Siemens Healthineers Ag

Siemens Healthcare Gmbh

Alexander Katzmann

Michael Suehling

Alexander Muehlberg

Felix Durlak

Felix Lades

Michael Wels

Michael Sühling

Oliver Taubmann

Rainer Kaergel

Felix Denzinger

Hendrik Ditt

Florian Thamm

Leonhard Rist

Lisa Kratzke

Stephen Ahmad

Stephan Ahmad

Alexander Mühlberg

One or more example embodiments of the invention relates in one aspect to a computer-implemented method for providing a stroke information. The method includes receiving examination data, the examination data comprising computed tomography imaging data of an examination area of a patient, the examination area of the patient comprising at least one brain region, the at least one brain region being affected by a stroke; adjusting a causal model based on the computed tomography imaging data to obtain an adjusted causal model, wherein the adjusted causal model models a first variable as a first cause for an appearance of the examination area of the patient; receiving a first value for the first variable; generating the stroke information based on the adjusted causal model and the first value for the first variable; and providing the stroke information.

Method and data processing system for providing a stroke information

A computer-implemented method and system are for parametrizing a function including a processing algorithm and a representation generator, the representation generator being designed to generate at least one representation. In an embodiment, the method includes using an optimization algorithm to determine the processing algorithm and the at least one representation parametrization. The optimization algorithm optimizes a measure for the performance of the processing algorithm when operating on a set of training representations generated by applying the representation generator to training medical image datasets, by varying on the one hand the content of the at least one representation parametrization and/or the number of used representation parametrizations and on the other hand the processing algorithm and the algorithm parameters.

Computer-implemented method for parametrizing a function for evaluating a medical image dataset

A method is for providing a classification explanation. The method includes receiving an acquired medical image corresponding to an examination volume; and receiving or determining an actual classification value. The actual classification value classifies an anatomical structure within the acquired medical image. The method further includes receiving or determining a first classification value being different from the actual classification value, the first classification value being a potential classification value of the anatomical structure within the acquired medical image; applying a first generative function to the acquired medical image to generate a first synthetic image, the first generative function being based on the first classification value, and being configured to modify the anatomical structure to exhibit the first classification value; and providing a visualization based on the acquired medical image and the first synthetic image. Systems and computer programs are further for providing a classification explanation and/or generative functions.

Providing a classification explanation and a generative function

A computer-implemented method is for providing a clinical information. In an embodiment, the computer-implemented method includes receiving input data including a graph representation of a plurality of disease lesions of a patient; applying a trained function to the input data to generate the clinical information, the trained function being based on a graph machine learning model; and providing the clinical information, the clinical information including at least one information for prediction of the disease progression, survival or therapy response of the patient.

Method for obtaining disease-related clinical information

A computer-implemented method is for providing radiomics-related information. In an embodiment, the computer-implemented method includes receiving radiomics-related data; determining, based on the radiomics-related data and an assistance algorithm, a function for processing the radiomics-related data; calculating, based on the radiomics-related data and the function for processing the radiomics-related data, the radiomics-related information; and providing the radiomics-related information.

Method and data processing system for providing explanatory radiomics-related information

In one embodiment, a computer-implemented method provides a prediction of a medical target variable. The computer-implemented method includes receiving medical imaging data of an examination area, the examination area including a plurality of lesions of an anatomical structure, wherein each lesion of the plurality of lesions of the anatomical structure spaced apart from any other lesion of the plurality of lesions of the anatomical structure; calculating a spread parameter based on the medical imaging data, the spread parameter being indicative of a spread of a spatial distribution of the plurality of lesions of the anatomical structure; calculating the prediction of the medical target variable based on the spread parameter; and providing the prediction of the medical target variable.

Method and data processing system for providing a prediction of a medical target variable

A method is for obtaining at least one feature of interest, especially a biomarker, from an input image acquired by a medical imaging device. The at least one feature of interest is the output of a respective node of a machine learning network, in particular a deep learning network. The machine learning network processes at least part of the input image as input data. The used machine learning network is trained by machine learning using at least one constraint for the output of at least one inner node of the machine learning network during the machine learning.

Method for obtaining at least one feature of interest

A method is for generating synthetic training data and for training deep learning algorithms for tumor lesion characterization. In an embodiment, the method for generating synthetic training data for training a deep learning algorithm includes training a Generative Adversarial Network to generate synthetic image data, the Generative Adversarial Network including a generator and a discriminator; and using the generator of the Generative Adversarial Network to generate synthetic image data as the synthetic training data.

Methods for generating synthetic training data and for training deep learning algorithms for tumor lesion characterization, method and system for tumor lesion characterization, computer program and electronically readable storage medium

Growing community of inventors

Fuerth, Germany

Alexander Katzmann