Koninklijke Philips Corporation N.v.

Georg Rose

Jens Wiegert

Christoph Herrmann

Juergen Weese

Joerg Bredno

Alexandra Groth

Thomas Netsch

Michael Overdick

Rainer Pietig

Christoph Loef

Kai Eck

Sabine Mollus

Matthias Simon

Rainer Kiewitt

Guenter Zeitler

Carolina Ribbing

Hermann Schomberg

Jürgen Weese

Christoph Neukirchen

Matthias Bertram

Juergen Te Vrugt

Olaf Wischhusen

Oliver Muelhens

Astrid Lewalter

Joseph Hubertus Eggen

The invention relates to an apparatus and a method for the reconstruction of time-dependent cross-sectional images and may be applied for example in perfusion imaging in the vessel system () of a patient. According to the method, projections pare generated from a number M of different directions dand at different times t. Moreover, the time-dependent intensity function I(x,t) of the reconstructed volume is approximated by a predetermined model function I*((x),t), wherein the unknown parameter vector(x) is estimated for each voxel x. This estimation may be done using the update functions of known reconstruction algorithms like ART for at least N projections pin each iteration step.

Apparatus and method for the processing of perfusion images

Adaptively controlling an imaging system () includes constructing model feature characteristics () of a process over time, determining parameters and commands () for controlling the imaging system for each state of the process, performing data acquisition () for the process, extracting current features () of the process from the acquired data, matching () the current features () with the model feature characteristics () to determine a state of the process (), and controlling the data acquisition based on the state of the process to produce optimized data.

Utilizing physiological models to control functional acquisitions

Systems and methods for data acquisition in computed tomography (CT) applications are provided. The systems and methods are particularly adapted for scanning and acquiring/processing data in connection with high-power cone-beam CT applications. The electron beam is moved/scanned along the anode surface to multiple focal positions. Data acquisition for a full projection at one focus position and one view angle is achieved by activating each focus position multiple times during the data acquisition for one angle of the gantry. The detector array and associated data processing system are adapted to rapidly switch between the different focus positions during the acquisitions for one view angle and to collect all data belonging to the same projection into the same data set. Adaptive electron optics are utilized to move/scan the electron beam along the anode surface to the various focus positions. Alternatively, a plurality of cathodes may be provided for respective focus positions and the system may support fast switching therebetween to achieve desirably short spot times. The disclosed CT system permits greater power densities without risk of heat damage to the anode and effectively increases the track velocity of the electron beam on the anode surface. The CT system and associated data acquisition methods have particular utility in CT applications requiring increased time resolution and/or spatial resolution, e.g., cardiac CT applications.

Systems and methods for scanning and data acquisition in computed tomography (CT) applications

A 3D image of a region of an object is computed from truncated cone beam projection data acquired with an x-ray device and a prior CT image representing a larger region of the object. The truncated projection data are extrapolated to derive pseudoprojection data associated with projection directions outside the detector, and an intermediate CT image is reconstructed based on the truncated projection data completed with the pseudoprojection data. The prior CT image is then registered with the intermediate CT image. Forward projection data associated with projection directions outside the detector are computed from the truncated projection data and the registered prior CT image. The 3D image is finally reconstructed based on the truncated projection data completed with the forward projection data.

Cone beam CT apparatus using truncated projections and a previously acquired 3D CT image

An automatic dialog system for spoken inquiries into a database entry which contains several components available for inquiry, wherein speech recognition of a spoken utterance for inquiring into the database entry is supported by a language model which was prepared before a start of the dialog to which the spoken utterance belongs and which models a relative frequency of correlated occurrence of the components of the database entry provided for the inquiry in the spoken utterance of the dialog.

Automatic dialog system with database language model

The invention relates to an X-ray detector () with an array () of sensor elements (), wherein each row (i) of sensor elements is connected via an addressing line to an addressing unit (), and wherein each column j) of sensor elements is connected via a read-out line to a read-out unit (). In the read-out unit (), sensor signals are preprocessed, for example amplified by amplifiers (). The detector further comprises a control unit () which is adapted to set the gains of said amplifiers () for each column (j) and each row (i) individually. The values of the gains may particularly be derived from a priori knowledge, from previous images of the object, or from the image signals of rows that have already been read out.

X-ray examination apparatus and radiation detector

A method of automatic recognition of company names in speech utterances includes generating at least one word sequence hypothesis by a speech recognizer from a speech utterance consisting of one or more words, comparing the word sequence hypothesis with the entries representing company names stored in a database, and selecting, in dependence on the result of the comparison, one company name as a recognition result.

Automatic recognition of company names in speech utterances

Provided is a method of training an automatic speech recognizer, said speech recognizer using acoustic models and/or speech models, wherein speech data is collected during a training phase and used to improve the acoustic models, said method comprising: during the training phase, providing speech utterances that are predefined to a user by means of a game, wherein the game has predefined rules to enable a user to provide certain utterances; and providing the utterances by the user for training the speech recognizer.

Method of training an automatic speech recognizer

Growing community of inventors

Duesseldorf, Germany

Georg Rose