86 results about "Histopathology" patented technology

Methods and systems for analysing the cellular composition of a sample are described, comprising: providing an image of the sample in which a plurality of cellular populations are associated with respective signals and classifying a plurality of query cells in the image between a plurality of classes corresponding to respective cellular populations in the plurality of cellular populations. This is performed by providing a query single cell image to an encoder module of a machine learning model to produce a feature vector for the query image, and assigning the query cell to one of the plurality of classes based on the feature vector for the query image and feature vectors produced by the encoder module for each of a plurality of reference single cell images. The machine leaning model comprises: the encoder module, configured to take as input a single cell image and to produce as output a feature vector the single cell image, and a similarity module configured to take as input a pair of feature vectors for a pair of single cell images and to produce as output a score indicative of the similarity between the single cell images. Thus, the machine learning model can be obtained without the need for an extensively annotated dataset. The methods find use in the analysis of multiplex immunohistochemistry / immunofluorescence in a variety of clinical contexts.

A multimodal deep learning framework which is used to determine the likelihood of a particular treatment method effectively treating a patient with ovarian / kidney cancer with the goal of increasing patient survival. The framework takes into account not only large histopathology images (whole slide images), but also clinical variables to increase the scope of the data. The results demonstrate that the proposed models achieve high prediction accuracy and interpretability and can also be transferred to other cancer datasets without significant loss of performance. One of the key innovations here is the combination of pathology and clinical variables in a deep learning model to provide recommendations in therapy areas with limited information.

Computer-implemented methods of analysing a histopathology sample are described, comprising obtaining a plurality of tile representations using a tile representation machine learning model, assigning each of the plurality of tile representations to one of a predetermined set of histomorphological phenotype clusters, obtaining a whole slide image representation using a histomorphological phenotype cluster language model, and predicting one or more biological or clinical features associated with the sample using a task specific machine learning model, wherein the task specific machine learning model is a model that has been trained using training whole slide images and optionally associated one or more ground truth biological or clinical features of interest to predict the one or more biological or clinical feature of interest for a whole slide image using as input the whole slide image representation provided by the histomorphological cluster language model for the whole slide image.

The application relates to a compound medicine for delaying skeletal muscle aging and application thereof, and the medicinal active components in the compound medicine composition are composed of menadione bisulfite sodium and N-acetyl cysteine, and belong to the technical field of biological medicine. A novel drug combination mode is developed, an oxidant menadione bisulfite sodium (MBS) and an antioxidant N-acetyl-L-cysteine (NAC) are combined and given in different time periods to regulate the H2O2 circadian rhythm of the skeletal muscle of old mice, the changes of the muscle strength, histopathology and aging marker protein level of the skeletal muscle of the old mice are detected, and then the precise compound medicine capable of improving the skeletal muscle function of the old mice and delaying skeletal muscle aging is determined. The application provides an effective drug combination strategy for relieving or treating the delay of skeletal muscle aging, and has very significant meaning.

The application discloses a lactobacillus johnsonii OD-5 and application and products thereof, and belongs to the technical field of microorganisms. A technical problem to be solved by the application is to provide a lactobacillus johnsonii capable of treating kidney stones. A technical solution is a lactobacillus johnsonii OD-5 with a preservation number of CGMCC No. 38426. The lactobacillus johnsonii can reduce urine oxalic acid and regulate urine calcium, effectively correct abnormal urine biochemical conditions promoting stone formation, reduce related kidney function damage, and inhibit formation and deposition of calcium oxalate crystals in the kidney at a histopathological level, thereby significantly reducing the stone incidence. The application provides a solid theoretical basis for development of products taking the lactobacillus johnsonii OD-5 as a core component and used for preventing kidney stones and improving stone kidney damage.

The invention relates to the technical field of medicines, in particular to application of a neuropeptide Y1 receptor antagonist in preparation of a hereditary polycystic kidney disease treatment medicine. The neuropeptide Y1 receptor antagonist is selected from a compound BIBO3304 which plays a role in blocking combination of neuropeptide Y (NPY) and a Y1 receptor subtype thereof. On the basis that early-stage histopathology, high-throughput sequencing, cytobiology and molecular biology are combined with in-vitro cell culture and in-vivo animal experiments, the potential treatment effect of the neuropeptide Y1 receptor antagonist in preparation of hereditary polycystic kidney disease treatment drugs is provided, and a new basis is provided for hereditary polycystic kidney disease treatment.

This invention relates to a guinea pig model of chronic obstructive pulmonary disease (COPD) with chronic bronchitis, its preparation method, and its application. Specifically, this invention provides a guinea pig model of COPD with chronic bronchitis, established by subjecting guinea pigs to at least two intratracheal infusions of lipopolysaccharide (LPS) combined with repeated exposure to cigarette smoke. This results in the guinea pigs exhibiting pathophysiological characteristics consistent with those of COPD with chronic bronchitis in terms of cough sensitivity, airway inflammation, airway hypersecretion, lung function, and histopathology. This lays a solid foundation for in-depth research and drug screening of COPD with chronic bronchitis.

The invention discloses a method for establishing a mouse radioactive jawbone injury animal model, which comprises the following steps of: performing tooth extraction operation, performing radiation treatment after one day, and performing Micro-CT (Computed Tomography) scanning, intraoral examination and histopathologic detection on the lower jawbone on the thirteenth day after radiation so as to determine that the radioactive jawbone injury mouse model is successfully constructed. The animal model has the advantages that the pathological process of human early radioactive jaw necrosis is accurately simulated; the model is stable, good in repeatability and suitable for large-scale experimental research; and a reliable, short-cycle and convenient-to-operate animal model is provided for the mechanism research of radioactive jaw necrosis and the development of new drugs.

In some embodiments, tissue microarray (TMA) core images are used to train a deep learning network that can then be deployed to computer inferences regarding whole tissue section (WTS) images (WSIs). Preprocessing aligns paired serial core images from differently stained core sections with their associated metadata and H-scores (or other label data obtained from evaluating one of the paired core sections). In some embodiment, a self-supervised learning (SSL) pre-trained encoder is used to generate patch-level embeddings from TMA core images associated with corresponding labels that are then used to train an attention-based deep learning network to generate inferences. These and other aspects of the present disclosure are more fully detailed herein.

The invention belongs to the technical field of biological medicine, provides novel application of PRMT6, and particularly relates to application of a PRMT6 inhibitor in preparation of a medicine for preventing or treating sepsis-ARDS. The invention discloses the application value of the PRMT6 as the sepsis-ARDS treatment target for the first time. According to the application disclosed by the invention, the expression of PRMT6 is inhibited in a targeted manner, ferroptosis in alveolar epithelial cells (AECs) can be effectively inhibited, and the histopathology related to ARDS is further improved, so that the disease progress is effectively improved, and a new path is opened up for targeted therapy of sepsis-ARDS.

A generalizable and interpretable deep learning model for predicting microsatellite instability from histopathology slide images is provided. Microsatellite instability (MSI) is an important genomic phenotype that can direct clinical treatment decisions, especially in the context of cancer immunotherapies. A deep learning framework is provided to predict MSI from histopathology images, to improve the generalizability of the predictive model using adversarial training to new domains, such as on new data sources or tumor types, and to provide techniques to visually interpret the topological and morphological features that influence the MSI predictions.

The invention relates to the technical field of biological information, and discloses a gastric cancer survival analysis method based on a deep learning multi-modal fusion model, and the method comprises the steps: collecting histopathologic images, gene expression data and clinical information data of a plurality of patients, carrying out the preprocessing of the histopathologic image data, and then generating a data set, dividing the data set into a training data set and a test data set according to 7: 3; inputting the training data set into a MulitDeepsurv model for training, and evaluating performance by adopting a consistency index and an area under an ROC curve to obtain a trained model; inputting the test data set into the trained model for testing to obtain a risk score; and analyzing the risk score by adopting a Kaplan-Meier curve to obtain a distribution diagram of high-risk and low-risk patients. The problem that it is difficult to extract effective prediction features from multi-modal data can be solved, and the accuracy of disease diagnosis and prognosis evaluation is improved.

Provided herein are methods for the surgical removal of lung cancer tissue using CXL, a near-infrared fluorescent imaging agent. This approach involves administering a pharmaceutical composition containing CXL intravenously to a patient, detecting a fluorescence signal emitted from lung cancer tissues, and surgically excising the identified cancerous tissue. Administration doses may range from about 0.001 mg / kg to about 0.10 mg / kg, occurring between up to 4 days and about 1 hour before imaging. The method supports endoscopic imaging and surgeries, including thoracoscopic lung tissue resection, intraoperative visualization, and histopathological evaluation to confirm tissue removal. Exclusion criteria cover hypersensitivity history, renal impairment, and specific laboratory markers exceeding defined limits.

Methods for determining tumor heterogeneity are described. The methods may comprise, for example, obtaining a medical image associated with the sample from a subject; identifying a plurality of patches from the medical image; identifying a plurality of patch groups, wherein each patch group comprises one or more patches of the plurality of patches and corresponds to a region of interest in the medical image; inputting each patch group into a trained machine learning model to generate a plurality of genomic alteration predictions corresponding to the plurality of patch groups, wherein the plurality of genomic alteration predictions is related to the presence of one or more genomic alterations in each of the input patch groups; and generating the phenotypic tumor heterogeneity score by comparing the plurality of genomic alteration predictions.

A method and system for assessing a histopathological cause of kidney graft dysfunction in a subject following kidney transplantation is disclosed. The method comprises the steps of: a) generating one or more images of the native fluorescence emission from one or more exfoliated kidney cells obtained from a urine sample from the subject in a plurality of distinctive spectral channels, b) calculating, for each urinary exfoliated kidney cell, quantitative features of the autofluorescence signals in said one or more images, c) applying a feature selection methodology to the quantitative features to generate a set of optimised quantitative features; and d) applying a classification method to the optimised quantitative features to produce a multispectral profile for differentiating the histopathological cause of kidney graft dysfunction in the subject from a plurality of histopathological causes of kidney graft dysfunction.

The invention belongs to the technical field of molecular biomedicine, and particularly relates to a urinary tract epithelial cell marker and application thereof in diagnosis of urinary tract epithelial cell carcinoma. The molecular marker is cytoplasm thyroid hormone binding protein CRYM, and an immunochemical staining experiment proves that the cytoplasm thyroid hormone binding protein CRYM has the potential to serve as a single immunomarker to be used for distinguishing normal urinary tract epithelial cells / reactive hyperplastic urinary tract epithelial cells and urinary tract epithelial cancer cells. Therefore, the kit plays a key identification role in histopathologic diagnosis or urine noninvasive screening of urothelial carcinoma, and provides important technical support for clinical noninvasive diagnosis.

The invention discloses a new application of hyodeoxycholic acid, namely an application of hyodeoxycholic acid in preparation of a medicine for preventing or treating liver injury. A mouse drug-induced liver injury model is established through acetaminophen, ALT, AST, gamma-GT and the like in serum of a mouse given with hyodeoxycholic acid are remarkably reduced, and the liver function is basically recovered; pathological histology shows that the liver form and structure tend to be normal; the levels of inflammatory factors IL-1beta, IL-6 and TNF-alpha in the liver are remarkably reduced, and the inflammatory response of the liver is relieved; meanwhile, the levels of GSH, SOD and the like in liver tissues are improved, MDA accumulation is reduced, and liver oxidative stress is weakened. Therefore, the hyodeoxycholic acid can effectively relieve the APAP-induced drug-induced liver injury, and has great potential in development of liver protection drugs.

A method and a system of diagnostic assistance. The method includes obtaining a plurality of histopathological images of tissue samples. The method includes receiving, by a processing circuitry configured with a pretrained dense convolutional neural network, a histopathological image of the plurality of histopathological images and extracting global features of the histopathological image. The global features are spatial features of the histopathological image. The method includes extracting, by the processing circuitry, local features of the histopathological image. The local features are spectral features. The method includes concatenating, by a concatenation operator, the global features with the local features to obtain concatenated features. The method includes outputting, by a classification layer, a classification of the histopathological image based on the concatenated features.

The application discloses a kind of bone marrow cell few sample classification method, system and electronic equipment, method includes: obtaining bone marrow cell dataset, constructs few sample training set and test set establishes the multi-scale multi-modal few sample classification network model based on text multi-source generation selection;According to the few sample training set, the few sample classification network model is trained, and the trained bone marrow cell classification network model is obtained;The bone marrow cell image of test is input into the bone marrow cell classification network model, and the prediction class of bone marrow cell image is obtained, realizes the bone marrow cell image classification under the condition of few sample training.The present application selects histopathology pre-training model for bone marrow cell classification, and designs text multi-source generation selection module, standardizes the semantic description of each category of bone marrow cell, and further improves the few sample classification accuracy of bone marrow cell, which can be widely applied in the field of computer vision technology.

Diagnosis of prostate cancer often involves invasive measures, such as biopsies, in which tissue is removed and graded by a pathologist. Non-invasive measures, such as multi-parametric MRI, can be used to examine lesions and grade them using the PI-RADS scoring scale; however, achievable image resolution is limited by motion. A new paradigm, magnetic resonance histopathology (MRH), is disclosed, which aims to evaluate tissue texture at sub-millimeter resolution through a fast clinical acquisition process. The ability of MRH to identify cancerous tissue in the prostate through computer simulation analysis is demonstrated, reproducing the MRH measurement process on a set of high-resolution, histology slides annotated by pathologists (2, 4, 6, 8, 10, 12, 14). A dataset of spectral intensities (20) at sub-millimeter wavelengths is created, and a deep learning model (22) trained to classify the spectral data is based on normal or tumor tissue. A set of spatial frequencies is identified, which is used to optimize diagnostic capability under the constraint of limited acquisition time. In addition to single-region classification, the disclosed method and architecture integrate spatial context and local information, the inclusion of which improves model performance and denoises inference results. In addition to algorithms for estimating the physical length scale of lesions identified by the model, the trained model is demonstrated to be applied to unlabeled high-resolution 3D MRI data.

The invention belongs to the technical field of tumor drug research, and particularly relates to application of 2-phenyl oxindole in preparation of a drug for reversing cis-platinum drug resistance or treating tumors. In-vitro experiments and in-vivo experiments prove that the 2-phenyl oxoindole can effectively inhibit proliferation of triple negative breast cancer cells and can remarkably improve the sensitivity of the cells to cis-platinum with a series of concentrations, and pathological staining results of visceral organs and tissues of mice show that the 2-phenyl oxoindole can effectively inhibit proliferation of the triple negative breast cancer cells and remarkably improve the sensitivity of the cells to cis-platinum with a series of concentrations. The 2-phenyl oxoindole does not cause obvious injury to main organs such as liver, kidney and the like.

The application discloses application of calyculostero in preparation of blood sugar reducing drugs, and belongs to the technical field of pharmacological action of calyculostero. Experimental results show that the calyculostero can inhibit the activity of pancreatic alpha-amylase (IC50 is 4.34+ / -1.10 ug / mL) in a dose-dependent manner, reduce postprandial blood sugar, and improve sugar tolerance, reduce fasting blood sugar, improve total cholesterol and triglyceride levels, and reduce histopathological changes of liver, pancreas and kidney in long-term intervention, and has no obvious hepatotoxicity. The calyculostero can be used alone or together with a pharmaceutically acceptable excipient to prepare a pharmaceutical composition, and is used for reducing blood sugar or treating diabetes, and the dosage form includes oral preparations, injections and the like. The application provides a new natural medicine selection for drug treatment of diabetes.

The invention relates to heterobacterium faecalis, in particular to application of heterobacterium faecalis DSM 13633 or a culture solution thereof in preparation of a medicine for preventing or treating diabetic nephropathy. The invention proves that the urine volume of a mouse with diabetic nephropathy can be reduced by the heterobacterium faecalis DSM 13633, and the levels of urinary albumin, urine creatinine and urea nitrogen can be reduced, so that the Allobacter sterilicis can be used for improving the renal function impairment induced by hyperglycemia. Meanwhile, the pathological evaluation of kidney tissue shows that the Allobaculum stericolicis can be used for improving the renal lesion of the hyperglycemia mouse. According to the present invention, with the application of the Allobaculum stericoranis, the mRNA expression level of M1 type macrophage markers (Il6, Il1beta, iNOS) in the diabetic mouse kidney tissue can be reduced, the mRNA expression level of M2 type macrophage markers (Arg1, Il10, CD206) can be increased, and the results show that the Allobaculum stericoranis can alleviate the hyperglycemia induced renal tissue inflammation state;

The invention relates to an application of 7-phenylcarbamoyl heptanoic acid in preparation of antitumor drugs, in particular to a new application of 7-phenylcarbamoyl heptanoic acid in preparation of antitumor drugs, which develops the medicinal value of 7-phenylcarbamoyl heptanoic acid and has high antitumor activity on solid tumors or hematologic tumors. In-vivo experiments show that under an effective dose, the 7-phenylcarbamoyl heptanoic acid does not cause obvious weight loss, weight change of main organs or histopathologic injury of experimental animals, so that the 7-phenylcarbamoyl heptanoic acid has a relatively good treatment window and good safety.

This invention belongs to the field of biomedical technology and discloses a method for constructing and applying a podocyte-specific S1PR1 gene knockout mouse model. Podocyte-specific S1PR1 knockout mice were constructed using the Cre-LoxP system, and then an FSGS model was established via doxorubicin injection. The model was validated using urine, serum, histopathological, and molecular mechanism detection methods. The study found that decreased S1PR1 expression induces podocyte senescence and FSGS progression by downregulating Xab2, leading to abnormal POLR2A splicing and reduced expression. This invention is the first to construct such a model, revealing the regulatory role of the S1PR1-Xab2-POLR2A pathway in podocyte senescence, providing a reliable tool for studying the pathogenesis of FSGS, clarifying the potential of S1PR1 as a therapeutic target, and enabling drug screening for FSGS treatment. It has significant clinical translational value.

Embodiments of the present disclosure leverage hierarchical encoding and self- supervised learning (SSL) objectives to provide pretrained portions of a deep learning network for digital histopathology analysis. Some embodiments of the disclosure leverage different training methods for training different portions of the network. Some embodiments use a DINOv2 objective for pretraining a patch-level encoder and / or for pretraining a region- level encoder. Some embodiments use a contrastive learning objective such as simCLR to pretrain a patch-level encoder but use a different learning objective to pretrain a region-level encoder. These and other aspects of the present disclosure are more fully detailed herein.

The present specification provides a tissue pathology reading support device and a method therefor, which, with respect to an artificial intelligence model, divide, into a plurality of patches, a slide tissue image for learning that indicates a lesion site if a lesion is present, infer the classification of each of the plurality of patches so as to learn patch classification results, integrate the plurality of patches and the patch classification results so as to infer the classification of the reconstructed slide tissue image, thereby learning slide tissue image classification results, use the trained artificial intelligence model so as to infer the classification of each of the plurality of patches, thereby generating patch classification results, and integrate the plurality of patches and the patch classification results so as to infer the classification of the reconstructed slide tissue image, thereby generating slide tissue image classification results.

The application relates to a thymoma histopathological typing method and device based on artificial intelligence, which comprises the following steps: acquiring a thymoma histopathology whole slide image to be typed; inputting the thymoma histopathology whole slide image to be typed into a trained multi-path cross-scale visual Transformer model to obtain a typing result; wherein the cross-scale perception Transformer model is used for case information classification of the thymoma histopathology whole slide image, and the whole slide image Transformer model is used for thymoma typing according to the thymoma histopathology whole slide image after case information classification. The thymoma histopathology whole slide image is comprehensively utilized, the process of simulating the comprehensive observation of a pathology expert on multiple multi-scale local image patches in a histopathology whole slide image to determine a pathology information category and then diagnose a corresponding thymoma typing is effectively simulated, and therefore, the pathology information category and the thymoma typing can be accurately predicted.