Siemens Healthineers Ag

Siemens Aktiengesellschaft

Siemens Healthcare Gmbh

Michael Schrapp

Michael Suehling

Frank Dennerlein

Matthias Goldammer

Slobodan Ilic

Shadi Albarqouni

Linda Mai Bui

Juergen Stephan

Erick Arruda Camara Ferreira

Frank Enders

Matthias Senn

Dubravka Ukalovic

Dorothea Roth

Karsten Schoerner

A computer-implemented method for the further training of an artificial-intelligence evaluation algorithm that has already been trained based upon basic training data, wherein the evaluation algorithm ascertains output data describing evaluation results from input data comprising image data recorded with a respective medical imaging facility. In an embodiment, the method includes ascertaining at least one additional training data set containing training input data and training output data assigned thereto; and training the evaluation algorithm using the at least one additional training data set. The additional training data set is ascertained from the input data used during a clinical examination process with a medical imaging facility, which the already-trained evaluation algorithm was used, and output data of the already-trained evaluation algorithm that has been at least partially correctively modified by the user.

Computer-implemented method and system for training an evaluation algorithm, computer program and electronically readable data carrier

One or more example embodiments of the present invention relates to a system for detection of x-ray radiation. The system comprises photon-counting x-ray CT scanners and associated edge devices. Each edge device determines a quality indicator indicative of a quality of the sensor data based on scanner data. Further, each edge device generates a parameterized machine learning model by optimizing the quality indicator. A server device receives the generated parameterized machine learning models from the edge devices, aggregates the parameterized machine learning models into an aggregated parameterized machine learning model, and sends at least part of the aggregated parameterized machine learning model back to the edge devices.

X-ray radiation detection

Various embodiments include a method for facilitating tomographic reconstruction comprising: emitting an x-ray beam from an x-ray unit; ascertaining an attenuation of the x-ray beam during transmission through an object situated in a beam path of the x-ray beam; ascertaining structure data of the object based at least in part on the attenuation of the x-ray beam; and ascertaining a pose of the x-ray unit relative to the object using a digital model of the object and based at least in part on the attenuation of the x-ray beam.

Ascertaining the pose of an x-ray unit relative to an object on the basis of a digital model of the object

A method is provided for reducing noise in a tomogram and/or volume rendering of at least one object. The noise can occur when scattered radiation artifacts are corrected. At least one tomogram that is affected by scattered radiation and at least one preliminary tomogram that has been corrected by a defined correction method are produced from a plurality of projection image datasets that are affected by scattered radiation. The noise emerging when scattered radiation artifacts are corrected may be reduced by selectively smoothening the noise using a filter based on an edge contour of the at least one object, which contour is rendered in the tomogram that is affected by scattered radiation.

Noise reduction in tomograms

Growing community of inventors

Munich, Germany

Michael Schrapp