158 results about "Whole slide image" patented technology

A deep learning-based virtual HER2 IHC staining method uses a conditional generative adversarial network that is trained to rapidly transform autofluorescence microscopic images of unlabeled / label-free breast tissue sections into bright-field equivalent microscopic images, matching the standard HER2 IHC staining that is chemically performed on the same tissue sections. The efficacy of this staining framework was demonstrated by quantitative analysis of blindly graded HER2 scores of virtually stained and immunohistochemically stained HER2 whole slide images (WSIs). A second quantitative blinded study revealed that the virtually stained HER2 images exhibit a comparable staining quality in the level of nuclear detail, membrane clearness, and absence of staining artifacts with respect to their immunohistochemically stained counterparts. This virtual staining framework bypasses the costly, laborious, and time-consuming IHC staining procedures in laboratory, and can be extended to other types of biomarkers to accelerate the IHC tissue staining and biomedical workflow.

Presented herein are systems and methods for semantic image retrieval. A computing system may identify a first biomedical image. The computing system may apply an image retrieval model to the first biomedical image. The image retrieval model may have a convolution block having a first plurality of parameters to generate a feature map using the first biomedical image. The first plurality of parameters may be transferred from a preliminary model. The image retrieval model may have an encoder having a second plurality of parameters to generate a first hash code for the first biomedical image based on the feature map. The computing system may select. from the plurality of second biomedical images corresponding to a plurality of second hash codes, a subset of second biomedical images using the first hash code. The computing system may provide the subset of second biomedical images identified using the first biomedical image.

This specification discloses systems, methods, and techniques for classifying a grade of cancer represented in a tumor tissue sample. The techniques include obtaining a whole-slide image (WSI) of the tumor tissue sample and partitioning the WSI into a collection of patches. For each patch, (i) a contextualized feature representation of the patch is generated based on intrinsic features of the patch, local dependencies between the patch and a subset of local patches of the WSI, and non-local dependencies between the patch and a subset of non-local patches of the WSI; and (ii) an attention weight is determined for the patch. A WSI-level cancer grade for the tumor tissue sample is predicted based on the contextualized feature representations and the attention weights for the plurality of patches.

The invention relates to a computer-implemented method for assessing a risk of breast cancer recurrence, to a computer program having instructions which when executed by a computing device or system cause the computer device or system to perform the method as well as to a data-processing system comprising means for carrying out the method for assessing a risk of breast cancer recurrence. The method of the invention is for example performed by whole slide image (WSI) processing, wherein the risk of breast cancer recurrence is assessed from a WSI of a tumor tissue.

The present invention discloses a resolution adaptive seamless semantic segmentation method for digital pathology whole-slide images, belonging to the technical field of image segmentation. The method includes the following steps: obtaining a pathological whole-slide image to be processed; performing adaptive indexing on the pathological whole-slide image based on physical resolution information to obtain target image patches; constructing a semantic segmentation model, and training the semantic segmentation model using a mask-based self-supervised learning method based on a dataset with a specified resolution; and performing semantic segmentation on pathological whole-slide images with arbitrary physical resolutions using the target semantic segmentation model. The method of the present invention can generate local fields of view at any resolution level and correctly stitch to produce a high-quality whole-slide panoramic segmentation result.

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.

A laboratory information system (LIS) is linked with a whole slide image (WSI) management system to build a pathology image management system that can efficiently manage and utilize a digitized pathology image. A scan notification notifying that an image of a glass slide is scanned by a scanner is delivered to the LIS from the WSI management system to form a WSI link in the LIS, so that the LIS is linked with the WSI management system. By linking two systems with each other can eliminate the problem of mixing up specimens, for example, and hence, a pathologist can easily grasp the status of a pathology sample for which the pathologist is responsible.

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 machine learning (ML) workflow for virtual staining and computational pathology based on a label-free tissue sample is provided to avoid a laborious and time-consuming procedure of pathologist-based interpretation of formalin-fixed and paraffin-embedded histology. A virtual-staining ML model translates a label-free autofluorescence (AF) whole slide image (WSI) of the tissue sample into a virtual hematoxylin and eosin (H&E) -stained WSI, which is further transformed into a WSI virtually stained with a special stain by a stain-transformation ML model. Each of the ML models can be realized as a U-Frame model. A multiple instance learning (MIL) network with attention-based pooling can be applied to the virtual H&E-stained WSI or AF WSI to provide fast and accurate tumor diagnosis. Furthermore, the attention-based MIL network can be configured as a clustering-constrained-attention multiple instance learning (CLAM) model for providing multiclass tumor subtyping, or even multiclass disease typing, in diagnosis of the tissue sample.

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.

Embodiments of the present systems and methods may provide improved capability to predict the risk of recurrence of ductal carcinoma in situ (DCIS) conditions using whole slide image analysis based on machine learning techniques. For example, in an embodiment, a computer-implemented method for determining treatment of a patient may comprise receiving an image of living tissue of a patient, annotating the entire image into tissue structures, extracting texture features from the annotated image, determining a distribution of the extracted texture features relative to tissue conditions, classifying the patient into a risk group based on the distribution, and treating the patient accordingly based on the risk group.

A machine learning system makes medical predictions based, at least in part, on pathomic features indicating collagen fiber organization extracted from pathology images that include lesions. The pathomic features are extracted from pathology images. The pathology images may be routine clinical images gathered in the course of diagnosis and treatment, such as hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of tissue. The medical predictions may concern, e.g., the diagnosis, prognosis, genotype, or phenotype of a lesion, and may include disease-free survival (DFS) and overall survival (OS) of patients known or suspected of having malignant lesions. Methods for training a machine model to make, and for making, such predictions are also disclosed.

Embodiments herein disclosed relate to computer-implemented method and corresponding systems for providing a trained function (TFA) which function is configured to provide a classification result (CR) for a whole slide image (WSI) depicting tissue according to a plurality of tissue types (HE, CA, OT). Methods and systems are based on generating (S30) intermediate classification results (ICR) by inputting the set (WSI_T) into a first trained function (TF1), selecting (S40) classification results (SCR) from the intermediate classification results (ICR), inputting (S50) image data extracted from the set (WSI_T) corresponding to the selected classification results (SCR) into a second trained function (TF2) so as generate predictive classification results, and adapting (S60) the second trained function (TF2) based on a comparison of the selected classification results (SCR) with the predictive classification results.

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 a breast cancer full-slice image classification method based on example search and multi-example learning. The method comprises the following steps: firstly, extracting a foreground region from a full-slice image and segmenting the foreground region into structured image blocks; and then, extracting deep semantic features of the image blocks by using a feature extractor fusing CNN and Transform, and modeling a spatial relationship between the image blocks by introducing a position-coded MIL aggregator, thereby completing full-image-level feature fusion and classification prediction. After convergence of an MIL aggregator, a pseudo-label image block set is dynamically constructed based on the confidence of image blocks, an example classifier is introduced to train a feature extractor of shared parameters, iterative optimization of the feature extractor is realized, and the discrimination capability and classification performance of a model to a breast cancer lesion area are further improved. In a weak supervision pathological image classification task, the accuracy, robustness and expandability of breast cancer WSI classification are remarkably improved through structural design innovation and optimization strategy cooperation, and the method has important clinical application value and industrial transformation prospect.

A method for on-demand registration of whole slide images (WSIs), comprising receiving at least two digital images, a first digital image of a reference slide and a second digital image on a candidate slide, each at a first magnification level, identifying a first region of interest (ROI) on the first digital image at a target magnification level, registering a portion of the second digital image to a portion of the first digital slide image at the first magnification level to derive a transformation matrix, applying the transformation matrix to the first ROI to identify a second ROI on the second digital image at the first magnification level, mapping the second ROI to a corresponding second ROI on the second digital image at the target magnification level, and registering the corresponding second ROI to the first ROI at the target magnification level.

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.

Compact whole slide image (WSI) representations can be learned using a suitably trained generative model. The generative model is trained on training data using an instance-based training. Using gradient sparsity and quantization losses, the generative model learns to generate compact (e.g., sparse and binary) representations and / or embeddings of whole slide images.

Presented herein are systems, methods, and non-transient computer readable media for determining risk scores using multimodal feature sets. A computing system may identify a first feature set for a first subject at risk of a condition. The first feature set may include (i) a first radiological feature derived from a tomogram of a section associated with the condition within the first subject, (ii) a first histologic feature acquired using a whole slide image of a sample having the condition from the first subject, and (iii) a first genomic feature obtained from gene sequencing of the first subject for genes associated with the condition. The computing system may apply the first feature set to a model. The computing system may determine, from applying the first feature set to the model, a predicted risk score of the condition for the first subject.

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 present disclosure relates to a method for selection of ovarian cancer patients for treatment with PARP inhibitors This involves 1) preparing whole slide images of tissues of ovarian cancer patient to be treated 2) training and validating AI model built on Resnet-50 to recognize morphological features from tiles of hematoxylin and eosin stained whole slide images of tissues featuring the presence of homologous recombination deficiency as annotated by next generation sequencing 3) using the model to extract morphological features from the tiles of hematoxylin and eosin stained whole slide images of tissues of ovarian cancer patients, generating tile level predictions, aggregating tile level predictions to generate a probability score and selecting the patient for treatment with PARP inhibitors 4) administering PARP inhibitors treatment to the patient selected based on probability score reaching a predetermined threshold. Computer systems to implement the method are also disclosed.

The present application relates generally to identifying regions of interest in images, including but not limited to whole slide image region of interest identification, prioritization, de-duplication, and normalization via interpretable rules, nuclear region counting, point set registration, and histogram specification color normalization. This disclosure describes systems and methods for analyzing and extracting regions of interest from images, for example biomedical images depicting a tissue sample from biopsy or ectomy. Techniques directed to quality control estimation, granular classification, and coarse classification of regions of biomedical images are described herein. Using the described techniques, patches of images corresponding to regions of interest can be extracted and analyzed individually or in parallel to determine pixels correspond to features of interest and pixels that do not. Patches that do not include features of interest, or include disqualifying features, can be disqualified from further analysis. Relevant patches can analyzed and stored with various feature parameters.

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.