53 results about "Quantitative imaging" patented technology

The invention discloses a living blood vessel and lymph multi-parameter quantitative photoacoustic microscopic imaging system which comprises a high repetition frequency laser source, a photoacoustic scanning probe and a molecular imaging device. Through the cooperation of the multi-wavelength fast switching laser and the high-speed scanning probe, synchronous, dynamic and quantitative imaging of vascular function parameters and lymph concentration in a living tissue microenvironment is realized. The system has a video-level imaging rate and can capture a rapid biological process; through coaxial design of dispersion correction and a photoacoustic focus, high spatial resolution and high signal-to-noise ratio of a multispectral image are guaranteed; and the compact probe design realizes large-range scanning. The technology provides a powerful in-vivo visualization tool for research on life science problems such as tumor evolution and drug metabolism.

According to the subclinical non-obstructive coronary atherosclerosis metaphase plaque progress risk prediction method based on interpretable machine learning provided by the invention, multi-dimensional images and clinical features are integrated, and individualized risk prediction of subclinical non-obstructive coronary atherosclerosis is realized. Quantitative imaging biomarkers are managed for a long time, a key tool is provided for early screening of high-risk individuals, clinical doctors can be helped to judge whether comprehensive strategies such as enhanced lipid lowering, anti-inflammation and lifestyle intervention need to be adopted in time or not, plaque stabilization or fading is maximized, and the clinical effect is improved. And further, the future cardiovascular event risk is reduced. According to the method, a Shapley additive SAHP interpretation technology is introduced, the relative contribution of each prediction feature is quantified, and the interpretability of a machine learning model is improved. According to the method, a webpage tool for calculating the plaque progress probability on line is deployed, and the contribution degree of each feature to the plaque progress prediction result of a specific patient can be displayed more visually.

A method and a system for generating a multimodal diagnostic output related to a pathological condition of a patient includes at least one processor and a memory storing instructions executable by the processor to receive medical image data and narrative data of the patient. The medical image data is preprocessed through normalization, while the narrative data is standardized to ensure consistency. The preprocessed image data is input into a trained deep residual network (ResNet) to extract quantitative imaging features indicative of the pathological condition. In parallel, the preprocessed narrative data is input into a thematic analysis module to derive thematic codes reflecting emotional, cognitive, or social factors of the patient. The extracted imaging features and thematic codes are fused into a combined feature vector, which is processed by an integrated diagnostic model to generate a multimodal diagnostic output that enhances clinical precision and contextual interpretation.

The invention discloses a multi-element quantitative analysis method for laser ablation inductively coupled plasma mass spectrometry, and aims to solve the problems that the quantitative process of the existing LA-ICP-MS technology depends on a standard sample, the automation degree is low, and the existing LA-ICP-MS technology cannot adapt to complex multi-element signals. According to the method, full-automatic and multi-element (such as 9 main quantities and 30 trace elements) quantitative analysis is realized in the LA-ICP-MS field without an internal standard and an external standard, the analysis efficiency, the accuracy and the data comparability among different platforms are remarkably improved, and a breakthrough solution is particularly provided for application of element quantitative imaging and the like.

The application relates to a kind of quantitative imaging methods of living cells based on digital holographic microscopic sequential displacement aberration correction, and belongs to the field of optical measurement, comprising: collecting three holograms by sequentially displacing living cells; obtaining three original phase maps by phase demodulation; obtaining total mask map; sequentially displacing phase map in reverse direction; performing difference calculation to obtain global phase system aberration difference data; obtaining local system aberration difference data by using total mask map; performing difference processing on Chebyshev polynomial to obtain local polynomial difference data by using total mask map; fitting global system aberration by calculating corresponding coefficients from difference data; subtracting global system aberration from three original phase maps to obtain phase map of living cells after aberration correction. The application realizes high-precision quantitative phase imaging of living cells while retaining high-frequency information, has excellent displacement distance robustness, does not need to be equipped with high-precision displacement mechanism, and greatly reduces the hardware cost of measurement system.

This invention discloses a single-snapshot spatial frequency domain imaging and morphology correction method, system, and device, comprising: acquiring a set of monochromatic fringe images with different center wavelengths based on the same projected image; simultaneously inputting each monochromatic fringe image in the set into two parallel and independent deep learning networks, wherein the first deep learning network is used to extract the DC and AC components of the image; the second deep learning network is used to extract the wrapping phase component and fringe hierarchy information of the image, and perform absolute phase calculation to obtain the three-dimensional morphology before correction; performing height correction on the three-dimensional morphology and calculating the corrected diffuse reflectance image; performing background segmentation on the corrected diffuse reflectance image and spatially aligning it to the same coordinate system; and retrieving the optical characteristic parameters and physiological parameters of the tissue based on the spatially registered multi-wavelength diffuse reflectance data. This invention ultimately achieves real-time, wide-field, high-precision, and highly robust quantitative imaging of tissue physiological parameters.

The application discloses a B0 robust cardiac T1 quantitative imaging method, and belongs to the field of magnetic resonance quantitative imaging, and comprises the following steps: designing a dual-phase increment cardiac T1 quantitative imaging acquisition sequence, collecting original data based on the dual-phase increment cardiac T1 quantitative imaging acquisition sequence, constructing a simulation signal dictionary based on a magnetic resonance physical model, matching the original data with the simulation signal dictionary to obtain the best dictionary entry corresponding to the original data, and obtaining a T1 quantitative image and a B0 quantitative image based on the best dictionary entry. The application encodes B0 information by using a dual-phase increment sequence design, realizes B0 robust T1 quantitative imaging, reduces the influence of B0 field inhomogeneity under high field strength, and reduces bSSFP black band artifact interference. In combination with the dictionary matching technology, T1 and B0 are jointly estimated, more accurate T1 estimation and B0 quantitative images are provided, the method is easy to deploy and apply on an existing MRI platform, and has high implementation and migration feasibility.

The application provides a one-stop multi-delay arterial spin labeling kidney perfusion measurement method and system, and belongs to the field of magnetic resonance imaging. The method comprises the following steps: acquiring a time-encoding-based kidney arterial spin labeling sequence image of a subject; acquiring a kidney M0 image of the subject, wherein the M0 image is consistent with the number of layers, resolution and image acquisition mode of the kidney arterial spin labeling sequence image; and performing registration on the kidney arterial spin labeling sequence image and the M0 image to obtain a kidney perfusion measurement result of the subject. The application can realize one-stop multi-delay blood perfusion quantitative imaging of the kidney, greatly improves the imaging efficiency of traditional kidney multi-delay arterial spin labeling imaging, and fills the blank of one-stop multi-delay blood perfusion imaging of the kidney.

The application discloses a kind of time sequence in situ zymogram soil enzyme activity quantitative imaging methods based on multi-parameter screening, it is related to soil enzyme activity detection technical field, the method collects time sequence fluorescence image of enzymatic reaction, constructs pixel-level time sequence gray matrix;Multi-stage screening is carried out to pixel, including initial screening based on gray value and standard deviation, slope and goodness of fit screening of sliding window fitting, and reaction time window final screening;Extract maximum local linear growth rate as uncorrected enzyme activity, introduce diffusion correction model correction, obtain corrected enzyme activity;Quantitative conversion and visual output are realized in combination with fluorescence standard curve.This application changes static measurement into dynamic process analysis, effectively suppresses background noise, significantly improves the sensitivity, spatial resolution and quantitative accuracy of enzyme activity detection.

The application discloses a kind of superficial tissue viscoelasticity imaging system and imaging method, belong to biomedical ultrasonic imaging technical field;Among them, superficial tissue viscoelasticity imaging system includes ultrasonic robot, synchronous control module and data processing module;Ultrasonic robot is carried with the flexible patch ultrasonic probe of multiple source pressure sensing module setting, and ultrasonic robot, flexible patch ultrasonic probe and synchronous control module cooperate to realize the synchronization of creep mechanics excitation application, ultrasonic data acquisition and mechanics data acquisition;Data processing module is used to based on KVFD fractional viscoelasticity model inversion elastic modulus, flow parameter and viscous time constant, generates viscoelasticity multi-parameter quantitative imaging graph.The present application realizes automatic precision force loading and standardization imaging, solves the technical problems of poor repeatability of manual pressurization, unstable curved surface fitting, large physiological interference and insufficient viscoelasticity quantitative precision in the prior art.

The invention discloses a multi-parameter magnetic resonance quantitative imaging method and system, and relates to the technical field of MRI (magnetic resonance imaging), and the method comprises the steps: employing a multi-overlap echo sequence XMOLED, carrying out the simulation of magnetic resonance simulation software, and generating a simulation XMOLED image, constructing a simulation data set composed of a large number of paired simulation XMOLED images, simulation T2, T2 * and an apparent diffusion coefficient (ADC) quantitative graph, and training a deep learning neural network used for reconstruction of the magnetic resonance parameter quantitative graph; sequence parameters are configured on a magnetic resonance imaging instrument, an XMOLED signal of an actual imaging object is collected, and an XMOLED image of the actual imaging object is obtained through signal processing; and inputting the XMOLED image of the actual imaging object into the trained magnetic resonance parameter quantitative graph reconstruction network for reconstruction to obtain T2, T2 * and ADC quantitative graphs of the actual imaging object. According to the method, T2, T2 * and ADC quantitative diagrams can be obtained at the same time only through single-sequence XMOLED collection, the problem that scanning time is prolonged due to multi-sequence combined imaging is solved, and rapid and accurate multi-parameter quantitative magnetic resonance imaging is achieved.

This invention provides a method and system for motion correction in quantitative magnetic resonance imaging (MRI) based on dictionary matching, comprising: Step S1: generating a dictionary by simulating the evolution of the MRI signal and constructing an optimization problem to be solved; Step S2: performing dictionary matching on the acquired quantitative imaging image sequence to obtain a parameter map and a simulated image sequence; Step S3: registering the acquired image sequence to the simulated image sequence to correct motion; alternately executing steps S2 and S3 to solve the optimization problem until convergence, obtaining the motion-corrected image sequence and parameter map. This invention models the contrast changes of the quantitative imaging image sequence based on MRI physics, thus being more accurate and robust than methods based on image characteristics.

The invention relates to a microwave-induced thermoacoustic transcranial quantitative imaging method based on a REAGU-Net network, and the method achieves the simultaneous quantitative reconstruction of dielectric constant, conductivity and sound velocity in brain tissue through the MITAT technology, and provides a new methodology for the characteristic analysis of the brain tissue. A REAGU-Net novel network is developed, an attention guiding block and a residual error inducing block are combined to process the influence of acoustic non-uniformity on reconstruction quality, and effective application of deep learning in quantitative reconstruction is shown; the technology not only shows a good result in cerebral hemorrhage detection, but also can be potentially applied to detection and diagnosis of various diseases including breast cancer, liver diseases and thyroid diseases, and a new quantitative analysis tool is provided for clinic; the DL-MITAT method provided by the invention can provide quantized physical characteristic data, and the data not only is helpful for imaging, but also can provide support for physiological information prediction and the like in subsequent electromagnetic treatment; compared with a traditional TCD or ultrasonic imaging method, the transcranial MITAT has the remarkable advantages that due to the fact that ultrasonic waves of the transcranial MITAT only need to be transmitted with the skull for one time, the possibility of image attenuation and degeneration is reduced, and the imaging quality is improved.

The invention discloses a multi-parameter quantitative method and system based on multi-overlap echo steady-state free procession and a multi-task learning network, and relates to magnetic resonance imaging. The method comprises the following steps: designing and debugging a multi-overlap echo steady-state free precession sequence to obtain a magnetic resonance image with multiple contrast (T1, T2, T2 *) weighting; generating a training sample of the deep neural network; designing a multi-task deep learning network fusing interlayer information; training a network weight by adopting the training sample; and the trained multi-task deep learning network is adopted to map the actually acquired magnetic resonance image, and quantitative images of a plurality of parameters are obtained at the same time. Rich multi-contrast multi-echo information is provided based on multi-overlap echo steady-state free precession, a multi-task deep learning network fuses characteristics of different tasks in different levels, multiple times of scanning are not needed, and rapid and accurate multi-parameter simultaneous quantitative imaging can be achieved in one time of scanning.

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 application relates to a simultaneous multi-layer magnetic resonance parameter quantitative imaging method, which relates to magnetic resonance imaging. The method comprises the following steps: S1, designing a simultaneous multi-layer magnetic resonance parameter quantitative imaging pulse sequence; S2, generating a training sample of a deep neural network; S3, training the deep neural network by using the training sample to obtain a trained deep neural network; S4, collecting k-space data of an actual imaging object by using the simultaneous multi-layer magnetic resonance parameter quantitative imaging pulse sequence and carrying out pretreatment to obtain an aliasing image of the actual imaging object; and S5, reconstructing the aliasing image of the actual imaging object by using the trained deep neural network to obtain a multi-layer magnetic resonance parameter quantitative image. The method can realize multi-layer magnetic resonance parameter quantitative imaging in one scanning, and can not only be used for a lower acceleration multiple, but also be suitable for a high acceleration multiple, so that the acquisition time of quantitative imaging is shortened.

The application discloses an X-ray phase quantitative imaging technology and a measuring method, device and equipment and a storage medium thereof. The scheme provided by the application avoids the phenomenon that positive and negative phase images are overlapped from the imaging mechanism and signal detection of the system, directly extracts a phase image of a sample without subsequent complex positive and negative phase image separation operation, simplifies the data processing process, and improves the efficiency of sample phase information acquisition. The imaging technology constructs the correlation between the imaging system parameters and the separation degree of positive and negative phase images, quantitatively designs the imaging conditions required by each optical device in the system, proposes an experimental method for measuring absolute phase signals, and the detector assembly scheme can accurately measure phase images with different separation directions and degrees.

The application provides a kind of extracellular vesicle quantitative detection method based on self-interference spectrum reconstruction, it is related to the intersection field of biomedical detection and optical engineering.The method comprises: adding clinical sample into digital microfluidic chip, and separating sample droplet from droplet with functional modification magnetic bead by electrode;After mixing two droplets, add vesicle binding solution and mix, then incubate;Through magnetic control fixed magnetic bead, remove solution, then add deionized water to clean magnetic bead;After removing magnetic bead cleaning solution, add vesicle eluent and incubate with magnetic bead;Separate out the droplet containing extracellular vesicle;Transfer the droplet containing extracellular vesicle to the upper of gold-coated glass, remove droplet after incubation;Use deionized water to clean hybridized gold-coated glass;Use self-interference spectrum imaging system to detect vesicle quantity and its particle size distribution.The application can realize extracellular vesicle quantitative counting, particle size measurement and surface protein marker detection simultaneously, and improve single vesicle quantitative imaging precision and detection efficiency.

The invention discloses a high-temporal-spatial-resolution accurate quantitative imaging system for mobile source emission pollutants, which is combined with a bearing platform, an optical acquisition subsystem, a control and data acquisition subsystem, a differential optical thickness calculation subsystem, a concentration quantitative inversion subsystem and a dynamic smoke plume concentration field reconstruction subsystem. And the smoke plume flow velocity field, the pollutant absorption difference optical thickness and the sparse space-time high-precision pollutant concentration are dynamically reconstructed based on a deep learning model constructed by a neural network, and the smoke plume concentration field of the pollutants is obtained, so that accurate and rapid imaging monitoring of the pollutants discharged by the mobile source is realized.

This invention discloses a method, system, device, and medium for processing data for predicting the risk of neonatal encephalopathy, belonging to the field of medical image processing. The method includes: acquiring conventional thick-slice T1-weighted and T2-weighted images of the neonatal brain; performing super-resolution reconstruction of the magnetic resonance imaging data based on self-supervised learning, reconstructing anisotropic thick-slice images into isotropic thin-slice images; performing quantitative analysis on the reconstructed high-resolution images, extracting multiple quantitative magnetic resonance parameters including brain region volume, cortical surface area, and T1 / T2 ratio; inputting the quantitative magnetic resonance parameters into a pre-trained neonatal encephalopathy prediction model, and outputting the predicted neurodevelopmental outcome. This invention can stably extract quantitative imaging features from conventional clinical thick-slice MRI images without increasing the number of scanning sequences or extending the scanning time, achieving early, objective, and accurate risk assessment of the neurodevelopmental outcome of neonatal encephalopathy, and has high clinical application value.

The invention provides a Raman spectrum label-free cell pH quantitative imaging method and system based on physical model constraint deep learning, and the method comprises the steps: collecting water Raman spectrums of different cell samples, and constructing a spectrum data set; recombining and normalizing the spectral data set to obtain a preprocessed spectral data set; constructing a physical model constraint deep neural network by adopting a deep learning framework based on the preprocessed spectral data set; and constraining the deep neural network based on the physical model to obtain a pH image of the to-be-analyzed cell. The method is suitable for a novel dynamic, quantifiable and unmarked monitoring normal form of stem cell differentiation research, cell metabolism state evaluation and cell treatment product quality control. The strong spectral feature extraction and non-linear mapping capability of deep learning is utilized, dependence on an external source probe and destructive sampling is avoided, and rapid and robust decoding of cell metabolic activity and microenvironment dynamic information from a complex water spectrum is achieved.

The application discloses an infant brain T2 weighted magnetic resonance imaging optimization method based on a fast spin echo sequence. First, T1, T2 and PD quantitative imaging of the infant brain from 0 to 24 months old is collected to obtain T1, T2 and PD values of the infant brain white matter and gray matter regions, and according to the relationship characteristics of the infant brain white matter T2 value and the gray matter T2 value, the infant is divided into different month groups. Then, based on the 3D T2 weighted imaging of the variable flip angle fast spin echo sequence, the signal intensity of the infant brain white matter and gray matter under different refocusing flip angle chains is calculated through an extended phase graph algorithm, and the best flip angle chain design scheme of each group is determined with the maximum white matter / gray matter contrast as the target. The application fills the blank of the infant brain T2 weighted imaging optimization, formulates the best flip angle chain optimization scheme of different month groups, and thus significantly improves the contrast of the infant brain T2 weighted imaging.

The invention relates to the technical field of medical imaging, in particular to an oxygen saturation quantitative imaging device and method for an endoscope. The shooting part is configured to collect reflected light of the target area under illumination of the light source and output a collected color image and an exposure control parameter corresponding to the color image; the image processing part comprises a spectrum reconstruction module which is used for carrying out image de-gain processing on the color image and reconstructing a single-band image signal with a set wavelength; the light intensity estimation module is used for respectively calculating light intensity data of the light sources; and the quantitative calculation module is used for calculating a light absorption coefficient based on the light intensity data, calculating oxyhemoglobin concentration, deoxidized hemoglobin concentration and an oxygen saturation value based on the light absorption coefficient, and generating an oxygen saturation distribution image. The oxygen saturation image generated by the method has rich anatomical structure information and accurate physiological parameter information, and a tissue hypoxia region can be visually displayed.

In one or more implementations, systems, methods and computer implemented processes are provided that are directed to a method of treating a subject with a lung tumor, the method comprising: obtaining computed tomography (CT) image slices of the subject, wherein the CT image slices comprise images of the lung tumor. In a further implementation, the systems, methods and computer implemented processes are directed to identifying a first CT image slice where the lung tumor has a largest diameter among the CT image slices; and determining intensity-skewness of the lung tumor on the first CT image slice. In a further implementation, the systems, methods and computer implemented processes are directed to treating the subject with surgery, chemotherapy and / or radiotherapy, if the intensity-skewness is no greater than −1.5.

The invention discloses a magnetic particle concentration and tissue viscoelasticity synchronous quantitative imaging method which comprises the following steps: forming an external time-varying magnetic field, acting on magnetic particles in a medium through the time-varying magnetic field, enabling the magnetic particles to vibrate and transmitting vibration displacement to surrounding tissues; acquiring original ultrasonic data of the magnetic particles and the surrounding tissues during vibration, and calculating actually measured axial vibration displacement of the magnetic particles and the surrounding tissues based on the original ultrasonic data; according to a physical information neural network, combining the actually measured axial vibration displacement, performing iterative solution under a double loss constraint condition, and synchronously outputting quantitative imaging results of the magnetic particle concentration, the tissue viscosity and the tissue shear modulus; wherein the dual loss constraint condition comprises a data loss constraint and a physical equation loss constraint. According to the method, two types of key information of magnetic particle concentration and tissue viscoelasticity can be synchronously and quantitatively imaged, and the quantitative precision and robustness are improved.

This invention provides a dynamic quantitative imaging method and imaging device based on magnetic resonance fingerprinting. The method includes: scanning according to preset acquisition parameters to obtain the time series of magnetic resonance images of all voxels; dividing the time series corresponding to each voxel into multiple time windows; matching each time window with the dictionary of the corresponding time window; and obtaining a quantitative map of the time period corresponding to each time window based on the matching result. In other words, this invention divides the time series of each voxel acquired by scanning into multiple time windows in the time dimension, and each time window is equipped with a dictionary. By matching the dictionary of each time window, the quantitative processing result of each time window for each voxel is obtained. Therefore, a quantitative map is obtained for each time period corresponding to each time window, thereby forming a quantitative map with high temporal resolution. This not only allows for the acquisition of quantitative maps for each time period but also the acquisition of imaging change information based on time changes.

Methods and systems are provided for analyzing diffusion weighted images (DWI) using impeded diffusion fraction models for quantitative imaging diagnostic assay of cancer, such as glandular tissue cancers. The Impeded diffusion fraction models are tissue and cancer independent and generate a single score representative of multi-compartment diffusion fractions occurring within each voxel of a DWI image.

The invention provides a high-accuracy ultrasonic microscopic imaging method based on scanning standard target plate self-learning, and relates to the technical field of ultrasonic microscopic image processing. The method comprises the following steps: scanning a standard target plate by using a probe of an ultrasonic microscopic scanning system to obtain a sample data set for modeling; based on the sample data set, a regression learning model with a nonlinear mapping capability is adopted to establish a mapping relation between the pixel gray scale and the actual physical size, and an initial modeling result is obtained; taking the initial modeling result as input, and carrying out iterative optimization on model parameters by utilizing a self-learning mechanism to obtain an optimized self-learning model; and applying the optimized self-learning model to a to-be-measured ultrasonic microscopic image, carrying out size prediction and error compensation on pixel gray scale data, and generating an optimized quantitative imaging result. The problems that in the prior art, when an ultrasonic microscopic imaging technology is used for detecting tiny defects, measurement errors are large, quantitative precision is insufficient, and correction depends on a complex sound field are solved.

The application discloses an overlapping echo-based magnetic resonance multi-parameter simultaneous quantitative imaging method and system. The method comprises the following steps: designing an overlapping echo-based steady-state free precession multi-parameter quantitative imaging sequence; determining sampling parameters of the overlapping echo-based steady-state free precession multi-parameter quantitative imaging sequence; adding the sequence and setting the sampling parameters in an advanced magnetic resonance instrument which meets the performance requirements of the sequence and the sampling parameters, and completing data acquisition to obtain magnetic resonance data; generating training samples of a deep neural network; training the deep neural network by using the training samples to obtain a trained deep neural network; and reconstructing a magnetic resonance multi-parameter image by using the trained deep neural network and k-space data collected by the magnetic resonance imaging sequence. The method can realize simultaneous quantitative imaging of magnetic resonance multi-parameters, and can utilize different echoes and / or different k-space information in the k-space to realize correction of non-ideal factors, including but not limited to artifacts, radio frequency field inhomogeneity, main magnetic field inhomogeneity and the like.