34 results about "Whole slide image" patented technology

A computer implemented method of generating at least one shape of a region of interest in a digital image is provided. The method includes obtaining, by an image processing engine, access to a digital tissue image of a biological sample; tiling, by the image processing engine, the digital tissue image into a collection of image patches; obtaining, by the image processing engine, a plurality of features from each patch in the collection of image patches, the plurality of features defining a patch feature vector in a multidimensional feature space including the plurality of features as dimensions; determining, by the image processing engine, a user selection of a user selected subset of patches in the collection of image patches; classifying, by applying a trained classifier to patch vectors of other patches in the collection of patches, the other patches as belonging or not belonging to a same class of interest as the user selected subset of patches; and identifying one or more regions of interest based at least in part on the results of the classifying.

A system and method for improved viewing and navigation of large digital images, such as whole slide images used in microscopy. The system and method displays the digital image along with movable navigation and field of view boxes that enable a viewer to pan the digital image in an accurate manner, and also performs automatic absolute reorientation of the digital image and automatic relative reorientation of subsequent digital images in relation to the first digital image.

The invention discloses a whole slide digital pathological image processing and analysis method, and belongs to the field of the whole slide digital pathological image processing and analysis optimization method. The method comprises the steps that step one, a whole slide image (WSI) is segmented into multiple areas, and each area is analyzed; and step two, objects near the boundary of the areas are spliced. The disadvantages of the existing histopathological analysis software can only browse the whole slide digital image and cannot realize analysis or seamless splicing of the whole slide image and is low in efficiency, long in time consumption and blurred in image can be overcome. The main purpose of the method is to process whole slide digital pathological image analysis, segment the whole slide image into multiple areas with the help of the computer and the fine algorithm and automatically perform high-precision multi-vision seamless splicing and processing so that the analysis time can be shortened and the analysis precision can be enhanced, and the high-quality visual data can be acquired to be applied to various fields of pathological histology.

The invention is made out of methods for the development of Deep Neural Networks for cell detection and quantification in Whole Slide Images (WSI):1. Method to create generic cell detector that detects the centers and contours of all cells in a WSI.2. Method to create algorithms to detect cells of specific categories and that can classify between various types of cells of different categories.3. Method for efficient cell annotation with online learning.4. Method for efficient cell annotation with active learning.5. Method for efficient cell annotation with online learning and data balancing.6. Method for auto annotation of cells7. Cell Detection Studio: a method to create an AI based system that provides pathologists with a semi-automatic tool to create new algorithms aiming to find cells of specific categories in WSI digitally scanned from histological specimen

Using multiple imaging modes in whole slide image screening is potentially useful to reduce false positives. To use multiple imaging modes, a method for locating anomalies on a medical sample from an image thereof uses an anomaly-detection process that comprises using plural base classifiers individually to classify an object-of-interest suspected to be an anomaly. Each base classifier respectively extracts features of the object-of-interest and generates, according to the extracted features, a score indicating a likelihood of the object-of-interest being anomalous. The anomaly-detection process further comprises using an aggregate classifier to combine the scores generated by the base classifiers to determine whether the object-of-interest is the anomaly. The aggregate classifier determines a dependability measure for each base classifier according to setting-based variables of a setting under which the sample and the image are obtained, and then selectively combines the scores of the base classifiers according to the dependability measures.

A digital pathology system and an associated method and computer program product provide a quantitative analysis of entire tissue slides as well as intuitive, effective, fast, and precise quantification of biomarker expressions across relevant areas of the entire tissue slides. The digital pathology system enables a novel workflow that allows the user to efficiently outline clinically relevant morphology in its entirety, including solid tumor areas. Quantitative analysis results are then efficiently and intuitively provided to the user for all tissue content (i.e., millions of cells) within seconds. This efficiency is made possible by a pre-computation step that computes and stores image analysis results for later retrieval. Visualizing vast amount of data effectively is another componentof the system that provides information and confidence to the user about the biomarker expression levels.

A fully automated method for detecting and measuring a target of interest such as vasculature, capable of processing whole slide images and extracting large number of targets of interest per slide. The method includes the steps of: (a) obtaining a digital image of a tissue specimen; (b) using a first set of mathematical algorithms based on objectively-defined criteria to isolate the one or more targets of interest from the slide, thereby detecting the one or more targets of interest; and (c) using a second set of mathematical algorithms based on objectively-defined criteria to construct boundaries around the detected targets of interest and obtain quantitative attributes of these one or more targets throughout the slide, thereby measuring the one or more targets.

Pathologists are adopting digital pathology for diagnosis, by using whole slide images (WSIs). Explainable Al (xAI) is a new approach to Al that can reveal underlying reasons for its results. As such, xAI can promote the safety, reliability, and accountability of machine learning for critical tasks such as pathology diagnosis. HistoMapr provides intelligent xAI guides for pathologists to improve the efficiency and accuracy of pathological diagnoses. HistoMapr can previews entire pathology cases' WSIs, identifies key diagnostic regions of interest (ROIs), determines one or more conditions associated with each ROI, provisionally labels each ROI with the identified conditions, and can triages them. The ROIs are presented to the pathologist in an interactive, explainable fashion for rapid interpretation. The pathologist can be in control and can access xAI analysis via a why interface. HistoMapr can track the pathologist's decisions and assemble a pathology report by using suggested, standardized terminology.

A computer implemented method of generating at least one shape of a region of interest in a digital image is provided. The method includes obtaining, by an image processing engine, access to a digital tissue image of a biological sample; tiling, by the image processing engine, the digital tissue image into a collection of image patches; obtaining, by the image processing engine, a plurality of features from each patch in the collection of image patches, the plurality of features defining a patch feature vector in a multidimensional feature space including the plurality of features as dimensions; determining, by the image processing engine, a user selection of a user selected subset of patches in the collection of image patches; classifying, by applying a trained classifier to patch vectors of other patches in the collection of patches, the other patches as belonging or not belonging to a same class of interest as the user selected subset of patches; and identifying one or more regions of interest based at least in part on the results of the classifying.

The present techniques include methods and systems for finding correspondences between tissue spots in tissue microarray serial sections belonging to the same recipient block. The present techniques may also be used to relate individual tissue cores to clinical information. Using either a whole slide image or the relative x-y coordinates of the tissue spots on the slide, individual tissue spots in different tissue microarrays may be linked to one another and their clinical information.

Using multiple imaging modes in whole slide image screening is potentially useful to reduce false positives. To use multiple imaging modes, a method for locating anomalies on a medical sample from an image thereof uses an anomaly-detection process that comprises using plural base classifiers individually to classify an object-of-interest suspected to be an anomaly. Each base classifier respectively extracts features of the object-of-interest and generates, according to the extracted features, a score indicating a likelihood of the object-of-interest being anomalous. The anomaly-detection process further comprises using an aggregate classifier to combine the scores generated by the base classifiers to determine whether the object-of-interest is the anomaly. The aggregate classifier determines a dependability measure for each base classifier according to setting-based variables of a setting under which the sample and the image are obtained, and then selectively combines the scores of the base classifiers according to the dependability measures.

A system and method for improved viewing and navigation of large digital images, such as whole slide images used in microscopy. The system and method displays the digital image along with movable navigation and field of view boxes that enable a viewer to pan the digital image in an accurate manner, and also performs automatic absolute reorientation of the digital image and automatic relative reorientation of subsequent digital images in relation to the first digital image.

Cancer can be an aggressive disease. It is critical to determine the most effective patient-specific treatment quickly. Exemplary embodiments use a data-driven approach to extracting tumor information from data obtain from Whole Slide Image that is uploaded through an interface. Exemplary embodiments generate the following information about a tumor from a biopsy slide using neural networks: annotated areas of relevant tissues, molecular subtype, and expression status of an important gene and include three steps: the segmentation of tumor features; prediction of molecular subtype; and prediction of gene methylation status from a WSI.

Advantageous instruments, assemblies and methods are provided for undertaking imaging techniques (e.g., microscopic imaging techniques). The present disclosure provides improved imaging techniques, equipment and systems. More particularly, the present disclosure provides advantageous microscopy / imaging assemblies with rapid sample auto-focusing (e.g., microscopy / imaging assemblies having instant focusing for rapid sample imaging with auto-focusing). The present disclosure provides for high-throughput whole slide imaging with instant focal plane detection. A whole slide imaging platform / assembly that uses instant focusing systems / methods for high-speed sample autofocusing is provided. Such exemplary platforms / assemblies can be used for digital pathology or the like, and can provide improved, faster and cheaper diagnosis / prognosis of ailments / diseases. At least two exemplary rapid-focus systems for whole slide imaging are provided, a first system including two pinhole-modulated cameras mounted on the eyepiece ports of a microscope platform / assembly, and a second system including one pinhole-modulated camera mounted on the epi-illumination arm for auto-focusing.

Glioblastoma multiforme (GBM) is the most aggressive type of brain cancer. It is critical to determine the most effective patient-specific treatment quickly. Exemplary embodiments use a data-driven approach to extracting brain tumor information from data obtain from Whole Slide Image that is uploaded through an interface. Exemplary embodiments generate the following information about a glioblastoma tumor from a brain biopsy slide using neural networks: annotated areas of relevant tissues, molecular subtype, and expression status of an important gene and include three steps: the segmentation of tumor features; prediction of molecular subtype; and prediction of gene methylation status from a WSI.

Methods, systems, and apparatuses for automatically identifying glandular regions and tubule regions in a breast tissue sample are provided. An image of breast tissue is analyzed to detect nuclei and lumen candidates, identify tumor nuclei and true lumen from the candidates, and group tumor nuclei with neighboring tumor nuclei and lumina to define tubule glandular regions and non-tubule glandular regions of the image. Learnt supervised classifiers, such as random forest classifiers, can be applied to identify and classify the tumor nuclei and true lumina. Graph-cut methods can be applied to group the tumor nuclei and lumina and to define the tubule glandular regions and non-tubule glandular regions. The analysis can be applied to whole slide images and can resolve tubule areas with multiple layers of nuclei.

The present disclosure includes systems and methods for capture a whole slide image of a sample. In exemplary embodiments, a camera is configured to capture a digital image of a sample. The system captures a bright field image of the sample, and captures a digital image of the sample illuminated from a first incident angle at a first wavelength and a second incident angle at a second wavelength. The system can determine whether the sample is defocused based on the transitional shift between a first wavelength channel and a second wavelength channel of the captured digital image. The system can determine the defocus distance based on the transitional shift and autofocus using the defocus distance such the bright field image is in focus.

The invention discloses a computer implemented method capable of “translating” a request from a proprietary high-resolution image viewer made in terms of level, row, and column into a DICOM valid request made in terms of DICOM instance and DICOM frame number.

The invention provides an auxiliary diagnosis method for cervical histopathology based on an attention mechanism, which comprises reducing the whole glass slide image of cervical histopathology according to the proportion r to obtain a low-resolution image; building and initializing an attention module and a classification module; The rate image is input into the attention module, and the attention score is calculated; the position of the pixel with high attention score in the image is obtained, and the set size k blocks are intercepted; the small block is input into the training classification module, and the features of the small block with high score are extracted , get the feature vector, train the support vector machine classifier, input the trained support vector machine classifier, and realize the classification. The diagnostic efficiency and accuracy of the original method were improved. The lesion area in the positive cervical histopathological full-slide image is located to avoid the interference of the negative part in the positive cervical histopathological full-slide image to the classification model. Using attention mechanism to detect suspicious lesions in cervical histopathological whole slide images.