158 results about "Histology" patented technology

The system and method for processing a digital pathology image using a machine learning model that includes a self-supervised hierarchical Vision Transformer (ViT) configured to perform unsupervised clustering with multiple classification tokens. The method includes receiving a digital pathology image that depicts a tissue slice stained with histological dyes. The digital pathology image may be processed to generate a result comprising multiple predicted classifications of individual patches of the digital pathology image. The result is generated by a machine-learning model using a self-supervised hierarchical Vision Transformer (ViT) that may further comprise a multi-head self-attention module configured to predict a crosspatch relevance metric using an attention mechanism for each individual patch in the digital pathology image thereby assigning the individual patches to a cluster based on the crosspatch relevance metrics.

The present disclosure relates to systems and methods for tracking and printing within a histology system. In some embodiments, a system is provided that includes an information reader configured to read identifying data associated with a tissue block, a microtome configured to cut one or more tissue sections from the tissue block, one or more slides for receiving the one or more tissue sections, and a printer configured to receive the identifying data and print, after the one or more tissue sections are cut from the tissue block, one or more labels for the one or more slides, the one or more labels comprising information associating the one more tissue sections on the one or more slides with the tissue block.

A method and system for classifying field of view (FOV) images of histological slides into various categories that include certain stain patterns, artifacts, and / or other features of interest are provided herein. Few-shot learning (e.g., a prototypical network) techniques are used to train a deep convolutional neural network using a small number of training samples for a small number of image classes for classifying stain images belonging to a larger number of image classes.

A tamper for making paraffin blocks for histology may include a pliable tamper head and a handle. The handle may be permanently or removably attached to the tamper by using screws, magnets, or the like. The tamper may be made from a pliable material, such as a silicone rubber, with improved thermal transfer and high latent heat. In use, the tamper may be warmed in advance to a working temperature by placing the tamper on a hot plate of the embedding station or on a dedicated smaller hot plate. Alternatively, the tamper may be heated with an electric resistive element, a thermoelectric device, or an electric induction coil.

A deep learning-based digital staining method and system are disclosed that enables the creation of digitally / virtually-stained microscopic images from label or stain-free samples based on autofluorescence images acquired using a fluorescent microscope. The system and method have particular applicability for the creation of digitally / virtually-stained whole slide images (WSIs) of unlabeled / unstained tissue samples that are analyzes by a histopathologist. The methods bypass the standard histochemical staining process, saving time and cost. This method is based on deep learning, and uses, in one embodiment, a convolutional neural network trained using a generative adversarial network model to transform fluorescence images of an unlabeled sample into an image that is equivalent to the brightfield image of the chemically stained-version of the same sample. This label-free digital staining method eliminates cumbersome and costly histochemical staining procedures and significantly simplifies tissue preparation in pathology and histology fields.

The invention provides a puncture sample detection platform based on a tumor protein targeting probe. According to the puncture sample detection platform, IR-780 is used for marking tumor specific protein in a puncture sample; the improved three-dimensional gel electrophoresis device is used for separating proteins in tissues; the gel processing platform is used for processing and analyzing the separation gel medium; and the automatic diagnosis platform is used for automatically judging benign and malignant conditions of the puncture sample according to the intensity and coherence of the fluorescence signal and circling the contour of the malignant sample. Compared with clinical pathological examination, the method has the advantages that benign and malignant puncture samples are judged by evaluating the protein content of various tumor receptors, and the problem of diagnosis difficulty caused by limited histological information is well solved. Meanwhile, the dependence on visual diagnosis of pathological analysis of the frozen section and experience of pathologists is reduced, and the accuracy and efficiency of pathological tissue diagnosis are effectively improved. The automatic diagnosis platform can eliminate a large number of benign samples and can reduce repeated work of pathologists.

The invention provides a space transcriptomics organization space domain intelligent identification method based on a Graph Transform. The method comprises the following steps: reading a space transcriptomics data file; extracting features in the histological image data by adopting a pre-trained deep learning model; setting a spatial distance threshold value; acquiring spatial position data of each sampling point according to a set spatial distance threshold value, and constructing an adjacent matrix; combining the gene expression data, the adjacent matrix and the histological image features to obtain a normalized feature matrix; performing dimensionality reduction on the normalized feature matrix by adopting PCA; inputting the feature matrix subjected to dimension reduction processing into a feature learning model to obtain a comprehensive feature representation; clustering the obtained feature representations by adopting a Leiden algorithm to obtain a spatial domain classification result; according to the invention, deep fusion of multi-modal information is realized through a Graph Transform architecture, spatial distribution rules and functional characteristics of cells can be captured at the same time, and a systematic solution is provided for analyzing a complex structure of a tissue microenvironment.

Techniques for classifying, using a deep learning model, histopathological whole slide images (WSIs) as comprising images of cancerous or non-cancerous tissue and / or as comprising images of cancerous tissue having a genetic mutation or not having a genetic mutation are described herein. The techniques include at least one processor configured to instantiate a container-based processing architecture to train and / or use the deep learning model to process and classify at least one WSI. In some embodiments, a treatment may be selected and administered based on a classification result obtained from the deep learning model.

The invention provides an improved hard tissue decalcification solution and application thereof, and relates to the technical field of hard tissue decalcification, the improved hard tissue decalcification solution is obtained by mixing EDTA, ammonia water and water, and Ca < 2 + > ions are jointly chelated by the ammonia water and the EDTA in a water environment; the mass volume ratio of the EDTA to the ammonia water to the water is (140 to 280) g to (20 to 400) mL to (1000 to 2000) mL; the pH value of the improved hard tissue decalcification liquid is 6.5-7.5, the decalcification speed is accelerated by accurately controlling the pH value, the decalcification period is shortened by about 50%, it is guaranteed that antigen-antibody combination is not affected after decalcification, mild decalcification is achieved, and a high-quality sample is provided for subsequent histological research.

A system and method for performing virtual birefringence imaging and virtual staining (e.g., Congo red) of label-free human tissue is disclosed to show that a single trained neural network can rapidly transform autofluorescence images of label-free tissue into brightfield and polarized microscopy images, matching their histochemically-stained versions. Blind testing with quantitative metrics and pathologist evaluations on cardiac tissue showed that the virtually stained polarization and brightfield images highlight amyloid patterns in a consistent manner, mitigating challenges due to variations in chemical staining quality and manual imaging processes in the clinical workflow.

There is provided a method of classifying cancer, comprising: feeding an image of a histology slide of a cancer into a machine learning (ML) model, obtaining a score indicative of a probability of a positive status or a negative status of a marker from the ML model, accessing an indication of the positive status or the negative status of the marker obtained by a laboratory test, computing a threshold for determining whether the score generated by the ML model is discordant with respect to the indication according to the laboratory test, in response to the score being greater than a threshold and the negative status of the marker according to the laboratory test, classifying the cancer as a first category, and in response to the score being less than the threshold and the positive status of the marker according to the laboratory test, classifying the cancer as a second category.

Disclosed herein are methods, compositions, and devices for use in diagnosis and treatment of cancer. The methods include sequencing a panel of regions in cell-free nucleic acid molecules and detecting one or more biomarkers that are indicative of a cancer and capability for cancer subtyping.

The invention relates to the technical field of optics, and discloses a visualization method of a biological tissue three-dimensional full-information atlas, which comprises the following steps of: acquiring image data, electron microscope data, mechanical data, protein distribution, omics information and histological staining images of biological tissues by using various biological visualization technologies, and correspondingly processing the acquired data to obtain a three-dimensional full-information atlas of the biological tissues; finally, organization information fusion and digital display are achieved. According to the method, a cross-scale feature correlation algorithm framework is innovatively established, and multi-source heterogeneous data fusion is performed on medical image topological data (CT / MRI), ultrastructure scanning data (SEM / TEM), molecular positioning information (immunofluorescence, immunohistochemistry and enzyme immunoassay), omics maps (space transcriptome / proteome) and high-resolution tissue staining data. The data island dilemma caused by traditional single-mode analysis is broken through, and full-scale visualization from nanoscale molecular distribution to centimeter-level organ tissue structure-function relationship is realized for the first time.

The computer-implemented method according to the present invention provides two different classifications starting from an ultrasound image i.e. a binary benign / malignant classification and a histotype classification based on a segmentation of morphological parameters. Furthermore, a disambiguation algorithm is performed when the two classifications are inconsistent.

A method for predicting a risk of a clinical outcome of a patient, the method comprising: receiving clinical data relating to the patient; generating a histological index based on infrared absorption data collected from a sample of the patient; and generating a pre-determined risk score based on the histological index and the clinical data. The method may be partially or fully automated.

A method of operating a tissue processor for processing tissue samples is provided. The tissue processor includes at least one retort for receiving tissue samples, at least one container for storing a reagent, and at least one sensor arranged for fluid communication with one or both of the at least one container and the at least one retort for measuring a measured purity level of a reagent. The method includes the steps of conducting reagent from the at least one container or the at least one retort to the at least one sensor, automatically measuring, by means of the at least one sensor, a measured purity level of the reagent, checking whether the measured purity level meets a predetermined purity level of the reagent associated with the at least one container, and automatically determining, based on a result of checking, whether the reagent is suitable for processing tissue samples in the tissue processor. A tissue processor for processing tissue samples is also provided. A container is also provided for storing tissue samples for processing in a tissue processor.

1. Name of the designed product: upper sheet scanner. 2. Use of the designed product: the designed product is used for cell scanning (manual upper sheet) of histological specimens. 3. Design points of the designed product: in shape. 4. Picture or photo best indicating the design points: perspective view 1.

This platform is a privacy-preserving, federated learning system designed to integrate whole-slide digital pathology images with matched molecular profiling and clinical metadata for improved diagnosis, subtyping, and prognostic estimation of gynecologic tumors. The architecture comprises local institutional nodes that retain raw patient data while participating in distributed model training coordinated by a central orchestration server. Each local node preprocesses whole-slide images into patch-level tensors, extracts visual embeddings via convolutional backbones, and processes molecular vectors (e.g., somatic mutations, expression summaries, copy-number measures) via a molecular encoder. A multimodal fusion module - implemented as an attention- based transformer - integrates image and molecular embeddings into a unified representation used by multi-task heads for classification (histologic subtype, diagnostic label) and regression (risk score). The federated learning controller aggregates encrypted model updates (FedAvg) and returns improved global weights without exchanging raw data, enabling cross-site generalization while preserving patient privacy. Explainability components generate attention maps and tile-level saliency (Grad-CAM style) linked to molecular features, providing interpretable morpho- molecular correlations to pathologists. The platform supports API integration with PACS / LIMS, conforms to privacy standards via optional differential privacy and secure aggregation layers, and is extensible to additional omics modalities or transfer / fine-tuning workflows for related tumor types. By combining multimodal fusion, federated training, and clinician-facing interpretability, the system accelerates robust, generalizable AI for precision pathology in gynecologic oncology.

The utility model relates to an automatic tool setting device for a wax block of a slicing machine, which belongs to medical laboratory equipment and is applied to the fields of medical clinical pathological histology, cytology, clinical examination, biological research and the like. The wax block automatic tool setting device has the advantages that the displacement sensor is installed in the middle of the side of the wax block chuck below the blade of the blade frame, automatic tool setting of the wax block is achieved through positioning signals and control of the displacement sensor, fingers are prevented from being cut or scratched in the manual tool setting process of the wax block, the accuracy of tool setting of the wax block is improved, and the speed of tool setting of the wax block is increased; and the practicability, flexibility and reliability are improved. Unnecessary manual operation steps are reduced, simplicity and rapidness are achieved, labor and time are saved, and the working efficiency is improved. Therefore, the method has great market prospect and economic value.

Techniques for classifying, using a deep learning model, histopathological whole slide images (WSIs) as comprising images of cancerous or non-cancerous tissue and / or as comprising images of cancerous tissue having a genetic mutation or not having a genetic mutation are described herein. The techniques include at least one processor configured to instantiate a container-based processing architecture to train and / or use the deep learning model to process and classify at least one WSI. In some embodiments, a treatment may be selected and administered based on a classification result obtained from the deep learning model.

The utility model discloses a pathology and histology cytopathy observation device, which relates to the technical field of pathology and histology and comprises a box body, an electron microscope is fixedly mounted at the bottom of the rear side in the box body, and a rotating shaft is rotatably mounted between the top and the bottom of the front side in the box body. A placement box is fixedly mounted below the outer surface of the rotating shaft, the top of the placement box is of an opening structure, a plurality of placement grooves are circumferentially formed in the placement box at equal intervals, and one side of the placement box extends to the position below a lens of the electron microscope; and a driving mechanism is fixedly mounted at the top of the box body. According to the utility model, the glass slides can be automatically replaced, manual one-by-one replacement is not needed, the operation time is reduced, sample pollution is avoided, and the box body can effectively avoid pollution of a microscope lens or foreign matters attached to the surfaces of the glass slides caused by dust or airflow in an external environment, so that the imaging definition is reduced, and normal observation of cytopathy is influenced.

A histologic tissue sample support device (600) includes a tissue cassette (616), a cassette feature (626), and a frame (612). The tissue cassette (616) has at least one side wall (616a) and is coupled to the cassette feature (626). The cassette feature (626) has at least one element to secure, align, orient, bias, and / or provide indicia to identify a tissue sample. The tissue cassette (616) is movably coupled to the frame (612) that has a bottom edge (612f). The tissue cassette (616) and the cassette feature (626) are capable of moving from a first position to a second position with respect to the frame (612) and, in the second position, at least a portion of the cassette feature (626) and at least a portion of the side wall (616a) extend beyond the bottom edge (612f) of the frame (612) for sectioning in the microtome.

Disclosed are systems and methods for an artificial intelligence based pathology platform that can provide prognostic value to clinicians. For example, the platform can predict outcomes related to a cancer, and may include the steps of obtaining a histological sample of a cancer tumor of a patient, determining a feature set for the histological sample by applying a deep learning module trained on a population of histological samples of cancer tumors of the same type as the obtained histological sample of the cancer tumor, and generating an outcome set for the patient by applying a second model to the determined feature set.

There is provided a method for quantifying texture features in histological sample from a tumor sample, comprising:receiving a digital image of the histological sample, thendividing the digital image into a plurality of sub-areas, thenusing a trained machine learning model to predict a presence of at least one biological feature for each of the sub-areas, where a probability for the presence of the biological feature is represented by a value, thenforming a data matrix by arranging the values for the probabilities of the biological features in the same way as the sub-areas are arranged in relation to the digital image, thenapplying image analysis to the data matrix for a set of texture features, to produce a quantification of at least one texture feature.

The invention relates to the technical field of methylation detection site detection, and particularly provides an early gastric cancer lymph node metastasis risk prediction method, system, application and medium, and the method comprises the following steps: obtaining a gastric cancer public data set containing a DNA methylation chip data set and an RNA sequencing data set, and carrying out sample screening, quality control and grouping processing to obtain eight quality control grouping samples; carrying out methylation and RNA difference analysis on the quality control grouped samples to obtain a related gene set of differential methylation sites and differential methylation regions and an RNA differential expression gene set; a gene set of differential methylation sites and an RNA differential expression gene set are integrated and screened to obtain eight target genes. The system comprises a sample acquisition module, a gene analysis module and a gene screening module. Target genes are analyzed and screened on the basis of database biological information, and methylation detection sites for histopathological specimens are screened in combination with lymph node metastasis positive and negative early gastric cancer histological sample verification.

Comprehensive molecular profiling provides a wealth of data concerning the molecular status of patient samples. Such data can be compared to patient response to treatments to identify biomarker signatures that predict response or non-response to such treatments. Here, we used molecular profiling data to identify biomarker signatures (biosignatures) that predict a tumor primary lineage, cancer category or type, organ group and / or histology. The signature may use genomic and transcriptome level information.

The utility model relates to the technical field of animal tissue slicing, and discloses an adjustable animal tissue slicing device which comprises a main body shell, a driving module is arranged on the side wall of the main body shell, a conveying piece is fixedly connected to the inner side wall of the main body shell, and a transverse groove is formed in the conveying piece. On the premise of an automatic cutting mechanism, the slicing precision and uniformity can be improved, and the problem of non-uniform slicing thickness caused by human factors such as hand shaking and non-uniform force application in manual operation is effectively avoided; the thickness of each time of cutting can be accurately controlled, the consistency of the thickness of the slices is ensured, and a highly reliable and repeatable data basis is provided for subsequent histological analysis, pathological diagnosis and cell biology research, so that the accuracy and reliability of experimental results are improved, experimental errors caused by the thickness difference of the slices are reduced, and the experimental efficiency is improved. And scientific researchers can more accurately reveal the microstructure and pathological change characteristics of tissue cells.

A computer-implemented method for processing medical images, the method including receiving one or more of medical images of at least one pathology specimen, the pathology specimen being associated with a patient, wherein the medical image is a stained histology image. The method may further include receiving a stain type associated with the one or more medical images and identifying a color vision deficiency for one or more users. Next the method may include identifying a pixel transformation for the one or more medical images based on the stain type and color vision deficiency of the one or more users. Next the method may include applying a pixel transformation to each pixel within the one or more medical images. Lastly the method may include displaying the transformed one or more medical images to the one or more users.

The present disclosure relates to a system and method for processing a digital pathological image using a machine learning model that includes a self-supervising hierarchical vision Transformer (ViT) configured to perform unsupervised clustering with a plurality of classification markers. The method includes receiving a digital pathological image depicting a tissue section stained with a histological dye. The digital pathology image may be processed to generate a plurality of predicted classification results including individual tiles of the digital pathology image. The result is generated by a machine learning model using a self-supervised hierarchical vision Transformer (ViT), which may further include a multi-head self-attention module configured to predict, for each individual tile in the digital pathology image, a cross-tile correlation metric using an attention mechanism, and to predict, for each individual tile in the digital pathology image, a cross-tile correlation metric based on the predicted cross-tile correlation metric. Thereby assigning the individual tiles to clusters based on the cross-tile correlation metric.