31 results about "Medical imaging technology" patented technology

This invention discloses a low-pass filtered non-breath-hold saline angiography combined with cardiac mirror contrast imaging for lung perfusion imaging, belonging to the field of medical imaging technology. The method includes the following steps: S1: determining whether the subject's tidal impedance variation meets the imaging criteria; S2: injecting contrast agent into the subject to perform angiography; S3: obtaining an impedance decrease signal; S4: combining cardiac mirror contrast imaging with lung perfusion images. This invention solves the problem of low success rate of saline angiography in existing technologies, achieves separation of thoracic impedance caused by tidal breathing and thoracic impedance caused by saline angiography, reduces the influence of the cardiac region on lung perfusion images, further improves the accuracy of lung perfusion imaging, greatly reduces the interference of breath-holding on respiratory circulation, improves the simplicity of clinical application, and expands clinical application scenarios.

The application discloses a CT dose self-adaptive optimization system and method thereof, and belongs to the technical field of medical images, which comprises a CT scanner, an image data processing workstation, a high-risk population analysis device, a dose parameter self-adaptive optimization device, a dose parameter automatic adjustment device and an intelligent learning unit, and based on the theory of information geometry, the dose parameter optimization problem is promoted from the Euclidean space to the Riemannian manifold space, the dose parameter manifold and the image quality manifold are constructed, the geodesic line is calculated on the manifold through the Fisher information matrix as the Riemannian metric, and the optimal dose path is found. The system adopts a double-manifold collaborative optimization mechanism, establishes a mapping relationship between the two manifolds, and realizes accurate optimization of parameters in combination with a geometric-guided genetic algorithm, and through pre-scanning, high-risk population analysis, information geometry optimization and automatic parameter adjustment, individualized dose control is realized, the radiation dose is additionally reduced by 30-45% compared with a traditional method, the image quality is maintained or improved, and the safety of CT examination is remarkably improved.

The present application relates to the field of medical imaging technology, disclose a biliary tract cancer CT image prediction method and system based on momentum attention and large model verification, the method comprises: based on the pre-training visual-linguistic large model extracts the visual features of the patient's upper abdominal non-enhanced CT image, constructs a high-dimensional visual embedding vector, initializes the historical momentum attention map and the initial reasoning text sequence, and the first momentum attention map is obtained by guiding and updating through the momentum mechanism; again extract the key image patch set and the initial reasoning text sequence, and the first reasoning text is obtained by interlacing fusion of the image and the text; repeatedly execute attention update and image-text fusion operation until the reasoning thought chain and the preliminary diagnosis conclusion are generated; the correlation degree of reasoning and diagnosis is evaluated by a pure text logical verifier to obtain a logical consistency score, and the target intelligent auxiliary diagnosis report is generated by assembling the score, the present application can improve the efficiency of biliary tract cancer CT image prediction.

This invention discloses a method and application for constructing a model to differentiate between nasopharyngeal carcinoma and nasopharyngeal lymphoma based on PET and CT combined with deep learning and radiomics. It relates to the field of medical imaging technology. Existing related studies have small sample sizes and single-center designs; they only use a single modality or a single feature type, failing to fully utilize the complementary advantages of multimodal approaches. This invention provides a method for constructing a model to differentiate between nasopharyngeal carcinoma and nasopharyngeal lymphoma based on PET and CT combined with deep learning and radiomics, including: collecting PET and CT images of nasopharyngeal carcinoma patients and nasopharyngeal lymphoma patients from medical institution A and medical institution B respectively; preprocessing the images from medical institution A and segmenting them into a training set and an internal validation set, and using the preprocessed images from medical institution B as an external validation set; extracting radiomics features and deep learning features; screening key features affecting the occurrence of nasopharyngeal carcinoma or nasopharyngeal lymphoma; and using the training set to train and generate an ALL model that integrates PET & CT dual-modality, radiomics features, and deep learning features.

A method for assessing quality of an echocardiogram image based on fusion of image and text features is provided, which relates to the field of medical imaging technologies. The method includes performing feature extraction and classification by using a target detection model, aligning image features with quality control text features by using a visual-language feature alignment module, and performing sentence template selection, linear projection, and merging by using a large language model. The method utilizes cross-domain transfer of image and text features, to generate accurate and comprehensive echocardiogram image quality assessment reports, thereby enhancing interpretability and granularity of assessment results; introduces the target detection model to recognize and understand positional relationships of different anatomical structures within medical images, thereby providing rich medical domain prior knowledge for subsequent quality assessment, and achieving effective cross-domain transfer from natural images to echocardiograms; and introduces sentence templates to ensure consistency of quality control text.

The present invention provides a full-stack medical imaging foundation model, re for performing medical image segmentation, classification and localization using a unified language-image correlation mechanism. The present invention leverages pretrained language-guided associations to automatically recognize and localize disease targets without requiring medical imaging knowledge or manual box-prompting. The invention enables comprehensive clinical tasks across multiple disease classes and various medical imaging techniques, improves segmentation efficiency, and reduces human input burden. With operability through human language-only prompts by non-radiology specialists, the present invention improves real-world applicability and enables deployment of foundation model-based segmentation in diverse clinical environments.

This invention discloses a method for solving the JSD (Joint Action-Impedance Synergy Index), a method for evaluating upper arm muscle rehabilitation exercises, and an evaluation system, belonging to the fields of rehabilitation assessment and medical imaging technology. Its key technical points are: acquiring the instantaneous instability sequence of joint displacement and the average impedance change value, and constructing the Action-Impedance Synergy Index (AISI) as an evaluation indicator to achieve a three-level probability distribution classification of muscle rehabilitation levels. This invention integrates temporal and physiological characteristics of movement, providing an objective, quantitative, and multimodal muscle rehabilitation assessment scheme suitable for evaluating the effectiveness of rehabilitation training.

The application discloses a kind of magnetic resonance non-enhanced lower limb arteriovenous combined imaging method, belong to medical image technology field, including S1, judging acquisition times, and carrying out first acquisition, S2, set the delay time of data acquisition, S3, configure fast interrupt steady state, and carry out data acquisition, S4, repeat S1-S3 until all regions are completed first acquisition Data collection process, S5, switch to second acquisition, and judge acquisition times, and carry out second acquisition, S6, using the same process as S2 and S3 carries out data acquisition, S7, repeat S5 and S6 until all regions are completed second acquisition Data collection, S8, image reconstruction is carried out, and the arteriovenous separation image map is obtained, the application uses above-mentioned method, by fusing fast interrupt steady state sequence and golden angle radial sampling track, realize lower limb arteriovenous synchronous high contrast imaging under the condition of not needing electrocardiogram control.

The application discloses a method and system for reconstructing three-dimensional images based on two-dimensional X-ray images, relates to the technical field of medical images, and comprises a micro X-ray tube array arranged according to a known geometric rule, each tube being independently controllable for exposure; a high-voltage control module providing each tube with an independently stable and switchable high-voltage power supply, supporting sequential pulse exposure; an image acquisition module receiving and converting X-ray signals into multiple frames of original two-dimensional digital images; and an image processing module registering multiple frames of images according to the geometric positions of the tubes, fusing to generate a single composite two-dimensional image, and finally reconstructing a three-dimensional image based on the composite image and multi-view geometric information of the tube array. The technology replaces mechanical movement with a static tube array to obtain multi-view data, and simplifies data processing and improves imaging efficiency and quality through a new process of fusing first and reconstructing later.

The present application belongs to the field of image feature analysis, and specifically refers to a skin image feature analysis method based on a reflective confocal microscope, which comprises distortion correction, image preprocessing and global perception. Through GPU accelerated lookup table encoding and decoding technology, the efficiency of distortion correction is significantly improved, the number of memory access is reduced, real-time and efficient image processing is realized, the quality of the skin medical image is improved in combination with medical imaging technology, which has great significance for clinical application; in combination with feature extraction, matching and global optimization technology, a high-precision global skin image is obtained and updated, effectively solving the geometric distortion problem caused by probe jitter or inter-frame alignment error, and being able to adapt to the instability of artificial handheld operation, generating a global skin image in single-point imaging of a shaking skin lesion position, and ensuring the continuity and consistency of image acquisition.

This application relates to the fields of computer and medical imaging technology, specifically to a CT-based image diagnostic model training method, image processing method, and system. The CT-based image diagnostic model training method includes: acquiring a current medical image diagnostic model trained under supervised fine-tuning, and sample unenhanced scan images, wherein the current medical image diagnostic model includes a diffusion generation module; using the diffusion generation module, performing multiple denoising operations on random noise images based on the sample unenhanced scan images to obtain multiple first predicted enhanced scan images; determining multiple dominance values ​​corresponding to the sample unenhanced scan images based on the multiple first predicted enhanced scan images and the sample unenhanced scan images; and performing reinforcement learning training on the diffusion generation module based on the multiple dominance values ​​to obtain the target medical image diagnostic model. This application improves the accuracy of predicted images, resulting in higher diagnostic accuracy and efficiency.

The application discloses a kind of scanning method and system of intraoral tomographic image based on machine vision, it is related to medical imaging technical field, the method includes: by miniaturized optical probe in oral cavity along preset trajectory moves and gathers image and information;Adaptive light compensation is executed, feature point extraction and matching, probe pose estimation;Carry out depth optimization and hole filling;Generation continuous tomographic slice;Realize the closed-loop control of tomographic image layer thickness consistency;The system includes: miniaturized optical probe module;Multi-modal data fusion and pose estimation module;Real-time depth optimization and hole repair module;Tomographic slice generation and layer thickness closed-loop control module;Central processing and display module.The application can improve the robustness and precision of probe motion trajectory estimation, repair depth map hole and distortion, ensure that tomographic slice sequence has uniform resolution in Z axis direction, and realize whole-process real-time or quasi-real-time processing, improve the practicability and diagnostic efficiency of system.

The present invention relates to the technical field of medical images, and specifically relates to a segmentation method and apparatus for magnetic resonance vascular architectural imaging (VAI). The method and apparatus involve: performing data preprocessing on a VAI image set; constructing a deep learning model, and using the VAI image set, which has been subjected to data preprocessing, to train the deep learning model, so as to optimize a model parameter; and using the trained and optimized deep learning model to perform automatic tumor region segmentation on a new VAI image, so as to generate a segmentation result. In the present invention, by using a deep learning model such as a convolutional neural network (CNN), the features of vascular architecture can be automatically learned, and accurate segmentation is performed with regard to microvascular changes in a tumor region.

This invention discloses a method for reconstructing magnetoacoustic electromagnetic particle concentration images based on compressed sensing, belonging to the field of medical imaging technology. The method includes: acquiring voltage signals, reciprocal current density data, and vibration velocity data of the reconstructed region from the detection electrode based on a simulation model; constructing a linear equation between the voltage signal and the magnetic particle concentration distribution, and finding the optimal sparse basis; introducing a compressed sensing reconstruction method, constraining the magnetic particle concentration distribution through sparse priors, transforming the concentration distribution reconstruction problem into an optimization problem with regularization terms; solving the magnetic particle concentration distribution under the condition of consistent voltage measurement data; and plotting the solution based on the results. This invention enables rapid reconstruction of magnetoacoustic electromagnetic particle concentration images based on compressed sensing.

This invention discloses a method, apparatus, and storage medium for determining the evaluation value of a tissue window in stroke, relating to the field of medical imaging technology, and primarily aimed at improving the evaluation accuracy of the tissue window in stroke. The method includes: based on the DWI and ADC sequences of the examined object, obtaining the first target evaluation region R in the DWI sequence. dwi Based on the FLAIR sequence of the object under inspection and the first target evaluation region R dwi Obtain the second target evaluation region R infarction The second objective evaluation region R infarction To compare with the first target evaluation region R dwi High-signal regions of overlapping FLAIR sequences; based on the first target evaluation region R dwi The corresponding first evaluation volume and second target evaluation region R infarction The corresponding second evaluation volume is used to calculate the stroke tissue window evaluation value of the examined subject.

This invention discloses a real-time image center reflection reduction method and system based on FPGA, belonging to the field of medical imaging technology. The method includes: after system initialization, controlling a galvanometer to scan and synchronously acquire images; the FPGA detecting abnormal brightness areas in real time and extracting spot parameters; establishing and storing the mapping relationship between the galvanometer scanning angle and image pixel coordinates; generating control quantities for adjusting the imaging link gain based on the spot parameters, including at least one of laser power, ADC pre-stage gain and bias, and detector drive voltage; applying the control quantities to suppress reflection when scanning to the corresponding angle according to the mapping relationship; and uploading the processed image to a host computer for quality judgment and iterative optimization. The system includes a laser, galvanometer, detector, ADC, FPGA, DAC / digital bus, and host computer, forming a dual-link closed loop of forward imaging and reverse control. This invention utilizes the parallel processing capability of FPGA to achieve real-time, adaptive reflection suppression, effectively improving the quality of ophthalmic imaging.

This invention discloses a gold nanoparticle enhancer for magnetic resonance elastography, its preparation method, and its application, belonging to the field of medical imaging technology. The preparation method includes dissolving trisodium citrate in deionized water to obtain solution A, then adding chloroauric acid solution to generate solution B. When the temperature of solution B drops to 90°C, an equal amount of chloroauric acid solution is added to form solution C and stirred. An equal amount of chloroauric acid solution is added again and stirred to form solution D. After the reaction is complete, ultrafiltration, centrifugation, and washing are performed to obtain the gold nanoparticle enhancer. This invention achieves the controllable synthesis of the gold nanoparticle enhancer. The preparation method is simple, easy to operate, and has good reproducibility. The obtained gold nanoparticle enhancer has uniform particle size, good dispersibility, and excellent stability, making it easy to scale up production. More importantly, the gold nanoparticle enhancer prepared by this invention has excellent low toxicity and good biocompatibility.

This application provides a method and apparatus for region of interest (ROI) assessment, relating to the field of medical imaging technology. The method includes: acquiring chest images of a user at different times; performing the following for each chest image: extracting a lung region from the chest image, identifying anatomical landmarks in the lung region, determining the relative positions of different layers in the chest image based on the anatomical landmarks; determining the mapping relationship between different layers in different chest images based on the relative positions of the layers in each chest image; identifying a region of interest (ROI) within the lung region of each chest image; and generating a ROI assessment result based on the layer in which the ROI is located in the chest image and the mapping relationship between different layers in different chest images. This application can improve the accuracy of the assessment results.

The present application relates to the field of medical imaging technology, and particularly relates to a method for detecting retinal lesion hard exudate clusters under OCT imaging, which comprises the following steps: generating an Enface front projection image by establishing a three-dimensional coordinate system, and performing polar coordinate grid division to establish a mapping relationship between three-dimensional coordinate voxels and polar coordinate grids; on the Enface front projection image, extracting a suspected hard exudate grid according to the highlight aggregation feature; backtracking the vertical columnar region of the suspected hard exudate grid, taking the front highlight reflection focus and the rear acoustic shadow attenuation of the hard exudate in the Bscan section sequence as specific criteria to obtain real hard exudate clusters; quantifying each index of the real hard exudate clusters, and outputting a detection report of the real hard exudate clusters; the present application can quickly and accurately lock the real hard exudate clusters, and further provide a quantitative basis for long-term dynamic monitoring of fundus diseases.

This invention relates to the field of medical imaging technology, specifically to a method for identifying coronary artery inflammatory plaques based on multi-sequence CTA images. The invention obtains registered three-phase images by performing feature point matching and local thickness gradient correction on three-phase CTA images of the coronary arteries, and labels candidate plaques corresponding to these three phases. Based on the registered three-phase images, the change in CT values ​​within the candidate plaques over time is analyzed to obtain the contrast agent retention index, screening for suspected inflammatory plaques. For suspected inflammatory plaques, the enhancement amplitude and attenuation gradient of CT values ​​in the surrounding adipose tissue region are analyzed based on the arterial phase image and the registered delayed phase image to obtain the pericoronary fat inflammation index, confirming the inflammatory plaque. This invention achieves dual quantitative verification of inflammatory plaques from microvascular leakage within the plaque to the spread of inflammation to the surrounding adipose tissue, significantly improving the accuracy of inflammatory plaque identification and enabling early, non-invasive warning of coronary artery inflammation.

This invention discloses a domain-driven medical image quality control architecture, relating to the field of medical imaging technology. Key technical points include: extracting the quality control feature parameters of the medical image to be controlled; comparing the quality control feature parameters with standard quality control feature intervals to obtain target quality control features; performing attribute classification and correlation judgment processing on the target quality control features to generate a quality control feature set; obtaining the feature association parameters of the target quality control features to which the quality control feature set belongs, as well as the target quality control feature parameters; performing verification processing and analysis on the feature association parameters to obtain target quality control representation features; analyzing the target quality control feature parameters to obtain target quality control coefficients; obtaining quality control priority coefficients based on the target quality control coefficients; and outputting multi-dimensional medical image quality control processing instructions for the medical image to be controlled based on the quality control feature order and the target quality control representation features. The effect is to improve the quality stability of medical images.

This application relates to a time management method and computer device for SPECT scans, belonging to the field of medical imaging technology, and can improve scanning efficiency. The method includes: acquiring the resting time and scanning protocol of at least one object to be scanned; determining the expected resting time of at least one object to be scanned based on the scanning protocol; determining the actual remaining waiting time of at least one object to be scanned according to the current scanning status; planning the scan time of the object to be scanned based on the resting time, the expected resting time, and the actual remaining waiting time; and generating a time management list in a user management interface.

The application discloses a thyroid nodule detection method based on dynamic blur adaptive fusion, relates to the technical field of medical images, and takes into account the problems of real-time performance and image quality blur; the method does not suppress noise by regarding blurred images as noise interference, but learns and understands the blur structure, and the process is realized by outputting clear features and blur features through a double-branch perception network; a clear-blur switching unit is designed according to the change of the scanning speed and the average Laplacian variance of the image, the strategy can be adaptively adjusted according to the blur degree of the input image, and the clear features and the blur features are dynamically mixed. Moreover, the application is a plug-and-play component, and can be organically embedded in mainstream target detection frameworks, such as the YoLO series and the DETR series.

This invention discloses a compound, a chelate, a method for preparing the same, and its application in the preparation of magnetic resonance imaging contrast agents, belonging to the field of medical imaging technology. Specifically, this invention discloses a compound as shown in formula (I) or its stereoisomers, pharmaceutically acceptable salts, or mixtures thereof, which can significantly increase plasma exposure, has high bioavailability, and can prolong the in vivo imaging time window, possessing the advantages of long-acting, low-dose imaging; it also has good clearance properties and a low risk of tissue residue, thereby reducing free Gd. 3+ This approach aims to eliminate potential risks and provide a long-lasting, low-dose, and highly safe magnetic resonance imaging (MRI) contrast solution for clinical use.

This application discloses a medical image multimodal computing method and system based on cross-modal generation, applicable to the field of medical imaging technology. The method includes: acquiring brain image data and preprocessing the brain image data; training a dual-path Siamese neural network based on the preprocessed brain image data; wherein the dual-path Siamese neural network includes a cross-modal generation network and a brain image diagnosis network; inputting the first intermediate layer feature map of the acquired cross-modal generation network and the second intermediate layer feature map of the brain image diagnosis network into a cross-modal feature fusion module for feature fusion to obtain a diagnostic result; acquiring brain image data of a target user, inputting the target user's brain image data into the trained dual-path Siamese neural network and the cross-modal feature fusion module, and outputting an evaluation result.

This invention belongs to the field of nuclear medicine imaging technology, specifically relating to a PET myocardial blood flow quantitative optimization method, including the following steps: determining the shortest effective acquisition time: for specific types of research subjects and pathophysiological states, the injection time is determined through experimental analysis. 18 After F-Flurpiridaz, the shortest effective acquisition time required to achieve stable myocardial blood flow (MBF) quantification is achieved; an optimized acquisition protocol is implemented; image reconstruction and MBF quantification are performed based on the optimized acquisition time; results are verified and reported. This invention significantly improves scanning and quantification efficiency: by shortening the effective acquisition time by 2-7 minutes, the occupancy time of the PET scanner can be substantially reduced while ensuring data quality, increasing equipment turnover and enabling more subjects to be examined within the same time period.

This invention discloses a PET scattering correction and image reconstruction method based on time-of-flight (TOF) and GPU, belonging to the field of medical imaging technology. This invention uses a TOF histogram image as the initial radiation source distribution for scattering estimation for scattering correction. The computational overhead of the TOF histogram image is extremely low, and the initial scattering estimation can be executed in parallel with the sensitivity image calculation process, thereby effectively improving the computational efficiency of the overall reconstruction process. This invention has strong flexibility; it can be modularly integrated into EM-type reconstruction algorithms without requiring significant modifications to existing reconstruction frameworks, facilitating implementation. An atomically driven multi-GPU parallel MC computing framework solves the load balancing problem in multi-GPU computing, fully leveraging the performance advantages of multi-GPU computing resources. While meeting clinical needs in terms of computational efficiency, it can accurately estimate the scattering distribution, including multiple scattering coincidence events. The method of this invention is simple and easy to understand. This invention is applied to PET scattering correction and image reconstruction.

This invention discloses a portable image acquisition geometric adaptive correction method, belonging to the field of medical imaging technology. The method involves installing a first IMU at the X-ray tube end and a second IMU and an array of curvature sensors at the flexible imaging plate end to acquire relative attitude and flexible imaging plate deformation data in real time. When an angular deviation is detected between the X-ray tube axis and the equivalent principal normal of the imaging plate, a multi-degree-of-freedom robotic arm is driven to perform motion compensation. Simultaneously, a three-dimensional curved surface model of the flexible imaging plate is constructed based on the deformation data, and the original X-ray image is mapped back from the curved surface coordinate system to the standard planar coordinate system, outputting the corrected image. This invention achieves adaptive correction in non-standard environments, significantly reducing reliance on technician experience.

This application provides an automated liver segmentation modeling method and system based on a hybrid neural network, relating to the field of medical imaging technology. The method includes: preprocessing acquired raw liver images to obtain a three-dimensional liver image; wherein the three-dimensional liver image includes liver parenchyma, portal vein, and hepatic vein; inputting the three-dimensional liver image into a trained segmentation model to obtain liver parenchyma masks, portal vein masks, and hepatic vein masks; dividing the liver parenchyma into multiple watershed partitions based on the liver parenchyma masks, portal vein masks, and hepatic vein masks; determining the standard liver segment corresponding to each watershed partition based on preset liver segmentation rules; and elastically deforming the watershed partitions based on the standard liver segments corresponding to the watershed partitions to obtain deformed watershed partitions. This application can reflect the individualized vascular variation characteristics of patients.