Siemens Healthcare Gmbh

Siemens Aktiengesellschaft

Andreas Krauss

Terrence Chen

Vivek Kumar Singh

Kai Ma

Birgi Tamersoy

Rainer Raupach

Andreas Pancke

Ilka Redmann

Andreas Wimmer

Brian Teixeira

Thomas Driehorn

Jiangping Wang

Aron-Ernst Musiol

Wolfgang Röhl

Shaohua Kevin Zhou

Bernhard Schmidt

Yao-Jen Chang

Roland Barthel

Mingqing Chen

Gerhard Lechsel

Michael Stehle

Yifan Wu

Stephan Arens

Niklas Rehfeld

Klaus Neidhardt

The application relates to a power switch for breaking an electrical circuit when current and/or current time span threshold values are exceeded, including an energy converter, which on the primary side is connected to the electrical circuit, and on the secondary side provides an energy supply for at least one control unit of the power switch. A choke is connected between the secondary-side output of the energy converter and the control unit of the power switch.

Circuit breaker

A method for controlling a scanner comprises: sensing an outer surface of a body of a subject to collect body surface data, using machine learning to predict a surface of an internal organ of the subject based on the body surface data, and controlling the scanner based on the predicted surface of the internal organ.

Method for controlling scanner by estimating patient internal anatomical structures from surface data using body-surface and organ-surface latent variables

A method is described for controlling a tube current for acquiring at least one X-ray image. The method includes performing a preview acquisition of the region under examination; determining a three-dimensionally modulated X-ray attenuation of the region based upon the preview acquisition; determining initial tube-current profiles based upon the X-ray attenuation; defining a tolerance band for subsequent real-time modification of tube currents, a maximum permitted tube-current profile being determined for which an X-ray tube of the X-ray imaging apparatus does not overheat; determining an expected value and a maximum value of a potential patient dose based upon the initial tube-current profiles and the tolerance band; measuring an actual X-ray attenuation during acquisition of the at least one X-ray image; determining adjusted tube-current profiles based upon the actual X-ray attenuation and the initial tube-current profiles; and adjusting the tube current in accordance with the adjusted tube-current profiles determined.

Automated determination of an X-ray tube-current profile

For topogram predication from surface data, a sensor captures the outside surface of a patient. A generative adversarial network (GAN) generates the topogram representing an interior organ based on the outside surface of the patient. To further adapt to specific patients, internal landmarks are used in the topogram prediction. The topogram generated by one generator of the GAN may be altered based on landmarks generated by another generator.

Topogram prediction from surface data in medical imaging

A method is for determining a patient weight and/or a body mass index of a patient. The method includes acquiring image data containing depth information of the patient; generating a surface model of the patient based upon the image data acquired; determining density information or X-ray attenuation information of at least part of the patient; and determining at least one of the total patient weight and the body mass index of the patient using the surface model generated and the density information or X-ray attenuation information determined.

Method and apparatus for determining a patient weight and/or a body mass index

Machine learning is used to train a network to predict the location of an internal body marker from surface data. A depth image or other image of the surface of the patient is used to determine the locations of anatomical landmarks. The training may use a loss function that includes a term to limit failure to predict a landmark and/or off-centering of the landmark. The landmarks may then be used to configure medical scanning and/or for diagnosis.

Internal body marker prediction from surface data in medical imaging

A system and method includes operation of a generation network to generate first generated computed tomography data based on a first instance of surface data, determination of a generation loss based on the first generated computed tomography data and on a first instance of computed tomography data which corresponds to the first instance of surface data, operation of a discriminator network to discriminate between the first generated computed tomography data and the first instance of computed tomography data, determination of a discriminator loss based on the discrimination between the first generated computed tomography data and the first instance of computed tomography data, determination of discriminator gradients of the discriminator network based on the discriminator loss, and updating of weights of the generation network based on the generation loss and the discriminator gradients.

System for predicting computed tomography data from surface data

In scan data retrieval, a mesh is fit () to surface data of a current patient, such as data from an optical or depth sensor (). Meshes are also fit () to medical scan data, such as fitting () to skin surface segments of computed tomography data. The meshes or parameters derived from the meshes may be more efficiently compared () to identify () a previous patient with similar body shape and/or size. The scan configuration () for that patient, or that patient as altered to account for differences from the current patient, is used. In some embodiments, the parameter vector used for searching () includes principle component analysis coefficients. In further embodiments, the principle component analysis coefficients may be projected to a more discriminative space using metric learning.

Scan data retrieval with depth sensor data

According to an embodiment of the application, a method is provided for selecting an algorithm for correcting at least one image artifact in an image data record acquired by a medical imaging system and representing at least one region of interest of a subject under examination. The method includes identifying from the image data record at least one object element causing the image artifact and lying inside the region of interest of the subject under examination; determining from the image data record at least one characteristic describing the object element; determining an artifact correction algorithm on the basis of the at least one characteristic; and applying the artifact correction algorithm to the image data record. An embodiment of the application also provides a corresponding data processing facility and a medical imaging system.

Selection method for an artifact correction algorithm, data processing facility for performing the method, and medical imaging system

A method for determining a tube current profile for the recording of at least one X-ray image of body region of a patient with an X-ray image recording device, a corresponding computer program, a machine-readable data carrier and an X-ray image recording device are disclosed. The method includes acquisition of an image recorded via an optical sensor wherein the image has a field of view including at least the body region of the patient to be depicted by way of an X-ray image; determination of at least one piece of patient-specific, body-related information for the patient from the image; determination of an X-ray attenuation distribution of the patient at least for the body region to be depicted by way of an X-ray image with reference to the at least one piece of patient-specific, body-related information; and determination of the tube current profile with reference to the X-ray attenuation distribution determined.

Method for determining an X-ray tube current profile, computer program, data carrier and X-ray image recording device

A switch is disclosed for power distribution, in particular a circuit breaker and compact switch, which automatically interrupts the electric currents flowing through the switch in a polyphase electrical power supply system when a tripping situation occurs. In at least one embodiment, the switch includes switching contacts which are provided for each phase and can be opened via a switching shaft; an electronic release which automatically initiates the opening of the switching contacts via the switching shaft; electrical power converters, which in each case take the electrical power which is required for the electrical power supply for the release from the currents for the individual phases; instrument transformers which convert the currents in each of the individual phases to a measurement signal; an electronic circuit, in particular in the form of a microprocessor, for assessment of the current values which correspond to the measurement signals, wherein the occurrence of the tripping situation is in each case identified on the basis of the assessment. In order to improve the functional reliability of the switch, in at least one embodiment it is proposed that the currents emitted from the power converters are additionally recorded and that the electronic circuit carries out a plausibility comparison on the basis of the recorded current of the power converters and of the instrument transformers, and generates a warning signal in the event of non-plausibility.

A method is disclosed for controlling an electronic overcurrent trip for low-voltage circuit breakers. According to the method, digitized signals for the electricity values are generated and evaluated, and a tripping device providing short-circuit protection is activated when an overcurrent event is assumed to take place based on the evaluation. According to the method, signals whose electricity value does not lie between the electricity values of the previous signal and the subsequent signal, or whose electricity value does not correspond to the electricity values of the previous signal or the subsequent signal, are rated as potentially erroneous signals and are tested by use of additional criteria.

Method for controlling an electronic overcurrent trip for low-voltage circuit breakers

A three or four pole low-voltage power switch is disclosed wherein the switch is partly provided with a device for detecting ground faults. For this purpose, the current vectorial sum must be produced in the three or four conductors of a monitored network. For the switches of this type, output signals received from Rogowski coils are directed via resistances to an integration capacitor whose voltage forms an input signal of another measuring amplifier representing the current sum of a monitored network. The output signal of the measuring amplifier is, afterwards processed in a known manner in the microprocessor of an excess-current trip.

Three- or four-pole low-voltage power switch with Rogowski coils operating as current sensors

An electrical power breaker includes an electronic protective device and an electronic memory. The memory is accommodated in the power breaker such that it is physically separated from said protective device, for operational data for the power breaker. Data security when using the additional electronic memory is increased by the electronic memory being connected to the protective device via a data bus, which can be used to transmit control signals for the purpose of activating or deactivating a write protection device of the electronic memory. The data bus is preferably an IC bus, and the write protection device is controlled by an I/O module which is likewise controlled by the IC bus.

Growing community of inventors

Bubenreuth, Germany

Andreas Krauss