Leland Stanford Junior University

General Electric Company

Ge Medical Systems Information Technologies Gmbh

Christopher Frederick Beaulieu

David Seungwon Paik

Sandy A Napel

Denny Wingchung Lau

Vijaykalyan Yeluri

Yaseen Samara

Salih Burak Gokturk

Carlo Tomasi

Steven P Roehm

Perry S Frederick

Prakash Parayll Mathew

Garry Evan Gold

Raghav Raman

Frank Owen

Robert John Herfkens

Padmavathi Sundaram

Richard Allen Barth

Acar Burak

Afra J Zomorodlan

William Murray Stoval, Iii

Improved surface feature recognition in CT images is provided by extracting a triangulated mesh representation of the surface of interest. Shape operators are computed at each vertex of the mesh from finite differences of vertex normals. The shape operators at each vertex are smoothed according to an iterative weighted averaging procedure. Principal curvatures at each vertex are computed from the smoothed shape operators. Vertices are marked as maxima and/or minima according to the signs of the principal curvatures. Vertices marked as having the same feature type are clustered together by adjacency on the mesh to provide candidate patches. Feature scores are computed for each candidate patch and the scores are provided as output to a user or for further processing.

Polyp detection using smoothed shape operators

Certain embodiments of the present invention provide a system and method for image registration and display of relevant information. The method includes identifying one or more anatomical parts in an acquired image, mapping the acquired image to a reference image based on the one or more anatomical parts, storing anatomy information in relation to the acquired image, and displaying the acquired image based on the anatomy information. The method may also include controlling the displaying of the acquired image based on a voice command related to the anatomy information. Anatomy information may be displayed with the acquired image. Anatomy information may include clinical information, reference information, disease process information, a related image, and/or drug interaction information, for example. The acquired image may be displayed according to a display setting, such as a window level setting and/or other display setting, based on the anatomy information.

System and method for anatomy labeling on a PACS

A detection and classification method of a shape in a medical image is provided. It is based on generating a plurality of 2-D sections through a 3-D volume in the medical image. In general, there are two steps. The first step is feature estimation to generate shape signatures for candidate volumes containing candidate shapes. The feature estimation method computes descriptors of objects or of their images. The second general step involves classification of these shape signatures for diagnosis. A classifier contains, builds and/or trains a database of descriptors for previously seen shapes, and then maps descriptors of novel images to categories corresponding to previously seen shapes or classes of shapes.

Three-dimensional pattern recognition method to detect shapes in medical images

A technique is provided for generating scout or navigational images based upon a series of related images. The related images are analyzed to compute pixels of scout images, such as by determining a characteristic of aligned pixels of each of the related images. The scout or navigational images are then projections of the related images and individual rows or columns of the scout images correspond to individual images of the related set. One or more of the related images may then be accessed by review of the scout image or images. The scout images may be referred to in their own right for an overview of features of interest and may be modified by a user. The technique provides for efficient time management by allowing specific images to be identified in large image series, and facilitates intelligent use of bandwidth for accessing specific images in a viewer workstation.

Image data navigation method and apparatus

Growing community of inventors

Los Altos, CA, United States of America

Christopher Frederick Beaulieu