35 results about "Heterotaxy" patented technology

The invention belongs to the technical field of medical image processing, and particularly relates to an automatic positioning and typing method for cervical posterior longitudinal ligament ossification, which is characterized in that ossification focus spatial distribution characteristics of CT images and spinal cord morphological parameters of MRI images are synchronously analyzed based on CT and MRI images, a vertebral body-ossification-spinal cord spatial relationship is explicitly modeled through anatomical structure topological constraint, and a cervical vertebra-ossification-spinal cord spatial relationship is obtained. Diffuse calcification artifacts, heterogeneity signal interference and multi-modal data registration deviation are overcome, accurate positioning and typing diagnosis of the ossification are achieved, multi-dimensional feature fusion analysis is achieved, the limitation of traditional single iconography index diagnosis is broken through, space continuity and clinical parameters are integrated through a hybrid classifier, and the accuracy of diagnosis is improved. The accuracy and robustness of typing judgment are improved, a structured diagnosis report is automatically generated in the whole process, and the clinical decision-making efficiency and the standardization level are remarkably improved; the principle is scientific and reliable, and the ossification continuity index, the spinal canal invasion rate and the spinal cord compression grading parameters are automatically calculated according to the typing standard.

The invention relates to the technical field of medical image analysis, in particular to a left ventricular compliance assessment method and system based on medical image.The method comprises the following steps that a planar three-dimensional coordinate from a left ventricular apex to a mitral annulus is obtained through a CT image, a thin-plate spline interpolation algorithm is called to establish a left ventricular long-axis model, the ultrasonic end-stage internal diameter is obtained synchronously, and a left ventricular compliance assessment result is obtained. And inputting the left greenhouse long axis model and the ultrasonic diastole end-stage inner diameter into an Euclidean distance calculation function to generate a left greenhouse length-diameter ratio. According to the method, a left greenhouse long axis model is constructed by integrating CT three-dimensional coordinates and ultrasonic inner diameter, the length-diameter ratio is calculated by combining Euclidean distance, point cloud registration is carried out, a myocardial wall area is segmented, local deformation is quantized by utilizing Gaussian curvature gradient, a correction factor is generated by inputting a radial basis function network, and a parameter coupling mechanism is established by fusing an aorta root angle. And optimizing the weight of the pressure-volume equation, establishing a dynamic model, and realizing a quantitative evaluation system of spatial heterogeneity and time continuity.

The invention belongs to the technical field of medical image analysis, and relates to a lesion detection method and system based on multi-scan interactive deformable Mama, and the method comprises the steps: 1, image block embedding; 2, multi-scale feature extraction and interaction in the backbone network are scanned in parallel; 3, feature pyramid optimization based on dynamic weighted scanning fusion; 4, performing multi-scale fusion; according to the invention, through the adaptive scanning network and the deformable scanning mechanism, the characterization problem of the morphological heterogeneity of the oral cancer focus and the pulmonary nodule microstructure feature is effectively solved, the double breakthrough of the detection precision and the calculation efficiency is realized, and an efficient and reliable solution is provided for multi-cancer medical image analysis.

The invention discloses a construction method of a homogenized self-assembled heart organoid, and belongs to the field of organoid. The preparation scheme of the heart organoid provided by the invention is controllable in method and simple in procedure, emphasizes the transition of differentiation from an iPSC 2D level to a 3D self-assembly heart organoid, overcomes the heterogeneity, including size, structure, function and even gene difference, of cross-batch or even same-batch organoid caused by an existing differentiation method, and has good cross-batch reproducibility. The constructed heart organoid contains various cell types and can continuously beat for at least 180 days in vitro, and the heart organoid in the same batch is uniform in height and stable in function. The preparation scheme does not need an engineering scaffold, matrigel and the like, emphasizes self-assembly of heart organs, and better accords with physiological characteristics of a human body.

The invention relates to a device for distributing and receiving a population of pancreatic islets heterogeneous in size, the device comprising a matrix having a first face opposite a second face, characterized in that the matrix comprises concentric channels centered on a center O, the channels have an opening for receiving the pancreatic cells, the opening leading out onto the first face, the opening extending over the entire length (L) of the channel, the opening having a width (I) taken along the section Si, the device being configured such that the widths of the opening of two adjacent channels have an equal or increasing value moving away from the center O and such that the widths of the opening of a channel closest to the center O and of a channel furthest from the center O have an increasing value moving away from the center O. The invention relates to the field of implantable devices, in particular artificial pancreas devices.

The invention relates to the technical field of image processing, and further relates to a tumor characteristic spectrum construction method based on CTC enrichment and multi-omics analysis. The method comprises the following steps: 1, sequentially carrying out spiral inertial focusing and deterministic lateral displacement sorting on a whole blood sample to be detected, and finishing single-cell microcavity positioning capture of circulating tumor cells in a single-cell microcavity capture array region; 2, acquiring a time-varying curve of an oxygen molecule concentration value for each positioned and captured circulating tumor cell, and acquiring a metabolic function characteristic parameter group; 3, forming a multi-omics joint feature vector in combination with the metabolic function feature parameter group; and 4, constructing a circulating tumor cell subset based on the multi-omics combined feature vector, extracting symbolic molecular features, and integrating and outputting a tumor feature spectrum. According to the invention, more stable technical support can be provided for tumor heterogeneity analysis, metastasis potential evaluation and curative effect monitoring.

The invention belongs to the technical field of biomedical materials and tissue engineering, and particularly relates to a self-pumping stent material with a double-layer heterogeneous structure as well as a preparation method and application of the self-pumping stent material. A hydrophobic membrane is prepared by an electrostatic spinning technology, and a hydrophilic microgel assembly is prepared by an emulsion method. Adding a dopamine modified polymer, and establishing a dynamic phenylboronic acid ester bond between microgel through a dopamine group to form a hydrophilic microgel assembly; the adhesion connection of the microgel assembly and the hydrophobic membrane is realized through mussel bionic chemical reaction of dopamine groups, and a double-layer heterogeneous structure based on the hydrophilic assembly and the hydrophobic membrane is constructed, so that a self-pumping effect is generated, and one-way flow of liquid components from the hydrophobic side of the stent to the hydrophilic side of the stent can be realized. Implanting the stent into an alveolar bone defect wherein the hydrophobic membrane contacts gingiva and the hydrophilic microgel assembly fills the bone defect; through the self-pumping effect of the stent, nutritional ingredients in the gingiva are unidirectionally pumped to the defect part of the alveolar bone, so that the regeneration of the alveolar bone is promoted.

According to an aspect of the present invention, there is provided a method for imaging vasa vasorum density of a vessel in the body such as coronary and carotid arteries and the aorta and thereby assessing the risk of adverse health outcomes for a patient, comprising administering a contrast agent to the patient; performing a contrast-enhanced CT scan to measure Hounsfield distribution and heterogeneity related to vasa vasorum density in and around the vessel wall of a patient; analyzing the data to determine a metric related to the density of the vasa vasorum; and recommending a diagnostic and / or therapeutic next step to the patient to prevent adverse health outcomes based at least in part on the metric related to the vasa vasorum density.

The invention relates to the technical field of intra-operative navigation, in particular to an intra-operative brain glioma deep learning detection method and system based on hyperspectral imaging, and the method comprises the steps: analyzing the internal heterogeneity of brain glioma based on spectral difference, and evaluating the coverage earnings of a pre-operative planning path and an intra-operative detour path; analyzing oxyhemoglobin saturation distribution based on absorption peak characteristics of hemoglobin in a specific wave band, and evaluating the ischemia risk of a pre-operation planning path and an intra-operation bypassing path; respectively mapping the pre-operation planning path and the intra-operation bypassing path to a brain functional region topology network, and evaluating a functional injury risk corresponding to the paths based on a topology connection relation and a local ischemia risk; and carrying out expected income and risk trend analysis on the pre-operation planning path and the intra-operation bypassing path, and generating an operation path decision suggestion. According to the method, the accuracy and the safety of operation path decision making are effectively improved by quantifying the path coverage income and the function damage risk of the operation path.

The invention relates to the technical field of medical image segmentation, in particular to a thoracic surgery esophageal cancer tissue digital pathological image segmentation method and system. According to the method, a region of interest in a sample image is segmented by using an initial U-Net model, the wettability is quantified according to the dispersion of a cell direction in an expansion region of the region of interest, and an abnormal expansion region is identified. And obtaining a comprehensive infiltration resistance coefficient based on the fiber trend and cell density of the local tissue on the migration trunk path. And dividing the abnormal expansion region into a plurality of window regions, quantizing a cascade constraint fusion coefficient, and further dynamically regulating and controlling segmentation edge retention parameters of a U-Net model decoder. According to the method, case histological characteristics and microenvironment dynamics constraints are fused into the segmentation process of the U-Net model, and the method has relatively high segmentation precision for transition regions with high morphological heterogeneity and wettability growth.

The invention discloses a tumor molecular typing method based on EMT heterogeneity and application of the tumor molecular typing method in cancer evolution visualization. According to the invention, molecular typing is carried out on para-carcinoma tissues and corresponding cancer tissues according to EMT characteristics, the para-carcinoma tissues and the corresponding cancer tissues are divided into three EHBMT subtypes of epithelium type, mesenchymal type and intermediate type, then changes of the para-carcinoma tissues and the corresponding cancer tissue subtypes from the same donor are analyzed, and visualization of tumor evolution is realized. According to the method, tumor evolution can be visualized from the perspective of EMT characteristics, personalized precise medical treatment of the patient is guided, and the method has important significance in improving prognosis of the patient.

The invention discloses a multi-omics malignant pleural effusion immunometabolism reprogramming spatio-temporal heterogeneity analysis device, which comprises an integration analysis module used for carrying out multi-modal integration and consensus clustering analysis on a multi-omics data set to obtain an integration analysis result, dividing the malignant pleural effusion training samples of the malignant pleural effusion patient into an immunometabolism activation type subtype, an immunometabolism transition type subtype and an immunometabolism inhibition type subtype according to the confluence analysis result; the screening construction module is used for screening immune metabolism markers from the characteristics of the immune metabolism inhibition type subtypes, forming a candidate target point set according to the immune metabolism markers, and constructing a prediction model; and the evaluation suggestion module is used for calculating treatment response scores and combining the treatment response scores with the clinical staging information to construct a column diagram, and a prognosis risk evaluation result and personalized treatment guidance suggestions are obtained, so that the accuracy of prognosis evaluation and the reliability of treatment response prediction can be improved, and accurate risk stratification and personalized treatment guidance for patients can be realized.

The invention discloses a liver cancer iconography diagnosis method based on artificial intelligence, which integrates anatomical structure characteristics of CT enhanced scanning, soft tissue heterogeneity characteristics of MRI diffusion weighted imaging and dynamic blood flow characteristics of ultrasound contrast, and covers three dimensions of morphology, histology and hemodynamics of a focus. The one-sidedness defect of single-mode information is overcome, multi-mode data complementation is achieved, the misdiagnosis and missed diagnosis risks caused by feature missing are effectively reduced, and the diagnosis accuracy is improved. The cross-modal attention module calculates the cosine similarity between each modal and the global reference feature and dynamically distributes the weight, thereby avoiding the limitation of the fixed weight, enabling different modal features to make accurate contributions according to the actual expression of the focus, strengthening the characterization capability of the combined feature for the liver cancer focus, and improving the accuracy of the liver cancer focus. And the recognition precision of the model on difficult focuses such as fuzzy boundaries and complex blood supply is improved.

The invention relates to the field of medical technical equipment, in particular to a puncture needle for muscular tissue biopsy, and aims to solve the problem that an existing device cannot meet the requirements of transverse and longitudinal puncture paths at the same time, the puncture needle comprises a needle shell, and further comprises a longitudinal sampling mechanism and a transverse sampling mechanism; the longitudinal sampling mechanism is slidably arranged at one end of the needle shell and used for obtaining tissue samples in the needle entering direction. The transverse sampling mechanism is movably arranged in the radial direction of the needle shell, and one end of the transverse sampling mechanism penetrates through the needle shell and is used for obtaining tissue samples in the direction perpendicular to the needle entering direction. Longitudinal sampling and transverse sampling can be achieved at the same time in the one-time puncture process of a diseased region, multi-point sampling is needed in some diseased regions due to heterogeneity, complex conditions of the diseased regions can be reflected more comprehensively, meanwhile, the puncture frequency is reduced, and discomfort of a patient is reduced. The transverse sampling enables the detection of the sample to be more comprehensive and three-dimensional, and the accuracy and reliability of tissue biopsy are further improved.

The present invention relates to the field of medical image segmentation technology, and in particular to a method and system for segmenting digital pathological images of esophageal cancer tissue in thoracic surgery. The method uses an initial U-Net model to segment a region of interest in a sample image, quantifies the degree of infiltration based on the discrete amount of the cell direction in the extended area of ​​the region of interest, and identifies the abnormal extended area. Based on the local tissue fiber orientation and cell density on the main migration path, a comprehensive infiltration resistance coefficient is obtained. The abnormal extended area is divided into multiple window areas, and the cascade constraint fusion coefficient is quantified, thereby dynamically regulating the segmentation edge retention parameters of the U-Net model decoder. The present invention integrates the histological characteristics of the case and the microenvironment dynamic constraints into the segmentation process of the U-Net model, and has a strong segmentation accuracy for transition areas with high morphological heterogeneity and invasive growth.

A computer-implemented method for determining a risk of having or developing steatohepatitis and / or a complication thereof in a subject. The method includes the steps of: receiving at least one image of the subject and at least one clinical and / or biological data, both previously obtained from the subject; calculating a score of fat infiltration heterogeneity on the at least one image based on at least one radiomic feature obtained for a region of interest including at least one skeletal muscle; combining the calculated score of fat infiltration heterogeneity with the at least one clinical and / or biological data previously obtained from the subject; determining a risk for the subject of having or developing steatohepatitis and / or a complication thereof based on the combination of the calculated score of fat infiltration heterogeneity with the at least one clinical and / or biological data.

The invention discloses an osteoporotic bone sample sampling device, and belongs to the technical field of sample sampling, the osteoporotic bone sample sampling device comprises a sampling platform, one side of the sampling platform is provided with a control panel, and the center of the surface of the top end of the sampling platform is welded with a material guide disc; meanwhile, the surface of the top end of the material guiding disc is communicated with a collecting box at the bottom of the sampling platform, adjustable fixed rotating assemblies are welded to the two sides of the material guiding disc and used for clamping and fixing bone tissue samples of different positions and different densities, and multi-direction rotating assemblies are welded to the tops of the adjustable fixed rotating assemblies and used for drilling the bone samples from multiple angles. By adopting the adjustable fixed rotating assembly and the multi-direction rotating assembly, the equipment can perform multi-angle and multi-direction sampling at the same position and in the same direction, the heterogeneity of bone tissues can be captured more comprehensively, and errors or local deviation possibly generated by single-direction sampling are avoided.

The invention discloses a tumor metastasis risk assessment method and system based on circulating tumor DNA (ctDNA) spatial heterogeneity. The core of the method is as follows: blood samples of at least two different anatomical sites (such as peripheral veins and tumor drainage veins) of the same subject are obtained at the same time, and ctDNA in the samples is subjected to sequencing analysis; calculating characteristic data (such as a relative abundance ratio) representing ctDNA spatial distribution based on the mutation abundance difference between different parts; and finally, inputting the feature data into a pre-trained metastasis risk assessment model, and outputting a quantitative tumor metastasis risk score. According to the method, the limitation of traditional single-point liquid biopsy is broken through, the detection sensitivity of tiny metastases can be remarkably improved by utilizing the spatial distribution information of the ctDNA, potential metastasis positioning information is provided, and powerful technical support is provided for accurate diagnosis and treatment decision of tumor patients.

The present application relates to the technical field of intraoperative navigation, and particularly relates to an intraoperative brain glioma deep learning detection method and system based on hyperspectral imaging, the steps of the method comprising: analyzing the internal heterogeneity of brain glioma based on spectral difference, evaluating the coverage benefits of preoperative planning path and intraoperative detour path; analyzing the blood oxygen saturation distribution based on the absorption peak characteristics of hemoglobin in a specific wave band, evaluating the risk of local ischemia of the preoperative planning path and the intraoperative detour path; mapping the preoperative planning path and the intraoperative detour path to the brain function area topology network respectively, and evaluating the functional damage risk of the paths based on the topological connection relationship and the risk of local ischemia; analyzing the expected benefits and risk trends of the preoperative planning path and the intraoperative detour path, and generating surgical path decision suggestions. The present application quantifies the path coverage benefits and functional damage risks of the surgical path, effectively improving the accuracy and safety of the surgical path decision.

Ultrasound images of a patient's cornea or sclera include speckles that can be tracked between frames to measure tissue displacement, such as during a heartbeat that changes intraocular pressure. Speckle tracking techniques and noise reduction filters allow for the strain within the tissue to be calculated and compared to known thresholds to determine stiffness. These measures will be used to diagnose keratoconus and other ophthalmology disorders at an early stage, as an abnormally low stiffness or heterogeneity in stiffness will indicate high risk for progression of certain diseases.

The invention relates to the technical field of medical information, in particular to a chronic osteomyelitis prediction model training method, prediction method and device based on habitat imaging and radiomics, electronic equipment and a storage medium. Comprising the following steps: respectively training multiple machine learning algorithms by using a first sample set, a second sample set, a third sample set, a fourth sample set, a fifth sample set and a sixth sample set to obtain corresponding six types of training model sets; and respectively selecting the model with the best evaluation result from the six types of training model sets to form a chronic osteomyelitis prediction model group. According to the method, the internal heterogeneity of the focus can be deeply quantified and the internal heterogeneity and microenvironment characteristics of the focus can be captured on the basis of the inhabitation characteristics, the focus can be more accurately positioned when the boundary of the focus is fuzzy, a clearer focus excision boundary is provided for surgeons, scientific excision is further converted into accurate excision, unnecessary tissue damage is reduced, and the operation efficiency is improved. And the risk of postoperative recurrence and complications is reduced.

Methods for characterizing aneuploidy based intratumor heterogeneity for a tumor of a tumor type for a subject. The methods may comprise, for example, obtaining sample aneuploidy data for the tumor, calling subclonal aneuploidy events in the sample aneuploidy data and generating an intratumor heterogeneity score for the tumor sample, and use of the aneuploidy based intratumor heterogeneity in cancer treatment and prognostics.

A beam angle optimization method for particle therapy comprises: receiving, by an analysis apparatus, distance information from a patient's body surface to a tumor, internal heterogeneity information, internal transmission information of a particle beam, and internal motion information according to the patient's respiration; inputting, by the analysis apparatus, the distance information from the patient's body surface to the tumor, the internal heterogeneity information, the internal transmission information of the particle beam, and the internal motion information according to the patient's respiration into a deep learning model; and calculating, by the analysis apparatus, a particle therapy beam angle based on an output value of the deep learning model.

The present application encompasses TCRs and combinations of TCRs for treatment of melanoma (e.g., cutaneous melanoma, uveal melanoma, or advanced melanoma), non-small cell lung cancer (NSCLC), head and neck cancer (e.g., non-nasopharyngeal head and neck cancer), sarcoma, thyroid cancer, cervical cancer, ovarian cancer, anal cancer, genital cancer, or anogenital cancer. Due at least in part to the heterogeneity of solid tumor cells, therapies used to treat solid tumors often result in a partial response. The present disclosure includes, among other things, multiplexing of TCRs in a single therapy or therapeutic regimen of engineered T cells.

This invention relates to a method and medium for quantifying biomechanical heterogeneity and predicting prognosis in hepatocellular carcinoma (HCC) based on a multi-scale mechanical interaction network. The method includes: retrieving the shear modulus and loss angle parameter maps of the tumor based on multi-frequency magnetic resonance elastography data; dividing the tumor into multiple biomechanical regions using mechanical gradient-driven adaptive clustering; constructing an intratumoral mechanical interaction network and extracting its topological features; constructing a multi-organ mechanical coupling model of the tumor, liver, and spleen, and calculating the cross-organ stress transfer efficiency as a coupling feature; fusing intratumoral network features and cross-organ coupling features to form a multi-scale biomechanical phenotypic vector, and inputting it into a machine learning model in conjunction with clinical features to achieve individualized and accurate prediction of postoperative recurrence risk in HCC patients. Compared with existing technologies, this invention provides a novel systemic biomechanical perspective for prognostic assessment by quantifying the intratumoral mechanical heterogeneity and its mechanical interaction with host organs.

The invention discloses a hepatocellular carcinoma microvessel invasion prediction system and application thereof, and the system comprises a data collection module, a focus sketching module, an image preprocessing module, an image preprocessing and focus cutting module, a segmentation module, a peritumoral feature extraction module, and a feature fusion and classification module. The segmentation module uses a segmentation model to segment the processed focus area image and takes output features as tumor internal edge heterogeneity features, and the tumor edge feature extraction module performs feature extraction on tumor edges in a ResGCN composition mode of introducing an extrusion excitation module; and finally, a feature fusion module is used for realizing fusion of tumor internal heterogeneity features and tumor edge heterogeneity features to obtain a prediction result, a segmentation task and a classification task are combined, comprehensive features of the tumor are fully utilized, high-precision segmentation of the hepatocellular carcinoma is realized, a non-invasive and efficient prediction scheme of capillary invasion is provided, and the prediction efficiency of the hepatocellular carcinoma is improved. The method has important application value in clinical auxiliary diagnosis.

Methods for using tumor heterogeneity score as a biomarker to guide treatment and / or patient monitoring decisions are described. The methods may comprise, for example, acquiring knowledge of a driver mutation in a sample obtained from a subject; identifying one or more variants present in the sample; determining a tumor heterogeneity score for the sample based on the one or more variants; and comparing the tumor heterogeneity score for the sample to a threshold tumor heterogeneity score, where if the tumor heterogeneity score is less than or equal to the threshold tumor heterogeneity score, the subject is identified for treatment with a first anti¬ cancer agent, and where if the tumor heterogeneity score is greater than the threshold tumor heterogeneity score, the subject is identified for treatment with a second anti-cancer agent.

The application relates to the technical field of medical image processing and intelligent tumor grading recognition, and discloses a head and neck squamous carcinoma early recognition method based on imaging and deep learning, which comprises the following steps: acquiring head and neck CT, MRI and PET three-mode image data; adopting a two-stage dynamic structure alignment mechanism for registration; extracting fused imaging features; constructing a tumor sub-feature map; outputting a tumor grade and a prediction confidence through an uncertainty prediction model; and generating a saliency explanation heat map. Compared with the prior art which depends on single-mode images or shallow texture feature extraction models, especially under the condition that the boundary of a heterogeneous tumor region is fuzzy, different modes exist significant structure offset, the technical problem that high confidence precision discrimination of a real tumor staging state cannot be realized. Since the saliency guided registration mechanism and the improved graph convolutional neural network are introduced and combined with Dropout reasoning, the accuracy of the head and neck squamous carcinoma early stage recognition is improved.

The invention relates to a construction method and application of a congenital heart disease animal model, and belongs to the technical field of biology. According to the method, a Wt1 CreERT2 mouse with inducible tissue specific expression is mated with an Actg1 flox mouse, after a filial generation mouse is obtained, tamoxifen is used for induced knockout in a specific period of embryonic development, and specific knockout of the Actg1 gene in the epicardium is achieved. The method can stably and repeatedly construct the ventricular septal defect model with highly consistent phenotype, overcomes the problems of high phenotype heterogeneity and low intervention precision in the prior art, and is suitable for mechanism research and drug screening of congenital heart diseases.