39 results about "Tissue morphology" patented technology

The invention relates to a biomedical image feature fusion method based on a multi-scale heterogeneous hypergraph. The method comprises the following steps: S1, constructing a cell-level hypergraph model; s2, constructing a region-level hypergraph model; s3, constructing a sample-level hypergraph model; s4, transmission and fusion of cross-level hypergraph features: through a level graph neural network HGCN and a dynamic attention mechanism, transmission of cell-level hypergraph features-region-level hypergraph features-sample-level hypergraph features is carried out, global alignment is carried out, and global hypergraph features are obtained; and S5, constructing a histomorphological classification model by using the global hypergraph features, and outputting sample feature representation. According to the method, through multi-scale heterogeneous hypergraph modeling and cross-level dynamic feature fusion, the problems of single-scale characterization limitation and heterogeneous data high-order interaction bottleneck are solved, the cross-scale characterization capability of the biological tissue microenvironment is remarkably improved, the adaptability, generalization performance and analysis precision of a classification model to complex data scenes are enhanced, and the method is suitable for being popularized and applied. And a general framework is provided for complex biomedical analysis tasks.

The invention provides a pathological image tissue classification method based on staining invariance and tissue morphological characteristics, which comprises the following steps of: 1, modeling an input pathological image based on a staining invariance module, reconstructing an absorption coefficient of the image to obtain staining invariance characteristics, and fusing the staining invariance characteristics into a backbone network; 2, carrying out channel separation on the image based on a tissue morphology module, respectively extracting morphological characteristics of cell nucleus and non-nuclear tissues, and fusing the morphological characteristics into each level of a backbone network layer by layer in a pixel-by-pixel addition mode; 3, constructing a comparison loss function guided by a prototype, representing each category as an updatable category prototype, dynamically updating the prototype by using a high-confidence sample, and optimizing the feature expression ability by maximizing the similarity between the sample and the similar prototype and minimizing the similarity between the sample and the heterogeneous prototype; and 4, performing end-to-end training on the model by combining the prototype comparison loss and the cross entropy loss, and outputting prediction results of each category, thereby realizing accurate tissue classification of the pathological image.

This invention discloses a wired dual-modal imaging capsule endoscopy system, belonging to the field of medical device technology. The system includes a capsule module, a transmission and control module, a dual-modal imaging module, and a signal analysis module. The capsule module is used to achieve 360° circumferential scanning imaging of the esophageal mucosa. The transmission and control module ensures stable transmission of optical and electrical signals and precise control of capsule movement. The dual-modal imaging module integrates an optical coherence tomography submodule and a photoacoustic imaging submodule to acquire tissue morphology information and microvascular distribution information, respectively. The signal analysis module processes the dual-modal signals. This invention achieves three-dimensional high-resolution integrated imaging of the esophageal mucosa without the need for exogenous labeling agents, significantly improving the detection accuracy of early esophageal cancer and precancerous lesions.

The invention relates to a method for rapidly transparentizing biological tissues, which comprises the following steps: carrying out degreasing treatment on a fixed biological tissue sample by using a degreasing solution which is an aqueous solution containing tetrahydrofuran and tetrahydroxypropyl ethylenediamine (EDTP); the degreased biological tissue sample is subjected to refractive index matching with a refractive index matching solution, transparency treatment is completed, and the refractive index matching solution is an aqueous solution containing urea, iohexol and EDTA. According to the method for transparentizing the biological tissue, visceral organs can be transparentized quickly, tissue shrinkage is not caused, and the tissue form is reserved. In addition, the method for transparentizing the biological tissue according to the invention has the advantages of fluorescence protection, morphology retention and high biological safety.

The application provides an application of Buyang Huanwu Decoction in the preparation of a product for treating high altitude pulmonary injury of qi deficiency and blood stasis syndrome, and belongs to the technical field of medicines. After the prescription of the Buyang Huanwu Decoction is decocted with water, the decoction is used for treating high altitude pulmonary injury, can reduce pathological injury of lung tissues, reduce thickening of alveolar walls, make lung tissue structure clearer, and close to normal lung tissue morphology; meanwhile, the decoction can enhance exercise capacity, reduce asthenia symptoms of high altitude pulmonary injury of qi deficiency and blood stasis syndrome, and effectively treat high altitude pulmonary injury of qi deficiency and blood stasis syndrome.

The application discloses an application of Campanula medium in treatment of perimenopausal depression, and a method is as follows: Campanula medium is added into 10 times of distilled water in weight, decocted for 1 h and filtered, residues are added with 8 times of distilled water, and then decocted for 1 h and filtered, and filtrates are combined, and concentrated into 1 g / mL of medicinal liquid according to medicinal material, so that Campanula medium medicinal liquid is obtained. According to the experimental result, Campanula medium can improve the depression and anxiety behavior of PMD model mice. Campanula medium can improve the hippocampus tissue morphology and structure of the PMD model mice, increase the neuron Nissl body abundance of the hippocampus, promote the ER-BDNF-TrkB path, improve the monoamine neurotransmitter level, correct the HPA axis hyperactivity, and thus improve the depression behavior.

The invention discloses a digestive tract tumor biopsy sampling device convenient for puncture and sampling for medical oncology, which relates to the technical field of tumor biopsy sampling and comprises a biopsy device, a limiting seat and a base. According to the alimentary canal tumor biopsy sampling device convenient to puncture and sample for the medical oncology, tumor tissue can be accurately contained through the sampling groove, fragmentation of a tumor tissue sample is avoided, it is guaranteed that the tissue sample meets the tissue form needed by detection, the sample quality is guaranteed, the outer sleeve needle covers the sampling groove after sampling, the sample can be fixed and cannot fall off, and the sampling efficiency is improved. The tissue is prevented from remaining in the body or being polluted during withdrawing, and meanwhile the risks of bleeding and tissue damage in the puncture process are reduced; enough samples can be obtained through one-time operation, the repeated puncture frequency is reduced, the operation time is shortened, the pain of a patient is relieved, and the operation efficiency is improved; and the modularized puncture needle design allows medical staff to quickly adjust the puncture depth according to individual differences, and the flexibility is high.

The invention relates to the technical field of gene expression prediction, and discloses a spatial gene expression prediction method based on a pathological image and a multi-modal heterogeneous graph. According to the method, a multi-modal heterogeneous graph containing a target slice edge, a cross-slice edge and a reference slice edge is constructed, and intra-slice space continuity and a cross-slice sharing mode are fused; designing a complementary mask strategy to generate an enhanced view, and enhancing the adaptability of the model to data defects; by means of CNDA bidirectional attention and CNAP multi-head pooling modules, precise cross-slice knowledge migration is achieved; and optimizing the multi-dimensional constraint model through a comprehensive loss function. According to the method, the association rule of tissue morphology and gene expression can be effectively captured, and the space consistency and accuracy of prediction are improved; the robustness and generalization of the model are enhanced, and data of different diseases and platforms are adapted.

The application discloses a medical tissue morphology image analysis information processing method and device, equipment and medium, and relates to the technical field of information processing. The method comprises the following steps: obtaining a target medical image to be analyzed, extracting an effective tissue region from the target medical image, and dividing the effective tissue region into a plurality of image instance blocks; inputting each image instance block into a pre-trained tissue feature extraction model, outputting a tissue morphology feature vector corresponding to each image instance block, performing attention scoring on each tissue morphology feature vector through an instance detection module of a multi-instance learning network, and selecting a target image instance block containing a pathological feature region according to the attention scoring; and performing aggregation processing on a target tissue morphology feature vector corresponding to the target image instance block, generating and outputting an aggregated global feature representation. The method automatically identifies a key region in a medical image and generates a visual global feature representation.

The invention relates to the technical field of medical image processing, in particular to a gastrointestinal anastomotic stoma healing real-time monitoring image analysis system which comprises an image acquisition module, a preprocessing module, a feature extraction module, a manifold construction module, a curvature analysis module, a geodesic prediction module, a risk assessment module and a decision support module. The system collects a continuous image sequence of a gastrointestinal anastomotic stoma area, extracts multi-dimensional features such as oxyhemoglobin saturation distribution, tissue morphology and blood vessel distribution, expresses a healing state as a low-dimensional manifold based on a differential geometry theory, detects abnormality through multi-scale curvature analysis, predicts a healing trajectory by using a geodesic theory, and performs multi-branch prediction. Risk grading and early warning are achieved, the healing state of the gastrointestinal anastomotic stoma can be objectively and quantitatively evaluated, nonlinear dynamic characteristics of the healing process are effectively captured, and potential abnormal healing is predicted 48-96 hours in advance.

Features are disclosed for imaging block and slice samples using an imaging system. The imaging system can link the images by identifiers associated with the block and slice samples. The imaging system can train a machine learning algorithm based on correctly linked images. In some embodiments, the trained machine learning algorithm may include an image analysis module or a convolutional neural network. The imaging system can use the trained machine learning algorithm in order to determine a confidence score of a match between the block and the slice samples. The trained machine learning algorithm can use features of the block and the slice samples such as shape and tissue morphology to determine whether the samples match. In some embodiments, when the confidence score is below a certain threshold, the imaging system can alert a user that the samples may not match.

The application relates to the medical technical field, in particular to application of zidovudine in preparation of a medicine for preventing and / or treating alcoholic gastric ulcer, and experiment results show that the zidovudine has a remarkable curative effect on peptic ulcer disease and inflammatory bowel disease, can effectively improve mucosal integrity, promote tissue morphology improvement, and restore animal body weight, and has a good clinical application prospect.

The invention provides a pathology agent system with reasoning ability. The pathology agent system comprises a pathology host agent, a pathology physician agent, a pathology section viewer, a pathology multi-mode large language model and a pathology report agent. The pathology host agent is responsible for coordinating a diagnostic pathology analysis process and strategically planning a pathological section area for detailed examination; the pathology main agent plans and coordinates the plurality of pathologist agents to investigate different pathological section tissue areas at the same time according to the formulated preliminary pathological diagnosis hypothesis and strategy; and each pathologist intelligent agent interacts with the pathological section viewer and the pathological multi-mode large language model, analyzes a specific pathological section area and feeds back a result to the pathologist intelligent agent. According to the invention, different pathological section areas can be studied step by step in a layered manner, and important background information such as tissue morphology and peripheral features can be captured based on analysis of a full pathological section level.

The invention discloses a method for identifying the intestinal health degree of micropterus salmoides, which is characterized in that the intestinal health degree of the micropterus salmoides is evaluated and identified by detecting three indexes of intestinal sensory morphology, intestinal tension value and intestinal tissue morphology of a micropterus salmoides sample and combining an evaluation model of the intestinal health degree of the micropterus salmoides. The identification method is applied to micropterus salmoides culture, and technicians can conveniently and systematically evaluate the intestinal health condition of micropterus salmoides in time so as to formulate a culture scheme and disease prevention and treatment measures of the next step; meanwhile, the method can be used for guiding adjustment of raw material components or proportion of a breeding feed formula, and is beneficial for improving the growth performance of micropterus salmoides and increasing breeding benefits.

The application provides a pharmaceutical composition for protecting intestinal injury caused by chemotherapy and use, and belongs to the field of medicines. The application also provides a pharmaceutical composition for protecting tight junction injury of intestinal mucosa caused by chemotherapy, which is prepared from raw medicinal materials in the following proportions by weight: 1-3 parts of astragalus polysaccharide and 1-3 parts of sanguisorba officinalis saponin I. The astragalus polysaccharide combined with the sanguisorba officinalis saponin I can not only improve the immunity of the body after chemotherapy, but also protect the intestinal mucosa injury caused by intestinal chemotherapy drugs, and solves the problem that there is no specific drug for intestinal injury after chemotherapy on the market. The drug efficacy test proves that the astragalus polysaccharide combined with the sanguisorba officinalis saponin I has a synergistic effect on protecting the tight junction injury of intestinal mucosa caused by chemotherapy. The composition of the application can protect the intestinal injury of pets caused by chemotherapy or diarrhea of young animals, maintain the integrity of the intestinal tissue morphology and structure, enhance the immunity of young animals, reduce economic losses, and reduce the use of antibiotics.

The application discloses an immune regulation pharmaceutical effect analysis method based on a concentrated pill of psammochloa and astragalus, which comprises the following steps: raw material extraction, animal model construction, multi-dimensional detection and data statistics. The raw materials of psammochloa and astragalus are weighed according to a specific ratio, and then are prepared into extract by ethanol decoction and concentration. After the experimental animals are grouped and administered intragastrically, the individuals are screened by the four oxygen pyrimidine modeling. The immune organs are separated, weighed, and the index is calculated. The contents of various cytokines in serum and liver tissue are detected by the ELISA method. The tissue morphology, lymphocyte proliferation and protein expression are observed by HE staining, MTT method and immunofluorescence method. The expression of key signal pathway proteins is detected by electrophoresis and other steps after the total protein is extracted, and statistical analysis is carried out. The method is systematic and comprehensive, the result is accurate and reliable, and a scientific basis is provided for the immune regulation pharmaceutical effect evaluation of the concentrated pill.

The present invention provides a first aid tourniquet pressure monitoring and automatic alarm system, which relates to the technical field of pressure monitoring. The system includes a biological reaction monitoring module, a pressure adjustment analysis module, a real-time pressure adjustment module, a safety threshold detection module, and an emergency response activation module. In the present invention, through real-time monitoring of biological reactions, the changes in microblood flow, skin electrical impedance and tissue morphology of patients after using a tourniquet are captured, making the monitoring of individual reactions more comprehensive, and combining the patient's actual physiological state to evaluate the safety and effect of pressure, making the monitoring more dynamic and personalized, and the combination of real-time pressure adjustment and emergency response ensures that when the pressure exceeds the safe range, the pressure is quickly adjusted and a warning is issued through an alarm, avoiding secondary injuries caused by improper pressure, improving the safety and response speed of tourniquet use, and being able to more accurately prevent patient tissue damage, ensuring real-time effectiveness and safety during first aid.

The invention discloses a tissue sample processing method for three-dimensional pathological imaging, and belongs to the technical field of tissue sample processing. The tissue sample treatment method comprises the following steps: step a, decolorizing a tissue sample; b, tissue transparentizing based on the swelling hydrogel; in the step a, the discoloring of the tissue sample adopts a mode of matching physical discoloring with chemical discoloring; wherein the physical decolorization is realized by continuously irradiating a tissue sample under blue-violet light. The problem that autofluorescence of endogenous pigment and residual blood in a tissue sample interferes with biomarker observation is solved in a mode of matching physical decoloration and chemical decoloration, meanwhile, tissue transparentization is realized by utilizing expanded hydrogel, and the tissue form is kept stable, so that a good foundation is laid for subsequently realizing high-efficiency elution and multi-round marking of an antibody; therefore, in-situ multiple marking and high-resolution three-dimensional imaging of tissue samples, especially thick slices such as brain tumor tissues and the like can be realized.

This invention discloses a destaining solution for DAB immunohistochemical staining. The destaining solution comprises a functionalized ionic liquid with a volume concentration of 10%-40% and a co-solvent of 60%-90%. The functionalized ionic liquid is a carboxyl-functionalized imidazole ionic liquid and / or a hydroxypyridine ionic liquid. The co-solvent is a glycerol solution. The destaining solution of this application uses a functionalized ionic liquid as the core active component, which can rapidly and thoroughly remove DAB chromogenic products. The ionic liquid has good biocompatibility, and when combined with a specific concentration of glycerol co-solvent, it can create a moisturizing environment, effectively preventing tissue drying and detachment. The mild pH environment and the selection of a neutral protease ensure that the tissue morphology and antigen activity are not damaged, facilitating subsequent counterstaining operations.

The invention relates to the technical field of rehabilitation medicine and intelligent rehabilitation engineering, and discloses a self-adaptive constant-speed rehabilitation training method based on tissue morphology and electrophysiological signal double feedback. According to the method, muscle group tissue morphology and electrophysiological signals are synchronously collected through high-resolution ultrasound and surface myoelectricity, and muscle structure-function joint representation is constructed through multi-modal time sequence alignment; an adaptive impedance adjusting model is used for dynamically generating individualized constant-speed training resistance, and a joint angular speed closed-loop feedback correction track is combined, so that it is ensured that the resistance is accurately matched with the muscle state under full-range constant-speed movement. Rehabilitation normal form transformation from experience driving to physiological feedback driving is achieved, and training accuracy, safety and individual suitability are improved.

The invention provides a construction method of a spinal cord injury animal model for maintaining the integrity of subarachnoid space, which comprises the following steps: adopting a mammal with spinal cord injury, clamping and closing the opening of the dura mater of the mammal, dripping biological glue in alignment with the clamped and closed position, and suturing after the biological glue becomes frost and the dura mater is adhered together. The invention also provides application of the spinal cord injury animal model for maintaining the integrity of the subarachnoid space in research on motor function, nervous tissue recovery or tissue morphology recovery of animals after spinal cord injury. The application shows that after experimental spinal cord injury is caused, the motion function and histomorphological recovery of a mouse can be improved by tightly suturing the dura mater.

The invention relates to the technical field of image processing, in particular to an endocrine-related anorectal traditional Chinese medicine pharmacological image sequence analysis method, which comprises the following steps: acquiring continuous frame images, extracting annular boundaries, comparing contour trends to identify repeated areas, tracking a one-way evolution image layer to remove redundant frames, and positioning a traditional Chinese medicine path tracking and pushing area. And screening a rhythm image according to a hormone cycle, screening a rhythm section image, tracking a boundary drift analysis extension direction, screening a continuous path region, and obtaining a structure disturbance graph. According to the method, redundant regions are eliminated through contour trend comparison, the recognition continuity of structural changes between image frames is enhanced, a continuous response region is extracted through boundary consistency in the path direction, the time advancing trend of tissue morphology is analyzed in combination with contrast of a hormone cycle, and a structural disturbance trajectory is constructed according to the boundary advancing direction. And a response path is extracted by combining the offset distribution of the central axis structure in the sequence, so that the tissue change in the image has directivity, rhythmicity and sequencing.

The application relates to the medical technical field, in particular to application of 6-mercapto guanine in preparation of a medicine for preventing and / or treating alcoholic gastric ulcer, experimental results show that the 6-mercapto guanine has remarkable curative effect on peptic ulcer disease and inflammatory bowel disease, can effectively improve mucosal integrity, promote tissue morphology improvement, restore animal body weight, and has a good clinical application prospect.

The invention relates to the technical field of medical imaging processing, in particular to a multimodal image fusion method based on prostate cancer tissue morphology, which comprises the following steps: acquiring microvascular photoacoustic imaging, ultrasonic elastography and magnetic resonance imaging of the same prostate part; taking microvascular photoacoustic imaging and ultrasonic elastography as reference images, taking magnetic resonance imaging as a floating image, and constructing a bidirectional supervised registration network; and carrying out lightweight processing on the bidirectional supervised registration network through transfer learning, and establishing a rapid registration network. According to the method, firstly, high-precision registration results of magnetic resonance, photoacoustic and ultrasonic images are obtained through a complex model structure, then a small model structure is formed through transfer learning, the high-precision performance of the complex model structure is learned, structural simplification and high-precision performance of the model are considered, the requirement for a deployment environment is reduced, and the cost is reduced. And the universality is improved.

This invention relates to the field of medical image processing technology, specifically to a method and system for processing immune scoring data based on deep learning. The method includes: acquiring an immunohistochemically stained whole-section image to be scored; dividing the whole-section image into non-overlapping image blocks; performing multi-level spectral separation and decomposition on each image block to construct a spatial density distribution map of immune cells in the whole-section; segmenting the tumor central region and invasion edge region on the spatial density distribution map according to tissue morphology gradients, and extracting the corresponding local density distribution. This invention, by inverting the effective chemotaxis coefficient and effective proliferation coefficient of the reaction-diffusion coupling system from the spatial density distribution map of immune cells, can directly quantify the degree of mechanistic deviation of immune cell chemotaxis and proliferation capacity in the tumor microenvironment, overcoming the limitations of traditional methods that rely solely on static cell density counting, and giving the scoring a clear biophysical meaning.

The invention discloses a wrist strap restraining tool with intelligent pressure monitoring and adjusting functions, and belongs to the technical field of medical care equipment. The wrist strap restraining tool comprises a wrist strap body, a pressure sensor array, an air bag, an air pressure adjusting system and a core control module. A processor in the core control module is configured to obtain real-time pressure distribution data collected by the pressure sensor array; constructing a tissue shape situation field representing the compression state of the wrist tissue; comparing the maximum form risk potential value in the tissue form situation field with a preset tissue steady state threshold value; and when the maximum form risk potential value exceeds the tissue steady state threshold value, the air pressure adjusting system is driven to carry out differential adjustment on the air bag so as to execute potential field equalization regulation and control, and therefore the maximum form risk potential value is reduced. According to the method, the tissue shape situation field is constructed and is subjected to active equalization regulation and control, so that the tissue damage risk caused by local pressure concentration can be avoided.

The present application relates to the technical field of medical imaging processing, in particular to a multi-modal image fusion method based on prostate cancer tissue morphology, comprising the following steps: obtaining microvessel photoacoustic imaging, ultrasonic elastography and magnetic resonance imaging of the same prostate site; taking the microvessel photoacoustic imaging and the ultrasonic elastography as reference images and the magnetic resonance imaging as a floating image to construct a bidirectional supervision registration network; and performing lightweight processing on the bidirectional supervision registration network through transfer learning to establish a fast registration network. The present application first obtains a high-precision registration result of the magnetic resonance, photoacoustic and ultrasonic images through a complex model structure, and then forms a small model structure through transfer learning to learn the high-precision performance of the complex model structure, so that the simple structure and the high-precision performance of the model are compatible, the requirement of the deployment environment is reduced, and the universality is improved.

Features for imaging a block sample and a slide sample using an imaging system are disclosed. The imaging system can link images by identifiers associated with the block sample and the slide sample. The imaging system can train a machine learning algorithm based on correctly linked images. In some embodiments, the trained machine learning algorithm can include an image analysis module or a convolutional neural network. The imaging system can use the trained machine learning algorithm to determine a confidence score of a match between the block sample and the slide sample. The trained machine learning algorithm can use features of the block sample and the slide sample, such as shape and tissue morphology, to determine whether the samples match. In some embodiments, the imaging system can alert a user that the samples can not match when the confidence score is below a certain threshold.

The invention belongs to the technical field of biology, and particularly relates to application of bacteroides vulgaris in preparation of medicine for preventing and treating sepsis injury, the sepsis injury is kidney injury caused by sepsis, the survival time of mice with sepsis can be obviously prolonged after pretreatment of bacteroides vulgaris, the survival rate of the mice is increased, and the application of bacteroides vulgaris in preparation of medicine for preventing and treating sepsis injury is achieved. In addition, the traditional Chinese medicine composition can obviously improve mouse kidney tissue morphological lesions, inhibit CLP-induced mouse kidney tissue pathological morphological injuries, obviously reduce serum BUN and Creatinine contents and slow down mouse CLP-induced sepsis kidney injuries, and a new medicine is provided for preventing and treating sepsis injuries.

The invention discloses an ovarian endometriosis glandular epithelial organ and interstitial cell co-culture model and a construction method thereof. The construction method comprises the following steps: S1, constructing an ovarian endometriosis cyst glandular epithelial organ; s2, constructing a 3D culture body of the ovarian endometriosis cyst interstitial cells; and S3, digesting the glandular epithelium organ, mixing the glandular epithelium organ with the interstitial cells in proportion, and embedding the glandular epithelium organ in matrigel for three-dimensional co-culture. According to the invention, a patient-derived ovarian endometriosis glandular epithelial organ and interstitial cell co-culture system is established for the first time, the model and a primary focus are highly homologous in tissue morphology and biomarker expression, and the bionic degree is high; it is clear that the number of glandular epithelial organs is the largest when the ratio of epithelial cell clusters to interstitial cells is 1: 2, the vitality of the glandular epithelial organs in a group with the ratio of 1: 2 to 1: 4 is remarkably improved, and the technical bottlenecks that an existing co-culture model is fuzzy in proportion, and the cell viability is difficult to maintain are solved.