Apple Inc.

International Business Machines Corporation

Other

Yaniv Gur

Tanveer Fathima Syeda-Mahmood

Jay Christopher Capela

Charles J Migos

Alexander Charles Maclean

Roger Rock Rosner

Mehdi Moradi

Christopher Douglas Weeldreyer

Peter Berger

Peter William Rapp

Hongzhi Wang

Matthew Ross Lehrian

David James Beymer

Jacob Grundtvig Refstrup

Mark Ambachtsheer

Markus Hagele

Gary William Gehiere

David M Hall

Christopher Erich Rudolph

Diego Bauducco

Alexander C MacLean

Paul B Elseth

Anup Pillai

Satyananda Kashyap

Simon Antony Ward

Steven J Israelson

Ehsan Dehghan Marvast

Alexandros Karargyris

M Frank Emanuel

Ahmed El Harouni

Joy Tzung-yu Wu

Peter Su

Shafiqul Abedin

Hakan Bulu

Mac Murrett

Guy Talmor

Martin James Murrett

Yufan Guo

Allison M Styer

Chun Lok Wong

Alastair Kenneth Fettes

Alan Eyzaguirre

Ashutosh Jadhav

Colin Compas

Xiang Cao

Mohammadreza Negahdar

Eugene R Siew

Peter G Berger

Mechanisms are provided to implement a machine learning framework that operates to register a plurality of machine learning algorithms used to train machine learning models to perform related tasks, and to index the machine learning algorithms to generate and store a machine learning algorithm metadata model for each machine learning algorithm. The machine learning framework receives a user specification of an analytics pipeline task for which a machine learning model is to be trained, and converts the user specification to machine learning algorithm search criteria used to search the index to identify matching machine learning algorithms having a corresponding machine learning algorithm metadata model that matches the machine learning algorithm search criteria. The machine learning framework outputs information describing the matching machine learning algorithms.

Machine learning model repository management and search engine

A method and system for automatically inferring a subject's body position in a two-dimensional image produced by a medical-imaging system are disclosed. The image is labeled with a body position selected from a semantically meaningful set of candidate positions sequenced in order of their relative locations in a subject's body. A processor performs procedures that each identify a class of image features related to pixel intensity, such as a histogram of gradients, local binary patterns, or Haar-like features. A second set of procedures employs applications of a pretrained convolutional neural network that has learned to recognize features of a specific class of medical images. The results of both types of procedures are then mapped by a pretrained support-vector machine onto candidate image labels, which are mathematically combined into a single, semantically meaningful, label most likely to identify a body position of the subject shown by the image.

Identifying subject matter of a digital image

Providing an infinite or seemingly infinite canvas as a workspace is disclosed. In some embodiments, an ability to add to a displayed canvas and view simultaneously one or more table objects, each of which has associated with it an ability to define the content of a first cell by reference to one or more other cells such that the content of the first cell is updated automatically and without further human intervention if the content of one or more of the one or more other cells is changed, is provided.

Infinite canvas

Mechanisms are provided for automatically annotating input images with bounding region annotations and corresponding anomaly labels. The mechanisms segment an input image to generate a mask corresponding to recognized internal structures of a subject. A template data structure is generated that specifies standardized internal structure zones of the subject. The mechanisms register the mask with the template data structure to generate a template registered mask identifying standardized internal structure zones present within the mask, and generate bounding region annotations for each standardized internal structure zone of the template registered mask. The bounding region annotations are correlated with labels indicating whether or not the bounding region comprises an anomaly in the input image based on an analysis of a received natural language text description of the input image. The bounding region annotations and labels are stored in association with the input image.

Automatic bounding region annotation for localization of abnormalities

Mechanisms are provided to implement an automated medical imaging report generator which receives an input medical image and inputs the input medical image into a machine learning (ML) computer model trained to predict finding labels based on patterns of image features extracted from the medical image. The ML computer model generates a prediction of a finding label applicable to the input medical image in terms of a finding label prediction output vector. Based on the finding label prediction output vector, a lookup operation is performed, in a medical report database of previously processed medical imaging report data structures, to find a matching medical imaging report data structure corresponding to the finding label. An output medical imaging report is generated for the input medical image based on natural language content of the matching medical imaging report data structure.

Automatic generation of medical imaging reports based on fine grained finding labels

Management of collections of medical documents is provided. In various embodiments, search criteria are specified for one or more datastore. Location information for a plurality of medical documents (e.g. images, textual documents, time series data, etc.) is retrieved from the one or more datastore. The location information for the plurality of medical documents is aggregated into a virtual collection. The virtual collection is indexed by metadata of the virtual collection.

Framework for modeling collections and their management

Annotation of large image datasets is provided. In various embodiments, a plurality of medical images is received. At least one collection is formed containing a subset of the plurality of medical images. One or more image from the at least one collection is provided to each of a plurality of remote users. An annotation template is provided to each of the plurality of remote users. Annotations for the one or more image are received from each of the plurality of remote users. The annotations and the plurality of medical images are stored together.

Rapid cross-validated ground truth annotation of large image datasets for image analytics

Workflows for automatic measurement of Doppler is provided. In various embodiments, a plurality of frames of a medical video are read. A mode label indicative of a mode of each of the plurality of frames is determined. At least one of the plurality of frames is provided to a trained feature generator. The at least one of the plurality of frames have the same mode label. At least one feature vector is obtained from the trained feature generator corresponding to the at least one of the plurality of frames. At least one feature vector is provided to a trained classifier. A valve label indicative of a valve is obtained from the trained classifier corresponding to the at least one of the plurality of frames. One or more measurement is extracted indicative of a disease condition from those of the at least one of the plurality of frames matching a predetermined valve label.

Workflow for automatic measurement of doppler pipeline

Assigning a semantically meaningful label to a digital image

This disclosure describes systems, methods, and computer program products for authoring content for digital books. In some implementations, a single graphical user interface (GUI) is presented that allows an author to design a layout for the digital book, including editing text and inserting various types of interactive elements in the text. The GUI functions as both a digital book layout design tool and a word processor to facilitate the building of a digital book. The relative page location of inserted widgets can be determined by a user-selectable anchor point placed within the text. An outline view of the digital book can be created and presented in the GUI based on a hierarchical structure determined by paragraph styles applied to the text. The GUI can provide a hybrid glossary and index page for allowing the author to create and manage a glossary and index for the digital book.

Authoring content for digital books

A mechanism is provided in a data processing system comprising a processor and a memory, the memory comprising instructions that are executed by the processor to specifically configure the processor to implement a medical imaging story board creation engine. The medical imaging story board creation engine executing in the data processing system receives a patient data structure comprising a medical imaging study comprising a plurality of electronic medical images. The medical imaging story board creation engine analyzes the patient data structure to determine a modality of the medical imaging study. The medical imaging story board creation engine determines, based on the determined modality of the medical imaging study, for each electronic image in the medical imaging study, at least one of an image mode or viewpoint. The medical imaging story board creation engine performs a saliency feature extraction operation on the electronic medical images in the medical imaging study based on the image mode or viewpoint of each of the electronic medical images. The medical imaging story board creation engine selects a subset of electronic medical images based on results of the saliency feature extraction. The medical imaging story board creation engine generates and outputs a collection of selected electronic medical images based on the selection of the subset of electronic medical images to form a medical imaging story board.

Automatic creation of imaging story boards from medical imaging studies

Features associated with smart tables are disclosed. In some embodiments, address tabs associated with a table are provided on-demand in response to receiving an indication of interest in the table. In some embodiments, controls for modifying the number of rows and/or columns of a table are provided on-demand when an indication of interest in the table is received. In some embodiments, in response to a passive indication of interest in an address tab associated with a row or column of a table, a set of one or more options associated with the row or column and/or associated table are made available.

Smart tables

Semi-automatic annotation of medical images is provided. In various embodiments, a classifier is applied to each of a first plurality of medical images to generate a label and an associated confidence value for each of the first plurality of medical images. The classifier is pre-trained using a manually labeled set of medical images. Those of the first plurality of medical images having an associated confidence value below a predetermined threshold are selected. The selected medical images are provided to a user. Updated labels are received from the user for the selected medical images. The classifier is retrained using the first plurality of medical images, with the updated labels for the selected medical images and the generated labels for medical images not selected.

Iterative semi-automatic annotation for workload reduction in medical image labeling

Growing community of inventors

Pittsburgh, PA, United States of America

Yaniv Gur