Koninklijke Philips Corporation N.v.

Nuance Communications, Inc.

Koninklijke Philips Electronics N.v.

Philips Intellectual Property & Standards Gmbh

Alexander Fischer

Lothar Spies

Daniel Gagnon

Carsten Meyer

Ralph Brinks

Uma Satya Ranjan

Andrew J Buckler

Bernd Schweizer

Rolf Dieter Bippus

Bart Jacob Bakker

Manoj Narayanan

Andreas Kellner

Marc Busch

Jens-Christoph Georgi

Shivakumar Kunigal Ramaswamy

Volker Stahl

Timo Paulus

Ana Belen Martin Recuero

Mark Christof Wengler

Utpal Kumar

Shuping Xie

Bart Bakker

A medical information processing and storage system includes a medical images database storing medical images and metadata relevant to the medical images. A processor is configured to perform post-acquisition image processing on medical images. A medical images archiver is configured to store a medical image in the medical images database after the medical image has been processed by the processor. The medical images archiver stores the medical image in the database with processing-descriptive metadata that is descriptive of the post-acquisition image processing performed on the medical image by the processor.

Medical workflow systems and methods with process workflow recordation

A system is provided for quantification of medical image data. First image obtaining means () are for obtaining a first image (A). Second image obtaining means () are for obtaining a second image (B). Spatial transformation obtaining means () are for obtaining spatial transformation information representing a correspondence between points in the first image and corresponding points in the second image. Identifying means () are for identifying a first image region (C) in the first image (A). Transforming means () are for transforming the first image region (C) into a corresponding second image region C') in the second image (B) based on the spatial transformation information. Quantification means () are for computing a quantification relating to the second image region (C&#x2032;) by accessing image values of the second image (B) within the second image region (C&#x2032;).

Quantification of medical image data

The invention describes a method and a system for generating training data (D) for an automatic speech recogniser () for operating at a particular first sampling frequency (f), comprising steps of deriving spectral characteristics (S) from audio data (D) sampled at a second frequency (f) lower than the first sampling frequency (f), extending the bandwidth of the spectral characteristics (S) by retrieving bandwidth extending informationfrom a codebook (), and processing the bandwidth extended spectral characteristics (S) to give the required training data (D). Moreover a method and a system () for generating a codebook () for extending the bandwidth of spectral characteristics (S) for audio data (D) sampled at a second sampling frequency (f) to spectral characteristics (S) for a first sampling frequency (f) higher than the second sampling frequency (f) are described.

Method and system for generating training data for an automatic speech recognizer

A method of identifying a myocardial region of interest in cardiac medical image data is disclosed. The method includes identifying myocardial tissue () in first () and second () views of the medical imaging data and constructing a myocardial surface (). In one embodiment, the myocardial surface is modeled as a plurality of elliptical arc segments () and a half ellipsoid.

Method and system for myocardial region of interest definition

An apparatus includes a scanner () and a scanning motion monitor (). A motion modeler () uses data from the scanning motion monitor () and the scanner () to generate a motion model which describes motion of a region of interest of an object. A treatment planner () uses image data from the scanner () to establish a treatment plan for the object. A treatment device, which operates in conjunction with a treatment motion monitor (), uses the motion model to compensate for motion of the object during application of the treatment.

Motion estimation in treatment planning

A radiological imaging method comprises: acquiring radiological lines of response (LOR's) from a subject; grouping the acquired LOR's into time intervals such that each group of LOR's () was acquired during a selected time interval; identifying a region of interest () for each time interval based on LOR's grouped into that time interval; for each time interval, determining a positional characteristic () of the region of interest identified for that time interval based on LOR's grouped into that time interval; for each time interval, spatially adjusting LOR's grouped into that time interval based on the positional characteristic of the region of interest identified for that time interval; and reconstructing at least the spatially adjusted LOR's to generate a motion compensated reconstructed image.

Radiological imaging incorporating local motion monitoring, correction, and assessment

This invention relates to rearranging a cluster map of voxels in an image aiming at the reduction of sub-cluster scatter. The cluster map that includes two or more cluster levels is displayed to the user along with the distribution of the voxels within each respective cluster levels. The aim is to enable the user to evaluate the quality of the cluster map and based on the evaluation to change the distribution of the voxels. Such a change in the distribution will result in an update of the cluster map.

Method of rearranging a cluster map of voxels in an image

A method for use in functional medical imaging includes adaptively partitioning functional imaging data as a function of a spatially varying error model. The functional image data is partitioned according to an optimization strategy. The data may be visualized or used to plan a course of treatment. In one implementation, the image data is partitioned so as to vary its spatial resolution. In another, the number of clusters is varied based on the error model.

Error adaptive functional imaging

A system, apparatus, and method are based on a priori knowledge of the shape of the input function for defining an input region-if-interest (ROI) in pharmacokinetic modeling. Kinetic parameter estimation requires knowledge of tracer input activity and the present invention provides an automatic way to define an ROI for estimation of an input function that takes into account a priori knowledge of the shape of the input function based on an administered dose.

Knowledge-based input region of interest definition for pharmacokinetic modeling

An imaging system () comprises a data device (), which controls radiation data acquisition from a subject positioned in an examination region () for an examination. A rebinning processor () bins the acquired data periodically into a histogram (). A transform () transforms the histogram () into individual independent or uncorrelated components, each component including a signal content and a noise content. A stopping determining device () compares an aspect of at least one selected component to a predetermined threshold (TH) and, based on the comparison, terminates the data acquisition.

Patient scan time optimization for PET/SPECT imaging

The invention relates to a method of controlling function units of a motorcar or of devices () installed in a motorcar, via speech signals, in which acoustic signals occurring in the motorcar, which contain noise signal portions that depend on the operating state and/or operation environment of the motorcar, and speech signal portions, as the case may be, are applied to a speech recognition system () and the speech recognition system () uses acoustic references () which are selected and/or adapted in dependence on detected data of the operating state and/or operation environment. The invention is not restricted to speech control in the domain of motorcars.

Method of controlling devices via speech signals, more particularly, in motorcars

This invention relates to a method of recognizing a speech utterance () available in spelled form, comprising a processing stage in which a corresponding letter sequence () is estimated by means of a letter speech recognition unit () based on Hidden Markov Models, and a second processing stage () in which the estimated result () produced by the first processing stage utilizing a statistical letter sequence model () and a statistical model () for the speech recognition unit () is post-processed, while the dynamic programming method is used during the post-processing. For providing robust and efficient speech recognition procedures for the use of speech signals for system control, a grid structure on which the dynamic programming is based and whose node points are provided for the assignment to accumulated probability values, is converted into a tree structure and that an A* algorithm is used for finding an optimum tree path. Also a speech control device wherein a complete word is input as a control signal and at least part of this word in spelled form is input, while the result of the letter speech recognition is used within the scope of the word speech recognition.

Growing community of inventors

Aachen, Germany

Alexander Fischer