67 results about "Vascular network" patented technology

The invention discloses an artificial intelligence-based periodontal state evaluation method, which comprises the following steps of: acquiring multi-modal tooth data which comprises a tooth surface image and a local blood vessel network image of an oral cavity; preprocessing the multi-modal tooth data, and performing cross-modal registration by using a registration module to obtain a registered tooth surface image and a registered blood vessel network image; extracting multi-dimensional features of the registered blood vessel network image through a first feature extraction module, wherein the multi-dimensional features comprise spatial morphological features, topological connectivity features and hemodynamic features of blood vessels; extracting macroscopic morphological features and lesion local features of the registered tooth surface image through a second feature extraction module; performing cross-modal fusion on the multi-dimensional features, the macroscopic morphological features, the local lesion features and the clinical data to obtain fusion features; and outputting a periodontal state evaluation result based on the fusion features, thereby facilitating improvement of periodontal state evaluation accuracy and periodontal disease early warning capability.

A lung CT blood vessel image segmentation and reconstruction system based on multiple interpretable features performs further fine-grained segmentation on the basis of main airway features through a feature extraction module to obtain a plurality of connected domains, performs multi-stage feature extraction on the connected domains, and outputs multi-scale feature information; the blood vessel segmentation module generates an information matrix according to the indexes and the pulmonary parenchyma mask, generates a blood vessel network segmentation result through an adversarial network and performs post-processing; and the model reconstruction module performs three-dimensional reconstruction on the blood vessel network segmentation result and the pulmonary parenchyma mask to obtain a 3D model. According to the method, on the basis of anatomical priori knowledge of pulmonary vessels and airways, a large amount of multi-scale feature information is utilized, the information loss of the two-stage segmentation network is reduced, and the network adaptability and the learning ability of the relation between pixels under the complex condition are improved. In the aspect of system design, a modular design and management mode is adopted, efficient resource access is achieved, and meanwhile the operability and usability of the system are improved through end-to-end process design.

An integrated modular microphysiological system is provided which includes a two or more chambers and a vascular network which includes at least one channel. The chamber can be configured for culturing a tissue and includes a layer of endothelial cells which forms an endothelial barrier within the well. The endothelial barrier can be in fluid contact with at least one of the at least one channels in the vascular network. The endothelial barrier can also be in fluid contact with a fluid in the chamber.

The invention provides a dynamic bionic robot skin, a control method thereof and a robot. The dynamic bionic robot skin is characterized in that a bionic blood vessel network channel is arranged in a dynamic bionic layer; the bionic blood vessel network channel is used for simulating dynamic changes of blood vessels; the bionic blood vessel network channel is an elastic cavity embedded into the dynamic bionic layer; the dynamic blood vessel regulation module is communicated with the bionic blood vessel network through a pipeline, and the dynamic blood vessel regulation module is used for changing the filling degree and / or form of the bionic blood vessel network channel by pumping a fluid medium into and out of the blood vessel network channel or adjusting the internal pressure; the light-transmitting bionic epidermal layer covers the outer surface of the dynamic bionic layer and is fixedly connected with the dynamic bionic layer, and bionic skin textures are arranged on the outer surface of the light-transmitting bionic epidermal layer. The invention further discloses a robot and a skin control method. The method is high in simulation degree, and physiological phenomena such as blood vessel filling contraction and artery rhythm can be achieved.

The invention discloses a culture medium for adipose-derived stem cells, and particularly relates to the technical field of stem cell culture. The culture medium comprises a basic culture medium and nerve-vascular niche components, wherein the basic culture medium comprises DMEM / F12, 10% of human-derived platelet lysate and 1% of antibiotic solution; the nerve-vascular niche comprises the following components: a Slit3 recombinant protein, a nerve growth factor-beta, a glial cell-derived neurotrophic factor, a lysyl oxidase inhibitor, dexamethasone, 3-isobutyl-1-methylxanthine and insulin. The traditional fetal calf serum is replaced by the human-derived platelet lysate, so that the risks of immunological rejection and pathogen pollution are avoided; through the synergistic effect of nerve-vessel niche factors, blood vessel maturation and innervation are promoted, programmed mechanical stretching culture is combined, the adipogenic differentiation efficiency of adipose-derived stem cells is remarkably improved, and engineered adipose tissue which is huge in lipid droplet, compact in structure and provided with a nerve-vessel network is formed.

The invention relates to the field of biomedical ultrasonic imaging, and discloses a pulse wave detection method and system based on ultrafast Doppler imaging, and the method comprises the steps: firstly obtaining a dynamic power Doppler image of the blood flow of a biological tissue; performing spectral analysis on the Doppler signal of each pixel point in the image to obtain a function that the frequency spectrum changes along with time; and on the basis, calculating a blood flow speed time sequence, an impedance index and a pulsation index of each pixel point, and finally obtaining an impedance index distribution diagram and a pulsation index distribution diagram of the whole blood vessel network. According to the method, ultrafast imaging and spectral analysis technologies are ingeniously combined, the structure and the function of the vascular network can be comprehensively evaluated, a new technical means is provided for hemodynamic research and disease diagnosis of organs such as spinal cords, hearts and brains, and the method has a wide application prospect.

The application provides an animal eyeball fixation recognition system and method, and relates to the technical field of ophthalmic detection and treatment equipment.The method comprises the following steps: acquiring a time interval of continuous imaging of an animal eyeball; controlling at least two light sources of different wavelengths to alternately irradiate the eyeball in the interval of continuous imaging of the animal eyeball, and collecting a multispectral image sequence comprising a scleral vascular network; extracting at least one set feature point of the scleral blood vessels from the multispectral image sequence, and establishing a feature set; acquiring feature point position information, and obtaining micro-motion vector information of the eyeball; and compensating the acquired continuous frame images according to the micro-motion vector information of the eyeball.The animal eyeball fixation recognition method provided in the application embodiment can reduce the constraint performance of a traditional rigid fixation device, and in turn reduce physical damage that may be caused to the animal eyeball.On the other hand, for high-frequency or periodic physiological micro-motions such as heartbeat and respiration, more accurate and real-time compensation can be achieved.

The present invention relates to systems, compositions and methods for multicellular bioprinting vascularized tissue constructs comprising a hierarchical vascular network. The methods employ a dual bio-ink strategy involving fibrous microgel matrix bio-inks with adjustable hardness, self-healing rheology, and microporosity to support capillary self-assembly, and sacrificial bio-inks that define a large pourable channel after removal. The system integrates top-down printing and bottom-up cell self-organization within a programmable bio-printing platform. The key aspect of the invention is to engineer the physical topography of the matrix to actively guide vascular morphogenesis beyond conventional permissive stents. The integrated platform enables the manufacture of complex bionic vascular networks with enhanced mass delivery, cellular viability, and in vivo integration potential. The invention represents an important progress in the aspect of extendable production of functional human tissues, and has application in regenerative medicine, disease modeling and drug discovery.

The invention relates to the technical field of medical image processing, in particular to a digital ophthalmology virtual intelligent doctor system based on artificial intelligence, and the system comprises an image obtaining module which is used for obtaining and preprocessing a fundus image to form a standardized image; the blood vessel segmentation module is used for extracting a blood vessel network, constructing a blood vessel topological map and recording blood vessel branch and path information; the micro-hemorrhage candidate generation module is used for screening red spots and performing path matching in combination with vascular topology to form candidate spots; the staged reasoning module is used for roughly scanning and finely classifying the candidate spots to generate micro bleeding points; the historical image management module is used for comparing the candidate points with historical images of the patient, marking new or changing spots and forming priority information; and the output and feedback module is used for generating a detection result according to the candidate micro bleeding points and the priority information. Automatic identification and sorting of the micro bleeding points are realized, and the screening efficiency and reliability are improved.

The application belongs to the field of intelligent medical treatment, and particularly relates to a method for constructing a refractory mycoplasma pneumoniae pneumonia prediction model and equipment. The method comprises the following steps: acquiring a baseline time data set and a follow-up time label of a mycoplasma pneumoniae patient; inputting the image data set into a lung blood vessel segmentation model to obtain a lung blood vessel network, obtaining a total lung blood vessel volume based on the lung blood vessel network, and obtaining a blood vessel volume of different cross-sectional areas based on a cross-sectional area of the lung blood vessel network; inputting a ratio of the blood vessel volume of different cross-sectional areas to the total lung blood vessel volume into a machine learning model to obtain a prediction label, and obtaining a refractory mycoplasma pneumoniae pneumonia prediction model after iterative optimization of the machine learning model based on a difference between the prediction label and the follow-up time label. The application segments a lung CT image to obtain a blood vessel network diagram, quantitatively obtains a percentage of a blood vessel volume of different thicknesses in a total lung blood vessel volume, and constructs a refractory mycoplasma pneumoniae pneumonia prediction model based on an innovative feature extraction method.

The present teaching provides device and method of use thereof, for example, for the placement of a medical implant inside the cerebrovasculature. Various embodiments of the present teachings include a medical implant, a delivery system, and an Optical Coherence Tomography (OCT) imaging system. The OCT imaging system is used to reveal the three dimensional (3D) volumetric structure of the vascular network, as well as vessel density and geometric features, blood flow velocity, flow rate, and other data useful for selecting suitable medical implant as well as treatment location. This OCT imaging system is also used to guide the medical implant deployment and post implantation assessment.

This invention relates to the field of organoid culture technology, specifically to a vascularized tumor organoid chip. It redesigns the traditional micropillar-separated culture medium and cell culture channels into a dynamically separated structure using acupuncture needles. This avoids the physical limitations of traditional micropillars on blood vessel growth, significantly increases the contact area between vascular cells, and promotes the growth of the vascular network. Simultaneously, the needle insertion channel and reservoir allow for free switching between micro-infusion pump and gravitational potential energy delivery modes. Furthermore, it enables dynamic detection during the co-culture of blood vessels and tumor organoids.

The invention relates to the technical field of medical image processing, in particular to a cross-modal fusion positioning method and system for accurate navigation of a coronary guide wire, and the method comprises the steps: firstly, obtaining a coronary X-ray angiography image and guide wire head end electromagnetic positioning data, constructing a vascular topological space expression, and carrying out the fusion positioning of the coronary X-ray angiography image and the guide wire head end electromagnetic positioning data; mapping the vascular network from the Euclidean space to a non-Euclidean topological space; secondly, processing a blood vessel connected graph and guide wire position data through two-channel feature extraction, and extracting features by adopting a topological sensitive convolution kernel; fusing vascular topological features and guide wire position features based on a manifold constraint cross attention mechanism to realize bidirectional information flow; further executing self-calibration state estimation, establishing a probability distribution model to quantify uncertainty, and realizing multi-source data fusion; according to the method, deep fusion of X-ray angiography and electromagnetic positioning data is achieved, and compared with a traditional method, the navigation precision is improved by about 40%.

Computational methods are used to create cardiovascular simulations having desired hemodynamic features. Cardiovascular modeling methods produce descriptions of blood flow and pressure in the heart and vascular networks. Numerical methods optimize and solve nonlinear equations to find parameter values that result in desired hemodynamic characteristics including related flow and pressure at various locations in the cardiovascular system, movements of soft tissues, and changes for different physiological states. The modeling methods employ simplified models to approximate the behavior of more complex models with the goal of to reducing computational expense. The user describes the desired features of the final cardiovascular simulation and provides minimal input, and the system automates the search for the final patient-specific cardiovascular model.

This application provides a medical image processing method and system. The method includes: acquiring vascular image volume data from photon-counting computed tomography scans of a target region; based on the vascular image volume data, performing skeletonization processing on the vascular network, extracting multiple skeleton points in the vascular network, and forming a vascular centerline network according to the connection relationships between the skeleton points; identifying endpoints and bifurcation points from the vascular centerline network, thereby dividing the vascular centerline network into several continuous and unbifuzzy vascular segments, and constructing a vascular centerline diagram structure based on each vascular segment; establishing and solving a blood flow analysis model based on the vascular centerline diagram structure to obtain the blood flow analysis results of the vascular network; wherein, the blood flow analysis results include the blood flow rate and / or pressure difference between the two ends of each vascular segment. This application improves the accuracy of the blood flow analysis results.

The invention discloses a method for preparing a vascular organ chip from human umbilical artery stem cells, and belongs to the field of biomedical engineering and tissue engineering. The method comprises the following steps: separating and culturing human umbilical artery stem cells to the third generation; preparing a PDMS micro-fluidic chip containing a liquid inlet channel, a liquid outlet channel, a growth channel and a central culture chamber; a blood vessel precursor aggregate is obtained through cell digestion, aggregate construction, mesoderm induction and blood vessel pedigree induction, the blood vessel precursor aggregate is inoculated into a Coll-1-Matrigel gel modified chip through a two-step method, and dynamic perfusion culture is conducted in combination with a culture medium containing VEGF-A and FGF-2. And finally, the structure and the function of the vascular organ are verified through immunofluorescent staining and fluorescent microbead perfusion. The problems that in the prior art, cell sources are limited, culture conditions are single and the like are solved, the high angiogenesis potential of the human umbilical artery stem cells and a dynamic culture system are utilized to construct a high-bionic-degree vascular network, and the method can be applied to drug screening, vascular pathological model construction and regenerative medicine research.

The invention discloses a bionic gastric mucosa micro-barrier structure, comprising: a bottom microfluidic channel for simulating a submucosal vascular network; the middle gastric epithelial cell layer is used for simulating a mucous membrane epithelial barrier and comprises a matrix layer, quaternary functional cells, a culture medium and a pH buffer module; and the surface dynamic mucus layer is used for simulating a mucous membrane protective barrier and comprises a vagus neurotransmitter simulant, exogenous mucus and a pressure sensor. According to the invention, continuous nutrition supply is provided for the middle gastric epithelial cell layer through the bottom microfluidic channel, the survival and functions of cells are maintained, and accurate tracking of the transgastric mucosa transport process is realized. A function collaborative network is formed through quaternary cells, the secretion volume and the injury state are monitored in real time, regulatory factors are dynamically adjusted, and it is ensured that a cell layer can still maintain the barrier function stable under external interference. When foreign matter impact or food friction signals are recognized through the pressure sensor, the pump speed is instantly increased, and local mucus loss is rapidly supplemented.

The application discloses a method for training a blood vessel segmentation model and related products, which comprises the following steps: obtaining a three-dimensional angiogram image for training, the three-dimensional angiogram image containing a blood vessel network composed of a plurality of vessel segments; giving each vessel segment a unique segment identifier to obtain a first segmentation mask of the three-dimensional angiogram image composed of segmentation masks of each vessel segment; determining the geometric features and semantic features of each vessel segment based on the segmentation mask of each vessel segment; constructing a first capsule vector and a first graph structure of all vessel segments based on the geometric features and semantic features of each vessel segment; and inputting the three-dimensional angiogram image, the first segmentation mask, the first capsule vector and the first graph structure as training data into the blood vessel segmentation model to train the same. The scheme of the application can realize high-reliability blood vessel segmentation recognition and provide strong support for accurate diagnosis of blood vessel diseases.

The present invention introduces an approach to neural tissue engineering by developing vascularized neurospheres (VNSs) through novel methods, systems, and kits. These VNSs are generated using a unique blend of neural, vascular, and supportive cells, cultured in specialized hydrogel-containing media. The VNSs feature an integrated vascular network, serving as a physiologically relevant in vitro model. The invention also offers a grafting technique for therapeutic applications in neural disorders and injuries, as well as facilitating brain-computer interfacing. Beyond therapeutics, the VNSs have broad applications in drug development, synthetic biology, disease modeling, and more. The invention also includes kits for VNS generation and methods for interfacing VNSs with probes for applications of brain-computer interfacing. Overall, this patent represents a significant leap in the field, bridging the gap between in vitro and in vivo systems and opening new avenues in research, therapeutics, and bioengineering.

The invention relates to the technical field of image recognition and detection, in particular to an rPPG image recognition and detection method based on topological features of a blood vessel network. On this basis, non-rigid motion correction based on a vascular topological structure, remote photoplethysmography signal weighted fusion combining topological importance and a time sequence quality index, and acquisition quality confidence evaluation and closed-loop control taking vascular network topological integrity, global time sequence signal periodicity and a signal-to-noise ratio as cores are introduced; then the blood vessel structure features and the dynamic pulse features are used for analyzing vital signs and hemodynamic states together, so that the signal extraction process more closely corresponds to a real blood flow path, and the robustness under the conditions of head raising, speaking, expression change and illumination fluctuation is improved; and the risk of outputting a misjudgment result under the condition that the vascular structure is invisible or the signal quality is poor is reduced.

The application discloses a periodontal state evaluation method based on artificial intelligence, which comprises the following steps: collecting multi-modal tooth data, wherein the multi-modal tooth data comprises tooth surface images and blood vessel network images of a local oral cavity; preprocessing the multi-modal tooth data, and performing cross-modal registration by using a registration module to obtain the registered tooth surface images and blood vessel network images; extracting multi-dimensional features of the registered blood vessel network images by using a first feature extraction module, wherein the multi-dimensional features comprise spatial morphological features, topological connectivity features and hemodynamic features of the blood vessels; extracting macroscopic morphological features and local lesion features of the registered tooth surface images by using a second feature extraction module; performing cross-modal fusion on the multi-dimensional features, the macroscopic morphological features, the local lesion features and clinical data to obtain fusion features; and outputting a periodontal state evaluation result based on the fusion features, which is beneficial to improving the accuracy of periodontal state evaluation and the early warning capability of periodontal diseases.

The invention discloses a vascular endothelial cell as well as a preparation method and application thereof. The preparation method comprises the following steps: inoculating induced pluripotent stem cells into a culture medium containing an ROCK signal channel inhibitor for culturing, and inducing the cultured induced pluripotent stem cells by using a culture medium containing a Wnt signal channel activator and a BMP signal channel activator, so that the induced pluripotent stem cells are differentiated into mesoderm cells; inducing the mesoderm cells by using a culture medium containing a vascular endothelial growth factor and a cAMP signaling pathway agonist, so that the mesoderm cells are differentiated into endothelial coarse cells; and performing positive sorting of the endothelial cell marker CD144 on the endothelial coarse cells to obtain purified vascular endothelial cells. The induction path of the method is clear and efficient, the period is short, the vascular endothelial cell population with high purity, complete vascular barrier function and mature phenotype can be obtained, and the cell population can be applied to construction of a vascular network in a gel matrix.

The invention discloses a lung tissue organoid culture method. The method comprises the following steps: firstly, carrying out three-dimensional differentiation culture on matrigel by utilizing lung basal cells in vitro to construct an organoid with alveolar epithelium characteristics; then, the organ is transplanted into the spleen of a recipient animal subjected to ectopic surgery (shifted to subcutaneous tissues). The rich blood vessel network and the unique microenvironment of the spleen greatly promote rapid vascularization, structural remodeling and functional maturation of organoids, and lung tissue highly simulating natural alveolus is formed. The invention overcomes the defects of insufficient vascularization and immature function of the existing organ-like model, provides an excellent in-vivo platform for researching lung development and disease mechanisms and carrying out drug screening and toxicological evaluation, and has important application value in the field of regenerative medicine.

Disclosed herein are apparatuses comprising one or more channels defining a luminal space, wherein the luminal space is defined by an inner wall of fibrous basement membrane material, as well as methods of their manufacture and use.

The invention relates to the technical field of human induced pluripotent stem cells, and discloses a method and a system for constructing vascular organs based on human induced pluripotent stem cells, and the method comprises the following steps: inducing human induced pluripotent stem cells to aggregate into cell aggregates, and identifying aggregate characteristics of the cell aggregates; determining mesoderm induction molecules of the cell aggregate to construct a mesoderm induction environment of the cell aggregate, and performing induced differentiation on the human induced pluripotent stem cells in the cell aggregate; detecting the expression level of the mesoderm marker gene in the mesoderm cells, constructing a vascular induction culture medium of the mesoderm cells, and inducing the mesoderm cells to differentiate into vascular lineage cells; constructing a three-dimensional extracellular matrix of the vascular lineage cells to differentiate the vascular lineage cells into a vascular network; and calculating the permeability and branch density of the vascular network to determine the fluid shear force and pulse frequency of the vascular network, and culturing the vascular network into a vascular organ. The construction stability and functionality of the vascular organoid can be improved.

This invention relates to the field of medical high-fidelity training model technology, and discloses a multi-vascular network biomimetic hemostasis model and method for junctional wounds. The model includes a biomimetic model, a blood bank system, a control system, and a temperature control unit. A biomimetic multi-vascular network is embedded in the junction area of ​​the biomimetic model, and a biomimetic wound opening is provided at the corresponding position of the biomimetic multi-vascular network. The input end of the biomimetic multi-vascular network is connected to the output end of the blood bank system, and the output end of the biomimetic multi-vascular network is located inside the biomimetic wound opening. The temperature control unit is located at the input end of the biomimetic multi-vascular network. A pressure sensor is provided in the biomimetic wound cavity wall of the biomimetic wound opening, and hemostatic material is filled inside the biomimetic wound opening, with the hemostatic material in contact with the pressure sensor. The control terminal of the control system is electrically connected to the blood bank system, the temperature control unit, and the pressure sensor. This invention can realistically simulate the bleeding process of penetrating and blind-tube injuries in the junctional wound of the simulation model, facilitating simulation training.

A microfluidic chip may comprise a plurality of separate microfluidic regions formed into a chip substrate. Each microfluidic region may be configured to simulate an organ and may comprise at least one inlet and at least one outlet with a microfluidic channel therebetween. Connecting microfluidic pathways may be provided between the separate microfluidic regions. The connecting microfluidic pathways may be configured to be vascularized. The connecting microfluidic pathways may comprise a surface treatment configured to receive endothelial cells. The surface treatment may comprise an extracellular matrix protein coating. Endothelial cells may be disposed within the connecting microfluidic pathways. The endothelial cells may comprise organ-specific endothelial cells that match an organ simulated by at least one of the separate microfluidic regions. The connecting microfluidic pathways may comprise synthetic microvascular networks having non-linear channels with physiologically relevant geometries. The physiologically relevant geometries may comprise bifurcations, varying cross-sectional areas, and convolutions.

The invention relates to the technical field of biomedical engineering, and discloses a diabetes wound repair stent with a bionic vascular network structure, comprising: a stent main body which is made of a biocompatible high polymer material and has a three-dimensional bionic vascular network structure built by a 3D printing technology inside, and the structure simulates hierarchical branching and connectivity of natural blood vessels; the bioactive factor loading unit comprises a vascular endothelial growth factor and mesenchymal stem cells, and the vascular endothelial growth factor is loaded in the stent through a microsphere encapsulation technology to form a space-time controllable release system; the surface functional modification layer is used for fixing vascularization promoting polypeptide on the surface of the stent main body through chemical grafting, and the polypeptide sequence comprises an arginine-glycine-aspartic acid structural domain. By means of the precisely-designed 3D printing bionic blood vessel network structure, grading branching and connectivity of natural blood vessels are effectively simulated, the blood vessel guiding efficiency is improved, and the blood vessel ingrowth speed is increased by two times or above.

The invention provides a medical endoscope image intelligent enhancement and focus recognition system, and relates to the technical field of data processing. The region segmentation module is used for detecting and distinguishing a suspected microvascular network region and a background region; the structure maintaining module is used for executing smoothing and color correction processing on the background area and executing texture maintaining processing on the suspected microvascular network area; the difference highlighting module is used for calculating the pixel difference between the suspected microvascular network region and the adjacent background region and executing local contrast enhancement in the region; the dynamic correction module is used for analyzing the brightness distribution relation between the suspected microvascular network area and the adjacent background area and executing self-adaptive brightness compression or lifting; the lesion recognition module is used for extracting complete blood vessel texture and a spatial distribution mode thereof, generating a lesion recognition result and outputting a suspicious lesion area; according to the invention, the accuracy of endoscope image focus identification is improved.