67 results about "Whole slide image" patented technology

Methods for multiple instance learning of tissue sample images are described. The methods may comprise, for example, receiving a whole slide image from a needle core biopsy sample from a subject; identifying a tissue region in the whole slide image; selecting a set of image patches from the identified tissue region; resampling the set of image patches at a plurality of image scales to generate a plurality of resampled image patches; generating image representations for the plurality of resampled image patches; extracting feature vectors based on the image representations; providing the feature vectors as input to a trained machine learning model configured to predict a gene alteration state; and outputting the predicted gene alteration state for the needle core biopsy sample for the subject.

The invention discloses a method and system for assisting weak supervision full slide image classification performance improvement in the technical field of computer vision and computational pathology, and the method comprises the steps: obtaining an image block instance set of WSI through a data preprocessing module, and obtaining an instance feature matrix through a pre-training feature extractor; learning features which are related to tasks but possibly contain deviation by using observation branches, and adaptively fusing observation representation and potential causal representation by intervention branches through a causal gate unit so as to correct false correlation; and combining the two-branch classification loss and cross-branch adversarial supervision loss joint optimization model, and finally outputting WSI classification prediction fusing double-branch results. According to the method and the system for assisting weak supervision full slide image classification performance improvement, shortcut learning can be effectively inhibited without explicitly annotating confounding factors, the generalization performance of a model on data outside distribution is remarkably improved, and the method and the system can be flexibly embedded into various mainstream MIL frames as a universal module.

Techniques of automated quality control for digital pathology whole slide images are presented. The techniques include obtaining a thumbnail image derived from a whole slide image of a pathology slide; determining whether the whole slide image includes an artifact in a first class of artifacts by providing the thumbnail image to an electronic neural network trained to detect artifacts in the first class of artifacts by analyzing a plurality of labeled training thumbnail images; generating a tissue mask representing tissue depicted in the thumbnail image; determining whether the whole slide image includes an artifact in a second class of artifacts by performing a comparison using the tissue mask; and providing an indication of whether the whole slide image includes an artifact in the first class of artifacts or an artifact in the second class of artifacts.

The present invention provides a multi-modal model construction method and system for predicting the efficacy of sorafenib in hepatocellular carcinoma. The method comprises: step 1, collecting clinical information of a target patient, and generating a whole slide image; step 2, preprocessing clinical data, and retaining clinical features as input for a multi-modal deep learning model; step 3, preprocessing the whole slide image; step 4, constructing an image model, acquiring patch-level scores of the pathological image on the basis of the preprocessed image and by using different aggregation algorithms, and predicting the score of the whole pathological image to obtain best model features; step 5, constructing a multi-modal model, performing modal fusion on the best model features and the clinical features, and outputting an image-level or patient-level prediction result; and step 6, testing and evaluating the model. The present invention achieves bimodal input of a pathological image and clinical information, fully utilizes the complementarity of the two types of modal data, and thus improves prediction accuracy.

Methods and systems are provided for optimizing the digital scanning of pathology slides in a transportable lab. A computing device-implemented method is described for receiving a plurality of pathology slides in the transportable lab, sorting the plurality of pathology slides based upon pathology slide condition to determine which of a plurality of scanners to utilize, and scanning at least one of the plurality of pathology slides utilizing Whole Slide Imaging or Whole Slide Imaging with Robotic Z-Stacking to generate a digital pathology slide. Transportable systems for scanning pathology slides, as described herein, include a triage stage for analyzing each of the pathology slides for digital scanning, a plurality of first slide imaging apparatuses for Whole Slide Imaging, and a plurality of second slide imaging apparatuses for Whole Slide Imaging with Robotic Z-Stacking.

The invention provides a full-slice image quality automatic control method and system based on a two-stage cascade deep neural network, and relates to the technical field of digital pathology image processing. According to the method, efficient, accurate and extensible automatic quality control is realized through the steps of a two-stage cascade detection architecture, a multi-scale feature fusion mechanism, standardized GeoJSON output and multi-dimensional quality scoring. The core of the method is that priori knowledge of pathology (firstly positioning organization and then checking quality) is converted into strict conditional probability decomposition, and the method is efficiently realized through a deep learning network. The mapping from the human cognitive process to the computational algorithm provides a new methodological enlightenment for the field of medical image analysis. Theoretical analysis and actual tests show that the method is remarkably superior to the prior art in the aspects of calculation efficiency, detection precision, cross-device generalization ability and the like, and has important clinical application value and commercial prospects.

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.

Techniques of automated quality control for digital pathology whole slide images are presented. The techniques include obtaining a thumbnail image derived from a whole slide image of a pathology slide; determining whether the whole slide image includes an artifact in a first class of artifacts by providing the thumbnail image to an electronic neural network trained to detect artifacts in the first class of artifacts by analyzing a plurality of labeled training thumbnail images; generating a tissue mask representing tissue depicted in the thumbnail image; determining whether the whole slide image includes an artifact in a second class of artifacts by performing a comparison using the tissue mask; and providing an indication of whether the whole slide image includes an artifact in the first class of artifacts or an artifact in the second class of artifacts.

The present invention relates to an apparatus, system, and method including a hierarchical deep learning model for analyzing large-scale pathology images in the form of Whole Slide Images (WSI) using a hierarchical deep learning model. More specifically, the invention relates to an apparatus, system, and method including a hierarchical deep learning model that divides a large-scale pathology image, which is a pyramid-shaped whole slide image composed of multiple magnification layers of high-magnification pathology images and low-magnification pathology images, into patches, thereby enabling more accurate analysis by applying the high-magnification pathology images to a segmentation model and generating faster analysis results by applying the low-magnification pathology images to a regression model.

The application discloses a multi-omics pathological analysis system and method for predicting the risk of colorectal liver metastasis, relates to the technical field of biomedical and cancer diagnosis, and comprises a data acquisition module, a data preprocessing module, a cell analysis module, a score construction module, a model construction and training module and a prediction and evaluation module; the application realizes comprehensive and accurate prediction of the risk of colorectal liver metastasis by integrating multi-omics data, including single-cell data sets, spatial transcriptome data, batch RNA-seq data, clinical data and whole slide image WSIs; the cross-dimension data fusion and analysis not only improve the accuracy and reliability of prediction, but also provide a powerful tool for in-depth exploration of the molecular mechanism of tumor occurrence, development and metastasis, especially in the cell analysis module, identification and analysis of the malignant cell subpopulation LMTMCs triggering liver metastasis can reveal cell subtypes and molecular characteristics closely related to liver metastasis, thereby providing a scientific basis for formulating a personalized treatment plan.

The application discloses a kind of framework auxiliary liver cancer tissue whole slide tumor microenvironment analysis methods in the field of artificial intelligence and bioinformatics, which includes the following steps: data collection and pretreatment are carried out to the whole slide image of liver cancer tissue;Using multi-label diagnostic framework assists whole slide image to complete classification task;Using multi-label diagnostic framework assists whole slide image to complete segmentation task.The framework auxiliary liver cancer tissue whole slide tumor microenvironment analysis method is through the multi-label diagnostic framework of deep learning technology to the whole slide image of liver cancer tissue.

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.

A system and method of categorizing protein expression in biological cells may include receiving a Whole Slide Image (WSI) of an Immunohistochemistry (IHC) assay of cells, stained with two or more color-specific markers, of two or more respective proteins, and applying a stain separation algorithm on the WSI image, to obtain two or more single¬ channel marker images. Based on the two or more marker images, embodiments may generate an enhanced color image, representing expression of the two or more proteins in the assay, and prompt a user to assign at least one label to at least one respective location in the enhanced color image. Embodiments may then use the at least one label as supervisory information, to train a machine-learning (ML)-based classification model, to classify at least one cell -representative location according to categories of expression of the at least two proteins.

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.

Various examples of the disclosure pertain to using whole-slide images that depict healthy tissue for a training process for at least one machine-learning algorithm for digital pathology. For instance, an autoencoder neural network can be trained based on the healthy tissue.

One or more example embodiments are methods and corresponding systems for providing a training data set for training a segmentation algorithm for segmenting whole-slide images in digital pathology as well as the use of the training data and corresponding ML segmentation algorithms. For example, a first segmentation of a whole slide image is refined based on an automatically generated annotation which has a higher level of detail than the first segmentation. A second segmentation results, which may be used as a ground truth for training the ML segmentation algorithm on the basis of the whole slide image.

The invention discloses a full-slice image cancer prediction and subtype classification method, system and device, and relates to the technical field of image processing and medical artificial intelligence. Comprising the following steps: preprocessing a full-slice image, cutting the full-slice image into image blocks with position coordinates, and extracting features; reconstructing the feature sequence into a two-dimensional feature map which retains the original spatial topology through a spatial recovery module; scanning and fusing along eight directions including a horizontal direction, a vertical direction and a plurality of diagonal lines by using a hyper-cross scanning module so as to capture multi-direction local space correlation; multi-scale global features are extracted and fused by adopting convolution layers with different expansion rates through a pyramid module; and finally, outputting a prediction result and a subtype label through a customized classifier, and generating a focus attention heat map. Through the architecture of spatial reconstruction-multidirectional scanning-multi-scale fusion, while the linear calculation complexity of O (n) is kept, the small focus recognition capability and classification precision are remarkably improved, and an efficient and reliable technical scheme is provided for digital pathological diagnosis.

A method for processing electronic medical images may include receiving an initial whole slide image of a pathology specimen, receiving information about slide quality aspects to modify, and generating a synthetic whole slide image by applying a machine learning model to modify the received initial whole slide image according to the received information. The pathology specimen may be associated with a patient. The synthetic whole slide image may have a reduced quality as compared to the initial whole slide image.

Systems (600) and methods (S100) for adapting a treatment plan to the characteristics of an individual anatomopathology (e.g. a tumor), and systems, methods and devices for implementing an adaptive treatment workflow (220) that automatically updates (S103) a treatment plan based on whole slide images (WSI) of the target anatomopathology.

The application discloses a kind of based on the generation of antinomy network's tissue pixel label acquisition method and related equipment, comprising: based on the whole slide image of tissue slice under the CK dyeing style generates multiple CK dyeing image blocks and obtains multiple DAB channel images;Based on Otsu method and morphological operation, the rough annotation image of each DAB channel image is obtained;The rough annotation image of each DAB channel image is corrected, and the tissue pixel label of each CK dyeing image block is obtained;CK dyeing image block is converted into target dyeing style image block using generative adversarial network model, and the tissue pixel label of the CK dyeing image block is set as the tissue pixel label of the target dyeing style image block.The application avoids excessive dependence on pathological professional knowledge, reduces the labeling time and effort of pathologists, and can efficiently obtain the tissue pixel label of tissue slice under different dyeing styles.

The invention provides an early prediction method for breast cancer neoadjuvant therapy based on a pathological full-slide image, and belongs to the technical field of breast cancer auxiliary diagnosis and treatment. The method comprises the following steps: firstly, acquiring a breast cancer digital pathological image sample, and performing color normalization to obtain a preprocessed image; then, background removal and block cutting are carried out under the amplification factors of 10X and 40X, and features are extracted by using a pre-training standard model to obtain two groups of vectors; constructing a deep learning model, inputting two groups of vectors, performing multi-scale feature fusion analysis, and outputting a probability value; and finally, on the basis of semi-supervised multi-instance learning, dividing samples into a training set and a verification set in proportion, training the model, adjusting hyper-parameters according to the verification set, and retraining full samples to obtain a final model for prediction. The technical problems that tumor cell microscopic information cannot be mined through existing MRI image analysis, the manual labeling cost of a digital pathology full supervision method is high, and data size difference and tumor surrounding information mining are difficult to consider are solved.

A classification method and system of whole slide images based on learnable feature merging and topology-awareness are disclosed. The classification method comprises: performing image block segmentation on a whole slide image to obtain a plurality of image blocks, and obtaining an initial feature sequence containing two-dimensional spatial coordinates and image block features; processing the initial feature sequence to obtain an assignment matrix for feature soft assignment, and weighting and aggregating the image block features based on the assignment matrix into a plurality of merged features to obtain a merged feature sequence; calculating a spatial distance matrix according to the two-dimensional spatial coordinates, and mapping the spatial distance matrix into a topology-aware spatial bias matrix using the assignment matrix; performing global attention calculation on the merged feature sequence by taking the topology-aware spatial bias matrix as a negative bias term, so that the attention interaction weight decays with the increase of the spatial distance, and predicting the classification result of the whole slide image. The classification method can reduce the computational overhead while maintaining the boundary information and spatial consistency.

The application provides an image processing method, device and equipment and a storage medium. It relates to the technical field of image processing. The method comprises: obtaining a target image; performing feature extraction on the target image based on an image feature extraction module to obtain target image features; the image feature extraction module comprises a sampling unit, a window maintaining unit and a grid maintaining unit connected in sequence; and a self-attention mechanism is applied in the window maintaining unit and the grid maintaining unit. In the method, when performing feature extraction on a whole slide image, local features can be captured by focusing on information such as the shape and texture of cells, and global dependence can be obtained by learning the differences between cells and other cells and microenvironments, so that a decision can be made by combining local and global representations.

A computer-implemented method for classifying a full slice image (WSI). The method comprises the following steps: extracting a plurality of instances from the WSI; determining an instance importance score (IIS) for each instance of the plurality of instances, where the IIS is determined based on a Shapley value score, and where the Shapley value score is based on a contribution of each instance of the plurality of instances; assigning each of the plurality of instances to one of a plurality of dummy pockets based on the determined IIS; and inputting each instance of the plurality of instances assigned to one of the plurality of dummy pockets to a multi-instance learning (MIL) classifier.

The application discloses a hepatocellular carcinoma prognosis evaluation method and system based on cell pixel density, and relates to the technical field of hepatocellular carcinoma prognosis evaluation. The method comprises the following steps: acquiring whole slide imaging and performing image preprocessing to determine a critical value of cell pixel level segmentation result; performing cell pixel density calculation according to the critical value of the cell pixel level segmentation result to determine the CD8+TILs density of a tumor area; performing standardization and average calculation processing on the CD8+TILs density of the tumor area to obtain a critical value of ATLS-8; and performing prognosis evaluation on hepatocellular carcinoma of a patient according to the critical value of ATLS-8. By using the application, the cell density on the whole slide can be accurately quantified, the accuracy of cell density measurement is improved, and the accuracy of prognosis evaluation on hepatocellular carcinoma of a patient is improved. The application can be widely applied to the technical field of hepatocellular carcinoma prognosis evaluation.

The present invention provides a system and method for capturing images during review of a microscope slide. In certain embodiments, such system and method allow for the capture of images and construction of a composited microscope mosaic image within the workflow of the slide reviewer, such as a pathologist reviewing a tissue sample. In certain embodiments, said mosaic images are whole slide images constructed by and capable of being viewed at variable resolutions and magnifications corresponding to the review of the original microscope slide by the slide reviewer.

An apparatus for interacting with one or more digital whole slide images (WSIs) acquired by an imaging device includes a display, a memory, and one or more hardware processors. The memory is configured to store computer-executable instructions. The one or more hardware processors are in communication with the display and the memory. The one or more hardware processors are configured to drive the display using the computer-executable instructions of the memory such that the one or more hardware processors are configured to generate a user interface. The user interface includes an image layer and one or more mask layers overlaying the image layer. The one or more mask layers have a predetermined opacity level. The one or more hardware processors are further configured to automatically adjust the predetermined opacity level as a function of a magnification level of the image layer.

Provided is a method for searching for a whole slide image performed by a computer device, which relate to the field of artificial intelligence. The method includes: cropping a whole slide image into a plurality of tissue images; generating, through an image encoder, image feature vectors respectively corresponding to the plurality of tissue images; clustering the image feature vectors respectively corresponding to the plurality of tissue images, to determine at least one key image from the plurality of tissue images; querying, based on image feature vectors respectively corresponding to the at least one key image, a database to obtain at least one target image package corresponding to the at least one key image; and determining a whole slide image to which at least one candidate tissue image comprised in the at least one target image package respectively belongs as a final search result.

A method of generating a prediction corresponding to a patient includes extracting a plurality of image embeddings from a plurality of image tiles corresponding to a whole slide image of a tissue sample of the patient; clustering the plurality of image embeddings into a plurality of image data groups based on a degree of similarity between the image embeddings; generating a plurality of weighted image embeddings by applying a plurality of first attention modules of the prediction system to the image embeddings of the plurality of image data groups; generating a slide-level image embedding by applying a second attention module of the prediction system to the weighted image embeddings such that the slide-level image embedding inherently includes genomic-based data corresponding to the tissue sample, which is not input to the prediction system; and generating the prediction based on the slide-level image embedding..

Computer-implemented methods and systems for providing a representation of a whole slide image are disclosed, implementing the following steps: - Obtaining a case identifier indicating a digital pathology case to be reviewed by a user within a corresponding diagnostic task of the user in a user interface, wherein the digital pathology case is linked to at least one whole slide image stored in an image database, - Determining conditional information that is relevant to the diagnostic task, based on the case identification, - Generating a representation of the whole slide image for display in a user interface by processing the whole slide image according to the conditional information, - Providing the representation for display in the user interface.