International Business Machines Corporation

Koninklijke Philips Corporation N.v.

Globalfoundries Inc.

Maria Gabrani

Antonio Foncubierta Rodriguez

Guillaume Jaume

David L DeMaris

Paul T Hurley

Konstantinos Bekas

Andreas Christian Doering

Pushpak Pati

Nathalie Casati

Marie Angelopoulos

Patricia Maria Sagmeister

Govind V Kaigala

Ritwik Ray

Anna Fomitcheva Khartchenko

Aditya Kashyap

Peter W J Staar

Frederick Roberts

Christopher Gagen

Gabriel Cuendet

Virginia Estellers

Ekaterina Volkova

Alan Edward Rosenbluth

Silvio Dragone

Mircea R Gusat

Florian Alexander Auernhammer

Josef S Watts

Kehan Tian

Saeed Reza Bagheri

Thomas Schlipf

David Osmond Melville

Rolf Clauberg

Ronald Peter Luijten

Cornelis Conradus Adrianus Maria Van Zon

Bogdan Prisacari

Elisabeth Francisca Maria Steffens

Wolfgang Emil Denzel

Chiara Marchiori

Ramya Viswanathan

Christian Hentschel

Amr Y Abdo

James M Oberschmidt

Jonathan Bruno Rohrer

Andreas Christian Döring

Reinder Jaap Bril

Nuri Murat Arar

Waleed Farrukh

Erwan Zerhouni

Frank De Morsier

Virginia Estellers Casas

Computer-implemented methods and systems are provided for interpreting a whole-slide image of a tissue specimen. Such a method includes detecting biological entities in a region of interest independently at each magnification level in a whole-slide image. An entity graph is generated for each magnification level, the entity graph comprising nodes, representing respective biological entities detected at that magnification level, interconnected by edges representing interactions between entities. The method also includes, for each region of interest, generating a hierarchical graph, defining a hierarchy of the entity graphs for that region, in which nodes of different entity graphs are interconnected by hierarchical edges representing hierarchical relations between nodes of the entity graphs. The method further comprises supplying the hierarchical graph for the region to an AI system to produce result data corresponding to a medical evaluation of the tissue specimen represented thereby, and outputting the result data for the tissue specimen.

Interpretation of whole-slide images in digital pathology

Embodiments of the invention relate to a computer-implemented method for quantifying a biomarker in a tissue sample of an organism. An image analysis system receives images of a stained tissue sample. Each received digital image depicts the tissue sample region at the end of an exposure interval. The system analyzes the intensity values and exposure intervals of the received digital images for determining the time when the intensity values corresponding to the plurality of exposure intervals ordered according to ascending exposure interval lengths reach a plateau (saturation residence time&#x2014;SRT). The system determines the amount of a biomarker in the tissue sample and/or predicts a tumor stage and/or a treatment recommendation as a function of the SRT.

Biomarker quantification in a tissue sample

A system and process for extracting information from filled form images is described. In one example, the claimed invention first extracts textual information and the hierarchy in a blank form. This information is then used to extract and understand the content of filled forms. In this way, the system does not have to analyze from the beginning each filled form. The system is designed so that it remains as generic as possible. The number of hard-coded rules in the whole pipeline was minimized to offer an adaptive solution able to address the largest number of forms, with various structures and typography. The system is also created to be integrated as a built-in function in a larger pipeline. The form understanding pipeline could be the starting point of any advanced Natural Language Processing application.

Extracting structured information from a document containing filled form images

A system and process for extracting information from filled form images is described. In one example the claimed invention first extracts textual information and the hierarchy in a blank form. This information is then used to extract and understand the content of filled forms. In this way, the system does not have to analyze from the beginning each filled form. The system is designed so that it remains as generic as possible. The number of hard coded rules in the whole pipeline was minimized to offer an adaptive solution able to address the largest number of forms, with various structures and typography. The system is also created to be integrated as a built-in function in a larger pipeline. The form understanding pipeline could be the starting point of any advanced Natural Language Processing application.

Methods and systems are provided to extract information within complex documents, and the extracted information may be compared to identify differences between complex documents or the extracted information may be analyzed with respect to the individual document. Information is extracted from complex documents comprising unstructured data to create a structured data repository, or analytics knowledge base. This database may be utilized to compare concepts that are common to one or more documents, allowing ease of comparison of documents, and identification of information that is different or identification of (same or similar) information that is presented differently in a set of complex documents.

Extraction of information and smart annotation of relevant information within complex documents

Computer-implemented methods are provided for generating a data structure representing tabular information in a scanned image. Such a method can include storing image data representing a scanned image of a table, processing the image data to identify positions of characters and lines in the image, and mapping locations in the image of information cells, each containing a set of the characters, in dependence on said positions. The method can also include, for each cell, determining cell attribute values, dependent on the cell locations, for a predefined set of cell attributes, and supplying the attribute values as inputs to a machine-learning model trained to pre-classify cells as header cells or data cells in dependence on cell attribute values.

Data structure generation for tabular information in scanned images

A method of determining a hierarchy of a blank template using an image of the blank template and using the determined hierarchy for providing labels and field values of text lines of a filled form document.

Method and system for extracting information from an image of a filled form document

The invention relates to the automated determination of the staining quality of an IHC stained biological sample. A plurality of features is extracted from a digital IHC stained tissue image. The features are input into a first classifier configured to identify the extended tissue type of the depicted tissue as a function of the extracted features. An extended tissue type is a tissue type with a defined expression level of the tumor marker. In addition, the extracted features are input into a second classifier configured to identify a contrast level of the depicted tissue as a function of at least some second ones of the extracted features. The contrast level indicates the intensity contrast of pixels of the stained tissue. Then, a staining quality score of the image is computed as a function of the identified extended tissue type and the identified contrast level.

Tissue staining quality determination

The invention relates to a computer-implemented method for automatically extracting data from a digital image comprising a graphical representation of quantitative data. The method comprises: Basic graphical objects are detected and structural primitives determined comprising grouping the basic graphical objects based on geometric relations. A semantic label is assigned to each of the structural primitives. A spatial data region of the graphical representation is determined using the semantic labels of the structural primitives. Quantitative data values are extracted which are represented by structural primitives within the data region which are assigned with first semantic labels identifying the respective structural primitives to represent quantitative data. The extracted quantitative data values are provided in units of pixels according to an image coordinate system. The extracted quantitative data values are transformed from the image coordinate system to a coordinate system of physical units of the quantitative data represented by the graphical representation.

Automatic data extraction from a digital image

A method for extracting information from a molecular pathway diagram may be provided. The method includes providing a molecular pathway diagram, detecting basic graphical structural elements in the diagram resulting in a set of basic objects, detecting a graphical semantic of each of the basic graphical structural elements resulting in a set of structural primitives, and detecting a graphical syntax of the basic graphical structural element relative to each other and to the diagram. Furthermore, the method includes assigning metadata to a plurality of the detected basic graphical structural elements, where the metadata includes basic graphical structural element data, graphical semantic data and graphical syntax data resulting in a set of entities and relationships.

Extract information from molecular pathway diagram

Apparatus, methods, and computer-readable media are provided for simultaneous feature extraction and dictionary learning from heterogeneous tissue images, without the need of prior local labeling. A convolutional autoencoder is adapted and enhanced to jointly learn a feature extraction algorithm and a dictionary of representative atoms. While training the autoencoder an image patch is tiled in sub-patches and only the highest activation value per sub-patch is kept. Thus, only a subset of spatially constrained values per patch is used for reconstruction. The deconvolutional filters are the dictionary elements, and only a deconvolution layer is used for these elements. Embodiments described herein may be provided for use in models for representing local tissue heterogeneity for better disease progression understanding and thus treating, diagnosing, and/or predicting the occurrence (e.g., recurrence) of one or more medical conditions such as, for example, cancer or other types of disease.

Simultaneous feature extraction and dictionary learning using deep learning architectures for characterization of images of heterogeneous tissue samples

Growing community of inventors

Thalwil, Switzerland

Maria Gabrani