously positions, scans, checks quality, analyzes, and / or outputs answers to diagnostic questions with or without MR images. Artificial intelligence-based scan analysis allows continuous or instant changes to the scan configuration to acquire the data desired to answer the diagnostic question. By using a simplified MR scanner, both the positioning of the patient relative to the MR scanner and the localization of the scan by the MR scanner are jointly solved. Sensors can sense the patient at the scan position, with reduced radio frequency requirements allowing a more open bore.

The present disclosure relates to a lumbar vertebra lesion identification method, device, medium and electronic equipment, wherein the method comprises: determining a lumbar vertebra image of a user, the lumbar vertebra image being a T2 weighted magnetic resonance image; inputting the lumbar vertebra image into a target detection model to obtain a lesion category of the lumbar vertebra of the user, wherein the target detection model comprises a down-sampling layer and a pooling layer, the down-sampling layer is used to extract feature data of the lumbar vertebra image, and the pooling layer is used to classify the feature data to obtain the lumbar vertebra lesion category of the user. Compared with the way of judging the lumbar vertebra lesion by artificial judgment and identifying the lumbar vertebra lesion by machine learning method in the related art, the error of identifying the lumbar vertebra lesion type can be reduced, and thus the accuracy of identifying the lumbar vertebra lesion can be improved.

An artificial intelligence (Al) engine is trained on a plurality of annotated magnetic resonance (MR) images of a patient's brain. A plurality of MR images of a patient's head is provided. For each MR image in the plurality of provided MR images, the Al engine detects a plurality of edges of the brain and determine a biparietal diameter (BP) value, detects a plurality of frontal horn edges, and detects a plurality of occipital horn edges. A correction module determines that at least one detected edge is associated with a non -ventricular body and updates the edge to correspond to the applicable horn. The Al engine determines a frontal horn diameter (F) value, and a occipital horn diameter (O) value. An indication module provides an indication on abnormal dilation of the patient's brain ventricles based on a maximum F value, a maximum O value, and the maximum BP value.

The application provides a method and system for removing electro-physiological signal gradient artifacts in a magnetic resonance environment, and relates to the technical field of magnetic resonance image processing. The method comprises: collecting an electro-physiological signal of a magnetic resonance scan and a scan synchronization signal; aligning and windowing the electro-physiological signal based on the scan synchronization signal to obtain a windowed sequence; constructing an artifact template based on the windowed sequence; combining the windowed sequence and the artifact template to calculate a first residual; performing principal component analysis on the artifact template and the first residual to obtain a second residual; performing logarithmic domain conversion and polarity extraction operations on the second residual to obtain a logarithmic domain sequence and a polarity symbol layer; inputting the logarithmic domain sequence into a deep learning denoising network to output a de-artifact logarithmic domain sequence; and performing inverse logarithmic transformation and polarity recovery operations on the de-artifact logarithmic domain sequence and the polarity symbol layer, respectively, to determine a de-artifact signal.

A system and method automatically detect, in MR images, WM lesions exhibiting a central vein sign. A set of MR images of a brain lesion is acquired, using images of the set as input to different ML algorithms. A first ML algorithm classifies inputted image(s) into first or second classes. The first class includes CVS+ / − and the second class CVSe lesions. A second ML algorithm classifies inputted image(s) into third or fourth classes. The third class includes CVS+ lesions and the fourth central vein sign− lesions. For each set, probability values are used that the set belongs to classes as inputs to a final classifier performing a final classification of the set into second, third, or fourth classes. For each class, the final classifier outputs final probability that the set belongs to the class. The second, third or fourth class with highest probability value is provided through an interface.

This invention relates to a two-stage super-resolution method for MRI images using high-quality codebook prior information. The method includes: a) data preprocessing, undersampling the fully sampled K-space data; b) designing a one-stage codebook network, pre-trained using ground truth images to obtain high-quality codebook information; d) designing a two-stage codebook-prior super-resolution network model that integrates prior information; e) supervised training of the model using ground truth images; and f) selecting the optimal model based on a validation set, inputting test data into the model to obtain the super-resolution MRI image. Compared with existing technologies, this invention introduces high-quality codebook prior information during the super-resolution process, effectively solving the problem of poor restoration of details and texture structure in super-resolution images. Better restoration of detailed texture information aids in clinical diagnosis and has promising application prospects.

There is provided a computer-implemented method for synthesising magnetic resonance angiography (MRA) images from other types of inputted magnetic resonance (MR) images, in a subject-specific manner, the method comprising providing a conditional generative adversarial network (cGAN) that learns a combined latent representation of the inputted magnetic resonance images for each subject and learns to transform this combined latent representation to a magnetic resonance angiography image corresponding to that subject, providing a plurality of magnetic resonance (MR) images as input into the cGAN, and outputting a plurality of MRA images from the cGAN based on the plurality of inputted MR images.

This invention discloses a method and system for identifying brain tumors in brain MRI images. The method includes the following steps: S1, acquiring the original brain MRI image data of the object to be identified and performing preprocessing operations to obtain standardized multimodal MRI image data; S2, performing preliminary tumor region screening on the preprocessed image data using a tumor tissue probability decoupling identification method based on multi-echo relaxation differences. This invention relates to the field of medical image processing technology. This method and system for identifying brain tumors in brain MRI images employs a tumor tissue probability decoupling model based on multi-echo relaxation differences and cross-scale brain network topology perturbation analysis, which can accurately screen potential tumor regions. Furthermore, it improves identification accuracy through dual constraints of metabolism and morphology. The introduction of cross-scale topology analysis, combined with abnormal propagation detection of brain network structures, effectively identifies suspected tumor regions and improves identification accuracy.

A conversion device is operable to perform a learning-based method of generating a synthetic electron density image (sCT) of an anatomical portion based on one or more magnetic resonance (MR) images. The method is processing-efficient and capable of producing highly accurate sCT images irrespective of misalignment in the underlying training set. The conversion device receives and installs a machine-learning model trained to predict coefficients of an image transfer function. The conversion device then receives a current set of MR images of the anatomical portion, computes current coefficients of the image transfer function by operating the machine-learning model on the current set of MR images, and computes a current sCT image of the anatomical portion by operating the current coefficients, in accordance with the image transfer function, on the current set of MR images.

The invention relates to the technical field of image processing, in particular to a synchronous acquisition and playback method and system for nuclear magnetic resonance images. The method comprises the steps that a high-resolution anatomical image is obtained, blood flow velocity information is coded for dynamic imaging, distortion data is corrected in real time, and analog signal data is output; the analog signal data are preprocessed, the preprocessed data are subjected to layered coding, a fixed-length abstract is generated, encryption processing is carried out, and encrypted data are output; decrypting the encrypted data, reconstructing a playback image sequence, and displaying the image sequence; the system comprises a data acquisition module, a fixed-length abstract generation module and a playback image sequence reconstruction module. By means of the mode, the change of blood flow along with time is dynamically displayed, and the assessment ability of lesion risks is improved.

To provide a resource allocation system and method for managing the use of local and remote resources for medical image processing tasks.SOLUTION: A simplified medical imaging ecosystem 100 including various networked medical facilities includes a first medical facility 102 and a second medical facility 103 that are operated as part of a medical system 106. The medical facility 102 includes a CT scanner 110, which includes a LCI112 used to process acquired projections to reconstruct CT images, and an MR scanner 120, which includes a LCI122 and processes acquired projections to reconstruct MR images. Medical facility 103 includes a computed tomography (CT) scanner 130 that includes a LCI132 used to process acquired projections to reconstruct CT images and a positron emission tomography (PET) scanner 140 that includes a LCI142 used to process acquired projections to reconstruct PET images.SELECTED DRAWING: Figure 1

The disclosure is directed to an undersampled point restoration method, device and magnetic resonance imaging system in magnetic resonance imaging. The method may include, during magnetic resonance scanning of an imaging subject, acquiring magnetic resonance signals of each channel by an undersampling mode and respectively placing the acquired magnetic resonance signals of each channel into the K-space of the each channel; and for any undersampled point in the K-space of each channel of the imaging subject, restoring the undersampled point by performing high-order interpolation on data points surrounding the undersampled point. Aspects improve the accuracy of restoring undersampled points in MR imaging, thereby further enhancing the quality of MR images.

The invention discloses a super-resolution reconstruction method based on a low-resolution nuclear magnetic resonance image, and belongs to the technical field of medical image processing, and the method comprises the following steps: firstly, inputting a high-resolution nuclear magnetic resonance image into a data preprocessing module for simulating a low-resolution image; secondly, inputting the preprocessed nuclear magnetic resonance image into an interpolation up-sampling module, and adjusting the size and the resolution of the preprocessed nuclear magnetic resonance image to be consistent with those of a high-definition image; and inputting the up-sampled low-resolution image into a three-dimensional convolutional neural network model based on a residual module, and realizing accurate prediction of each voxel intensity of the high-resolution nuclear magnetic resonance image in combination with a feature encoder, a feature decoder and a regression head. The method has the advantages that distribution characteristics of clinical low-definition MRI are better adapted, MRI data with non-fixed axial resolution are effectively processed, and the model can reconstruct high-frequency details of the skull and the face while restoring details of an anatomical structure of a brain region.

A computer-implemented method of reducing artifacts in multi-channel magnetic resonance (MR) images is provided. The method includes receiving a plurality of sets of MR images acquired by a radio-frequency (RF) coil assembly having a plurality of channels. Each set of MR images includes a plurality of slices of MR images acquired by one of the plurality of channels. The method also includes estimating a plurality of sets of artifacts in the plurality of sets of MR images by inputting the plurality of sets of MR images into a neural network model. Each set of artifacts corresponds to the one of the plurality of channels. The method further includes reducing artifacts in the plurality of sets of MR images based on estimated artifacts, deriving MR images of reduced artifacts by combining the MR images of reduced artifacts, and outputting the MR images of reduced artifacts.

This invention relates to a system and method for analyzing the lateral weight-bearing zone of femoral head necrosis. The method utilizes a data processing device to perform the following steps: First, an original femoral head necrosis model and an original femoral head model are formed based on CT and MR images. A first three-dimensional image, obtained by initial iteration and / or contour merging of the aforementioned models using a virtual reality device, is displayed from the operator's perspective. The lateral weight-bearing zone of the necrosis is obtained based on the three-dimensional image, and a lateral weight-bearing zone of the femur is generated based on the original femoral head model. The lateral weight-bearing zone of the necrosis, the lateral weight-bearing zone of the femur, and the first three-dimensional image are then further iterated and / or spatially registered using a virtual reality device to obtain a second three-dimensional image that can be imaged and displayed using either binding constraints or independent decomposition processing. This invention can accurately analyze the distribution of femoral head necrosis, effectively calibrate the lateral weight-bearing zone of femoral head necrosis, and accurately determine the spatial three-dimensional relationship of femoral head necrosis.

The invention relates to the technical field of image processing, in particular to an MR-CT image automatic fusion network model and method. The MR-CT image automatic fusion network model comprises a feature extractor which is used for extracting multi-level feature mapping of MR images and CT images; the feature fusion layer is used for carrying out image fusion by adopting a space mean value attention fusion method; and the feature reconstruction device is used for carrying out decoding reconstruction on the input fusion feature mapping fm to obtain a fused MR-CT image. The method has the beneficial effects that on the basis of extracting multilevel feature mapping of the MR image and the CT image through the feature extractor, the fusion weight of the feature map can be adaptively adjusted for each position by the space mean attention fusion method adopted by the fusion layer, so that detail information and global structure features in the source image can be better reserved; therefore, the obtained fused image has more detail information and a clearer boundary contour.

A method for grading a lesion in three-dimensional image data of a prostate of a patient is provided. The method comprises: registering 3D image data, the 3D image data comprising a plurality of different types of MR images of the patient; segmenting a prostate region in the 3D image data into a region of interest including a lesion, and extracting a plurality of radiomics features from the region of interest; lesions are graded by applying a machine learning model to the plurality of radiomics features.

The invention discloses an intelligent matching and operation planning system for osteochondral defect repair, and relates to the technical field of orthopedic implant design, and the system comprises an image acquisition and preprocessing module which is used for obtaining high-resolution nuclear magnetic resonance image data of both knee joints of a patient; and the three-dimensional modeling module is used for carrying out segmentation and three-dimensional reconstruction on the nuclear magnetic resonance image data, generating a knee joint three-dimensional entity model comprising the proximal tibia, the proximal fibula, the distal femur and the surface cartilage of the proximal tibia, the proximal fibula, the distal femur and the surface cartilage of the proximal tibia, the proximal fibula and the distal femur. The bearing curved surface of the prosthesis can accurately reproduce the self-healthy articular surface curvature of a patient, so that good anatomical matching and biomechanical compatibility are formed with an opposite-side joint after the prosthesis is implanted. Meanwhile, the handle structure is intelligently generated according to the three-dimensional shape of the defect area, and initial stable fixation of the prosthesis in the bone is facilitated.

The present disclosure provides a method, apparatus, and computer program for analyzing brain MR images based on a deep learning model. A method according to one embodiment of the present disclosure includes the steps of: training a neural network model based on training data including a plurality of brain MR images; when the training is completed, inputting a brain MR image obtained from a subject into the trained neural network model to identify a plurality of regions included in the subject's brain and to identify the volume of the plurality of regions; and providing numerical information regarding the volume of each region included in the subject's brain. The training step includes the steps of: applying a CDF mapping function set based on scan conditions to each of the plurality of brain MR images included in the training data to obtain an augmented MR image corresponding to each brain MR image; and training the neural network model based on training data including the augmented MR image.

The invention discloses an MR image loading method and device. The method comprises the steps of collecting a target image of a to-be-recognized object; a pre-trained recognition model is adopted to recognize the image features in the target image, a detection result is obtained, and the detection result is used for indicating the probability that the image features are successfully loaded; the image features with the successful loading probability higher than a preset threshold value in the target image are loaded, a loaded image is obtained, and the loaded image is a three-dimensional image; and superposing a preset virtual model into the loaded image to obtain a mixed reality MR image. The technical problem that the loading efficiency of the MR image is low due to the fact that the success rate of loading recognition is low in the prior art is solved.

The embodiment of the invention provides a magnetic resonance imaging method. The method may include acquiring magnetic resonance (MR) images of a subject, at least two of the MR images being acquired by an MRI scanner according to different imaging parameters. The method may further include processing the MR image by the trained machine learning model, obtaining one or more target MR mappings corresponding to at least a portion of the MR image. The second number of target MR maps is less than the first number of MR images. The trained machine learning model includes at least two sub-models, and each sub-model processes at least one MR image.

Provided are MR images of a subject gastrointestinal tract structure in which the lumen of the structure is usefully darkened on both T1-weighted and T2-weighted images when the structure is imaged following administration to the subject of an enteric contrast agent formulation with particles containing encapsulated gas or partial vacuum. The present invention provides an encapsulated gas or partial vacuum particle contrast medium of use in acquiring such MR images. In an exemplary embodiment, the invention provides an enteric contrast medium formulation. An exemplary formulation comprises, (a) an enteric contrast medium comprising a encapsulated gas or partial vacuum particle suspended in water.

The embodiment of the invention discloses an under-sampling point recovery method and device in magnetic resonance imaging and a magnetic resonance imaging system. The method comprises the following steps: in the process of performing magnetic resonance scanning on an imaging target, acquiring magnetic resonance signals of each channel in an undersampling mode, and putting the acquired magnetic resonance signals of each channel into a K space of each channel; and for any under-sampling point in the K space of each channel of the imaging target, recovering the under-sampling point by adopting a mode of performing high-order interpolation on the surrounding data points of the under-sampling point. According to the embodiment of the invention, the recovery accuracy of the under-sampling point in MR imaging is improved, so that the quality of the MR image is further improved.

The application discloses a white atractylodes rhizome softening endpoint discrimination method and system based on multi-modal data fusion and deep learning, adopts a Fourier transform near-infrared spectrometer, a low-field nuclear magnetic resonance instrument and a texture analyzer to perform multi-time point synchronous collection on a white atractylodes rhizome softening process, acquires data, and performs pretreatment after time sequence alignment and cleaning. After the above data is extracted and features are spliced into a combined feature vector, the combined feature vector is input into a convolutional neural network branch to extract a first feature vector; the nuclear magnetic resonance image is input into a residual neural network to extract a second feature vector; after the two feature vectors are fused, feature reweighting is performed through an SE-Block attention module, and finally, a regression layer is input to output a softening index S. The application eliminates false softening signals of single dimension discrimination, realizes a change from a traditional Chinese medicine processing black box operation to transparent production, and provides an objective technical means for traditional Chinese medicine decoction piece quality control.