35 results about "Multi contrast" patented technology

The invention discloses a medical image segmentation method based on high-resolution modal guidance and cross-modal boundary perception, and the method comprises the steps: carrying out the data preprocessing and enhancement of multi-contrast magnetic resonance imaging data, obtaining a boundary mask through a Canny operator and a Dilatation operation, constructing a multi-modal low-resolution data set, and carrying out the recognition of the multi-modal low-resolution data set; meanwhile, a high-resolution T2f modal data set is reserved, and the data set is divided into a training set, a verification set and a test set; a segmentation model is constructed, and the segmentation model comprises a high-resolution mode-guided double-encoder architecture module, a cross-level attention collaboration mechanism module, and a segmentation branch and boundary prediction branch decoder module; designing a training strategy of joint optimization of boundary contour detection and region segmentation, training the segmentation model by using a training set, and storing optimal model parameters on a verification set; and carrying out model performance verification in the test set, and segmenting a to-be-tested medical image by using the verified segmentation model.

The invention relates to a multi-contrast magnetic resonance image super-resolution reconstruction method and system. The method comprises the following steps: collecting an image data set, preprocessing the image data set, and dividing the image data set into a training set and a test data set; combining a Hilbert curve, a state space model and a frequency domain enhancement mechanism to construct a multi-contrast magnetic resonance super-resolution reconstruction model based on Hilbert double-domain fusion Mamba; and training a multi-contrast magnetic resonance super-resolution reconstruction model based on Hilbert double-domain fusion Mamba by using the training data set, and then completing the test of the test data set to obtain a super-resolution reconstruction image of the target contrast magnetic resonance image. Frequency domain features are scanned through a Hilbert curve, a cross-modal global frequency dependency relationship is captured, and high-frequency texture details are effectively recovered. And multi-modal local texture information is dynamically fused through a channel attention mechanism, so that neglect of local details by linear scanning is avoided, and the texture reconstruction precision is improved.

The invention discloses a multi-contrast magnetic resonance image reconstruction method and device based on detail contour feature perception. The method comprises the following steps: acquiring a target modal initial image and an auxiliary modal initial image; constructing an iterative network formed by alternately cascading image domain reconstruction units and data consistency layers, wherein each image domain reconstruction unit comprises an encoder and a decoder; in the first iteration, target modal initial images and auxiliary modal initial images are spliced and then input, an encoder extracts shared features firstly, then global contour features and high-frequency detail features are separated in parallel, and potential features are obtained through collaborative fusion; the decoder takes the potential features as input and outputs an image domain preliminary reconstruction result; the data consistency layer transforms the preliminary result into a k space, performs consistency correction on the preliminary result and a target modal sampling point, and then inversely transforms the preliminary result back to an image domain to complete one iteration; and splicing the current output and the auxiliary modal initial image again, inputting the spliced image into a next round of iteration, and repeating the process until a preset number of times to obtain a final target modal magnetic resonance image.

The invention discloses a multi-contrast MRI joint reconstruction method, system and device and a medium, and relates to the technical field of medical imaging and deep learning, and the method comprises the following steps: collecting under-sampling MRI image data of different contrasts, and generating an optimization objective function based on a plurality of contrasts; decomposing the optimization objective function into a first sub-problem related to an auxiliary variable and a second sub-problem related to an objective variable; and alternately solving the first sub-problem and the second sub-problem in sequence to obtain a plurality of optimal MRI reconstructed images. According to the method, feature interaction of multi-contrast data is carried out in a spatial domain and a frequency domain, so that efficient complementation and collaborative modeling of multi-contrast features are realized, and the problem of insufficient utilization of information between contrasts in a traditional method is solved. By sensing the characteristics of each contrast, targeted prompts can be generated to guide the reconstruction process. Therefore, the quality of low-quality contrast is improved, and the overall reconstruction result is enhanced.

The invention relates to a multi-contrast MRI (Magnetic Resonance Imaging) super-resolution method based on Mama. The method comprises the following steps of selecting a public multi-contrast MRI image data set Q; performing data preprocessing on all the MRI images in the Q to form a training set Dall; constructing a super-resolution model M, and inputting data into a corresponding feature extraction module to extract features according to a data format requirement of the model; performing context feature matching on the extracted features to obtain a matching feature set FM of different scales; and performing feature fusion operation on all matching features in the Ftarlr and the FM in sequence, performing each merging operation in a corresponding reconstruction module, and finally obtaining a reconstructed high-resolution target image TargetSR. By using the method, features can be deeply extracted, and detail features can be transferred from a high-resolution short-time MRI image to a target low-resolution long-time MRI image.

Methods and systems are provided for synthesizing a contrast-weighted image in Magnetic resonance imaging (MRI). The method comprises: receiving a multi-contrast image of a subject, where the multi-contrast image comprises one or more images of one or more different contrasts; and generating, by a deep learning model, a synthesized image having a target contrast that is different from the one or more different contrasts of the one or more images. The deep learning model is trained by a framework comprising a segmentation network for generating a segmentation map, a classification network for generating a pathology aware map and a reconstruction network for generating a plurality of synthesized images with different brightness levels in a tissue area.

The embodiment of the invention provides a magnetic resonance imaging method and related equipment. The magnetic resonance imaging method comprises the following steps: applying a multi-spin echo sequence in each magnetization reset period, and collecting a group of multi-spin echo data sets until M groups of multi-spin echo data sets are obtained; after each magnetization reset period, a T1rho preparation pulse with spin locking duration is applied, then a multi-gradient echo sequence is applied, a group of multi-gradient echo data sets are collected until M groups of multi-gradient echo data sets are obtained, and the M groups of multi-spin echo data sets and the M groups of multi-gradient echo data sets correspond to M different spin locking durations respectively; and performing fitting operation on the M groups of multi-spin echo data sets and the M groups of multi-gradient echo data sets to generate a quantitative atlas. According to the technical scheme, the problems that a traditional T1rho sequence is long in scanning time, low in signal-to-noise ratio and single in contrast ratio are effectively solved, and the technical effects of time multiplexing and multi-contrast imaging are achieved.

Systems and methods are described for segmenting medical images, such as magnetic resonance images, using a deep learning model that has been trained using random dropped inputs, standardized inputs, or both. Medical images can be segmented based on anatomy, physiology, pathology, other properties or characteristics represented in the medical images, or combinations thereof. As one example, multi-contrast magnetic resonance images are input to the trained deep learning model in order to generate multiple segmented medical images, each representing a different segmentation class.

The invention discloses a multi-contrast magnetic resonance image reconstruction method based on frequency domain error priori guidance, and the method comprises the steps: carrying out the modeling of a characteristic decomposition strategy, space alignment and k-space data in the design of a deep expansion network through frequency domain error priori guidance, and giving a definite physical constraint to the network; and irrelevant background or noise in the reference image, data acquisition efficiency and reconstruction quality under a significant sub-sampling condition, and a signal-to-noise ratio and marginal definition of the target image are filtered out.

According to one embodiment, an ultrasound imaging system is configured to receive images from an ultrasound imaging device, and output, to a display in communication with the processor circuit, a screen display including an image and a user control comprising a plurality of control positions. The system is further configured to receive a control input associated with a single selected position of the user control, and based on the single selected position, determine at least two altered image setting values associated with at least two image settings of the plurality of image settings. The system then generates an updated image using the at least two altered image setting values. Accordingly, a single, intuitive control can change multiple visual aspects of an ultrasound image, such as changing the image from grayscale to color, and many contrast and / or brightness levels in between, in a single user action.

This application belongs to the field of medical image processing technology, specifically disclosing a hybrid domain multi-contrast MRI super-resolution method and system based on variational networks. The method includes: acquiring and preprocessing high-resolution auxiliary images, high-resolution target images, and masks to obtain multi-channel high-resolution auxiliary images, low-resolution target images, and masks; iteratively updating the low-resolution target image of each channel using a hybrid domain multi-contrast variational network, and weightedly fusing the super-resolution target images of all channels to obtain the final super-resolution target image; measuring a loss function to train an MRI super-resolution model; and inputting the actual low-resolution MRI image into the MRI super-resolution model to obtain the actual super-resolution image. This application maintains the good interpretability of model-based methods, increasing the credibility in clinical practice, while leveraging the powerful feature representation capabilities of deep neural networks to effectively improve image reconstruction results, providing more accurate pathological information for precision medicine.

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.

Methods and systems are provided for synthesizing a contrast-weighted image in Magnetic resonance imaging (MRI). The method comprises: receiving a multi-contrast image of a subject, where the multi-contrast image comprises one or more images of one or more different contrasts; generating an input to a transformer model based at least in part on the multi-contrast image; and generating, by the transformer model, a synthesized image having a target contrast that is different from the one or more different contrasts of the one or more images, where the target contrast is specified in a query received by the transformer model.

The application discloses a kind of based on single-balanced detector's multiple contrast Jones matrix OCT imaging system, belong to optical imaging technical field.Sweeping laser light is divided into two beams by 1*2 broadband fiber coupler, one enters sample arm polarization delay module, generates two orthogonal sample lights of equal power, optical path difference is ξ, detects biological tissue, and sample returns the backscattering light transmission to 50 / 50 broadband fiber coupler by three-port fiber ring;With another into reference arm polarization delay module, generated two orthogonal reference lights of equal power, optical path difference is 2ξ, after interference, it is collected by a balanced detector.High-speed data acquisition card directly processes interference signal to realize real-time imaging;Another channel acquires k-clock signal, improves the detection accuracy of system by calculating correlation to system phase compensation.The application is suitable for medical fields and the like, to simplify system structure, reduce cost, save data processing time.

According to one embodiment, an ultrasound imaging system is configured to receive images from an ultrasound imaging device, and output, to a display in communication with the processor circuit, a screen display including an image and a user control comprising a plurality of control positions. The system is further configured to receive a control input associated with a single selected position of the user control, and based on the single selected position, determine at least two altered image setting values associated with at least two image settings of the plurality of image settings. The system then generates an updated image using the at least two altered image setting values. Accordingly, a single, intuitive control can change multiple visual aspects of an ultrasound image, such changing the image from grayscale to color, and many contrast and / or brightness levels in between, in a single user action.

The application discloses an anatomic structure perception low-field multi-contrast fast MRI joint reconstruction method, and is specifically implemented according to the following steps: step 1, constructing an anatomic structure perception low-field multi-contrast magnetic resonance image joint reconstruction model; step 2, constructing an anatomic structure perception low-field multi-contrast magnetic resonance image joint reconstruction network according to the reconstruction model constructed in step 1; step 3, training the anatomic structure perception low-field multi-contrast magnetic resonance image joint reconstruction network; and step 4, applying the trained anatomic structure perception low-field multi-contrast magnetic resonance image joint reconstruction network to magnetic resonance imaging. The method solves the problem of insufficient imaging optimization of a lesion part in the existing reconstruction method.

This application provides a method and apparatus for rapid multi-contrast magnetic resonance imaging based on helical trajectory acquisition. The method includes: constructing a modular multi-contrast imaging pulse sequence composed of multiple preparation modules, each preparation module being used to generate different magnetic resonance signals; generating magnetic resonance signals according to the modular multi-contrast imaging pulse sequence, and acquiring the magnetic resonance signals using a helical trajectory to obtain acquired magnetic resonance signals; and performing imaging reconstruction based on the acquired magnetic resonance signals to obtain magnetic resonance images with different contrasts. This method improves the generation efficiency of magnetic resonance signals by generating magnetic resonance signals with different contrasts through a modular multi-contrast imaging pulse sequence. Since the helical acquisition trajectory has high encoding efficiency, using a helical trajectory acquisition can effectively improve the acquisition efficiency of magnetic resonance signals, thus increasing the imaging speed of multi-contrast magnetic resonance images.

The present application relates to an MRI image reconstruction method, device, electronic device, and storage medium, wherein the MRI image reconstruction method includes: obtaining multi-contrast MRI sample data, including target modality and auxiliary modality high-resolution images; performing frequency domain conversion on the target modality high-resolution image and truncating high-frequency components to generate low-resolution frequency domain data; then performing spatial domain conversion on the target modality high-resolution image to generate a spatial domain low-resolution image; inputting the low-resolution frequency domain data and the spatial domain low-resolution image into a diffusion model, using the diffusion model to extract features of the two types of low-resolution data in the frequency domain and spatial domain respectively to generate current time step features; and using a structural attention mechanism to perform feature fusion on the current time step features and the features of the auxiliary modality high-resolution image to obtain a reconstructed image of the target modality. Through this application, the difficult problem of balancing spectral fidelity and detail enhancement in traditional MRI super-resolution methods is solved, significantly improving reconstruction efficiency and image quality.

The invention provides a segmented frequency domain self-supervised multi-contrast MRI (Magnetic Resonance Imaging) super-resolution reconstruction method. The method comprises the following steps: constructing and training a super-resolution reconstruction model, inputting to-be-reconstructed MRI image information of a tested object into the trained super-resolution reconstruction model, and outputting a continuous-scale high-resolution reconstruction image. According to the super-resolution reconstruction model provided by the invention, high-quality reconstruction can be completed by utilizing low-resolution data of a patient, and dependence on an external big data set is reduced; multiple MRI contrast ratios are processed at the same time, so that complementary information of all modes is fused to the maximum extent, and the overall reconstruction effect is improved; the MRI data information is effectively supervised, so that the constraint of low-frequency signals can be ensured, and a better high-frequency detail and edge reconstruction effect can be achieved.

Magnetic resonance imaging (“MRI”) using a spin- and gradient-echo (“SAGE”) pulse sequence with blip up-down acquisition (“BUDA”) encoding enables distortion-free, high-resolution diffusion-weighted imaging and / or quantitative parameter mapping. Phase-encoding polarities are alternated across shots during a multi-shot acquisition. In each shot, multi-contrast data are acquired at echo times associated with a gradient echo, a mixed gradient-and-spin echo, and a spin echo. High in-plane resolution and distortion-free quantitative parameter maps can be generated, such as T2 maps. T2* maps, paramagnetic susceptibility maps, and diamagnetic susceptibility maps. Diffusion-weighted data can be acquired using diffusion encoding gradients and BUDA encoding, where multi-contrast data are acquired in the b=0 acquisition. Diffusion parameter maps can be generated from the b=0 and diffusion-weighted data.

Systems and methods are described for segmenting medical images, such as magnetic resonance images, using a deep learning model that has been trained using random dropped inputs, standardized inputs, or both. Medical images can be segmented based on anatomy, physiology, pathology, other properties or characteristics represented in the medical images, or combinations thereof. As one example, multi-contrast magnetic resonance images are input to the trained deep learning model in order to generate multiple segmented medical images, each representing a different segmentation class.

The invention discloses a construction deviation high-precision detection system and method based on three-dimensional laser scanning, and the system comprises a point cloud collection module, a data preprocessing module, a noisy point elimination module, a deviation analysis module, and a report generation module. The method comprises the following steps: carrying out noisy point removal on point cloud data according to regions and components, registering a processed lightweight point cloud model with a BIM model, calculating a deviation value from a point cloud to a design surface by adopting a distance in a normal direction, enabling a result to directly correspond to construction acceptance indexes such as perpendicularity and flatness, and automatically generating a visual comprehensive analysis report through a report generation module. And the coordinate of the maximum deviation point is output for structural safety recheck, so that high-precision, traceable and lightweight intelligent evaluation of the whole-field construction quality is realized, the problems of multiple interferents, contrast distortion, extensive analysis and the like in a complex construction field are effectively solved, and the method has a relatively high popularization value.

The present application relates to the technical field of image reconstruction, and provides a multi-contrast magnetic resonance image reconstruction method, device, equipment, medium and product, wherein the method comprises: acquiring a plurality of initial magnetic resonance images of different contrasts; updating each initial magnetic resonance image by iteratively solving a target function until a preset convergence condition is met, to obtain a plurality of target magnetic resonance images of different contrasts after reconstruction; and the target function is used to constrain each initial magnetic resonance image to satisfy an amplitude constraint relationship and a phase constraint relationship. On the basis of ensuring the reconstruction quality of multi-contrast magnetic resonance images, the present application significantly improves the imaging acceleration multiple, i.e. improves the reconstruction efficiency of multi-contrast magnetic resonance images.

Automated processing and radiomic analysis of magnetic resonance imaging (“MRI”), such as multi-contrast MR images, and magnetic resonance fingerprinting (“MRF”) data, such as quantitative parameter maps, are integrated into a single workflow.

A method of imaging a biological material having a component that exhibits an ultra-short transverse relaxation time after excitement by electromagnetic energy is disclosed. More specifically, balanced steady state free precession ultra-short echo time (bSSFP UTE) magnetic resonance imaging (MRI) is used in combination with 3D center-out trajectory data collection and image subtraction techniques, to yield accurate high spatial resolution images of a material component having an ultra-short transverse relaxation time. In an embodiment, the 3D center-out trajectory can be a 3D rosette k-space trajectory. The disclosed methods can be used to image, among other things, biological materials such as without limitation, cortical and trabecular bones, lung parenchyma, tendons, and ligaments. In a particular example, the disclosed methods are used to image the myelin bilayer in brain white matter, such as for example, to detect, treat, or monitor brain lesions in multiple sclerosis patients.

The invention discloses a senile dementia related multi-contrast brain structure magnetic resonance imaging analysis method which comprises the following steps: acquiring multi-contrast brain structure magnetic resonance imaging data including T1 weighted imaging, T2 weighted imaging, proton density weighted imaging PD, liquid attenuation inversion recovery FLAIR and magnetic sensitivity weighted imaging SWI; constructing a model for multi-contrast brain structure magnetic resonance imaging analysis, wherein the model comprises an image denoising module, an image registration module and an image segmentation module; inputting the acquired magnetic resonance imaging data into the trained model; in the first step, noise suppression images corresponding to all contrast ratios are output, in the second step, multi-modal image registration is carried out, contrast ratio alignment images of unified voxel grids are generated, and in the third step, a final segmentation probability graph and a corresponding tissue label are output. By using the system and the method, high-quality, automatic and clinically deployable nuclear magnetic resonance imaging (MRI) brain image analysis is realized. The method can be widely applied to the field of medical image processing.

The application belongs to the technical field of medical image processing and computer-aided diagnosis, and discloses a multi-contrast learning coronary artery high-risk plaque detection method, system and terminal. A two-dimensional image sequence is extracted as a sample along a coronary artery center line point marked by a doctor on three-dimensional medical scanning data, and a sample data set is divided. A multi-contrast learning coronary artery high-risk plaque detection network based on a Transformer is constructed by taking a coronary artery two-dimensional image sequence sample as input and whether an image contains a high-risk plaque as output, so that coronary artery high-risk plaque detection is realized. The coronary artery high-risk plaque detection method does not need to label the extracted data sample, and thus labeling errors are avoided. A multi-path twin network based on the Transformer is trained using a large amount of unlabeled data, which is helpful to improve the ability of the network to generate feature representation. Patient-level feature representation is generated through feature recoding for final prediction, so that the working time is shortened.

The present invention discloses a deep learning-based method for detecting cerebral microbleeds for automated CMB detection using both SWI and phase images. Valid CMB data is selected using a 3D fast radial symmetry transform, and then false positives are reduced using a deep residual neural network. Through data preprocessing and enhancement, the model provides high sensitivity and a low number of false positives, outperforming manual and single-channel models. This method is a two-stage model for CMB detection using deep learning and 3D multi-contrast MRI data. The use of phase images along with SWI images significantly improves performance. By controlling the maximum translation amount, the model is also focused on the central region of the 3D volume to reduce interference from nearby structures. Increased test time further stabilizes the prediction and reduces uncertainty caused by doubts about valid CMB data. Compared to the SWI model, the better performance of the phase image plus SWI model is not only due to the differentiation of calcifications, but also due to the removal of false positives associated with blood vessels.

The application discloses a kind of based on double-domain feature and cold diffusion degeneration multi-contrast MRI arbitrary scale super-resolution reconstruction method.The method first obtains multi-contrast MRI slice and carries out spatial alignment processing;Second, construct 2D K space cold diffusion degeneration model, through Gaussian variable density mask simulates real MRI physical undersampling law;Subsequently, design based on time perception's double-domain multimodal feature extraction network, in spatial domain correction texture dislocation, in frequency domain enhances structural details, and generates multi-scale conditional feature pyramid;Finally, construct based on scale self-adaptive conditional mechanism's implicit diffusion reconstruction network, dynamically allocates feature fusion ratio, and breaks through pixel grid limit by continuous spatial coordinate decoding.Combining DDIM recursion and K space data consistency correction, the application effectively solves the scale fixed, generation exists illusion and other problems of existing method, realizes high-efficiency, high-fidelity arbitrary scale MRI super-resolution reconstruction.

The application discloses a multi-contrast MRI joint reconstruction method, system, device and medium, relates to the technical field of medical imaging and deep learning, and comprises the following steps: collecting under-sampling MRI image data of different contrasts, and generating an optimization objective function based on multiple contrasts; the optimization objective function is decomposed into a first sub-problem about auxiliary variables and a second sub-problem about target variables; the first sub-problem and the second sub-problem are alternately solved in sequence, and multiple optimal MRI reconstruction images are obtained. The application realizes efficient complementary and collaborative modeling of multi-contrast features by performing feature interaction of multi-contrast data in the spatial domain and the frequency domain, and overcomes the problem of insufficient utilization of information between contrasts in the traditional method. By perceiving the features of each contrast, targeted prompts can be generated to guide the reconstruction process. Thus, the quality of low-quality contrast is improved, and the overall reconstruction result is enhanced.