Abstract: A computer-implemented method includes receiving first medical image data, wherein the first medical image data is based on a first medical imaging of an examination object, receiving second medical image data, wherein the second medical image data is based on a second medical imaging of the examination object, wherein the first and the second medical imaging differ by at least one of an imaging modality or by an imaging protocol used, wherein the first and the second medical image data are registered with one another, determining synthetic image data by applying a trainable function to the first medical image data, determining a measure of similarity with a similarity function by comparison of the synthetic image data and the second medical image data, adjusting at least one parameter of the trainable function by optimization of the similarity function based on the measure of similarity, provision of the trainable function.

Abstract: The disclosure relates to a method (100) of optically analyzing a blood cell from a blood sample with a device for optically analyzing a blood cell from a blood sample, the device (1) comprising a microfluidic chamber with at least one fluidic flow-through channel, a first inlet (6) port configured to introduce at least a part of the blood sample into the fluidic channel, a first outlet (7) port configured to discharge at least a part of the blood sample from the fluidic channel, a flow generating and stopping device configured to generate a flow of the sample through the channel and to stop the flow while a least a part of the sample comprising at least one blood cell is situated within the channel and wherein after stopping the flow the sample is only influenced by gravity and inertial forces such that blood cells within the sample sediment on a first area of a lower surface of the channel, wherein cells sedimented within the first area of the lower surface can be optically analyzed in the chamber.

Abstract: The invention relates to a device for observing a biological probe. The device comprises an optical microscope, a beam splitting device and a plurality of cameras. The optical microscope comprises a support structure for supporting the biological probe in a beam path of the optical microscope. The beam splitting device is arranged in the beam path downstream from the biological probe, wherein the beam splitting device is configured to split the beam path into a plurality of beam paths. Each camera is arranged in one beam path of the plurality of beam paths and is configured to generate camera images of the biological probe. For at least some of the cameras, focal lengths of the cameras differ from one another and/or wavelength ranges captured by the cameras for generating the camera images of the biological probe differ from one another and/or sensor types of the cameras differ from one another.

Abstract: A functional component and having a partial plastic housing element with a plastic housing wall, the plastic housing wall having a device identification region integrated into the plastic housing wall and thus realizing a constituent part of the plastic housing wall. The device identification region comprising identification elements integrated into the plastic housing wall, those identification elements that realize part of a surface of the plastic housing wall realizing device identification elements, the device identification region being realized individually for the device by the device identification elements, such that the device can be unambiguously identified by means of the device identification region.

Abstract: In a computer-implemented method, a machine-learning model is pre-trained in an unsupervised manner to predict time-related information based on data obtained from a contrast-enhanced medical imaging measurement. This pre-trained machine-learning model is then used to build another machine-learning model to predict semantic context information for images determined from the contrast-enhanced medical imaging measurement.

Abstract: A meta-learning system includes an inner function computation module, adapted to compute output data from applied input data according to an inner model function, depending on model parameters; an error computation module, adapted to compute errors indicating mismatches between the computed output data and target values; a state update module, adapted to update the model parameters of the inner model function according to an updated state, updated based on a current state of the state update module, in response to an error received from the error computation module. The state update module is learned to adjust the model parameters of the inner model function, such that a following training of the inner model function with training data is improved.

Abstract: A method and a system are for performing at least one inference task on medical input data. In an embodiment, the system includes: a computing device configured to implement an artificial neural network, ANN. The ANN is configured to receive medical input data as an input and to perform at least one inference task based on the medical input data. The ANN includes an output layer with, for at least one inference task of the at least one inference task, a plurality of output nodes. Each output node corresponds to one quantile out of a plurality of defined quantiles.

Abstract: Various examples of the disclosure pertain to determining a label set for an anatomical structure such as a complex blood vessel, e.g., the coronary artery. The determining of the label set takes into account multiple inputs, such as the rule set of anatomical relationship between sub structures of the anatomical structure and a list of candidate labels and associated probabilities obtained for each one of the anatomical substructures.

Abstract: Various disclosed examples pertain to digital pathology, more specifically to training of a segmentation algorithm for segmenting whole-slide images depicting tissue of multiple types. An initial annotation of a whole-slide image is refined to yield a refined annotation based on which parameters of the segmentation algorithm can be set. Techniques of patch-wise weak supervision can be employed for such refinement.

Abstract: Various example embodiments pertain to processing images that depict tissue samples using a neural network algorithm. The neural network algorithm includes multiple encoder branches that are copies of each other that share the same parameters. The encoder branches can, accordingly, be referred to as Siamese copies of each other.

Abstract: One or more example embodiments provides a system and a method for differentiating a tissue of interest from another part of a medical scanner image, in particular pectoral muscle tissue from breast tissue in an X-ray mammography image. The method comprises providing a medical scanner image; inputting input data into a trained artificial neural network, the input data being based on the provided medical scanner image; generating, by the trained artificial neural network, output data based on the input data, the output data indicating a one-dimensional borderline between at least a part of the tissue of interest and the at least one other part of the medical scanner image; and outputting an output signal comprising or based on the generated output data.

Abstract: A functional component and having a partial plastic housing element with a plastic housing wall, the plastic housing wall having a device identification region integrated into the plastic housing wall and thus realizing a constituent part of the plastic housing wall. The device identification region comprising identification elements integrated into the plastic housing wall, those identification elements that realize part of a surface of the plastic housing wall realizing device identification elements, the device identification region being realized individually for the device by the device identification elements, such that the device can be unambiguously identified by means of the device identification region.

Abstract: Various example embodiments pertain to processing images that depict tissue samples using a neural network algorithm. The neural network algorithm includes multiple encoder branches that are copies of each other that share the same parameters. The encoder branches can, accordingly, be referred to as Siamese copies of each other.

Abstract: A computer-implemented method includes receiving first medical image data, wherein the first medical image data is based on a first medical imaging of an examination object, receiving second medical image data, wherein the second medical image data is based on a second medical imaging of the examination object, wherein the first and the second medical imaging differ by at least one of an imaging modality or by an imaging protocol used, wherein the first and the second medical image data are registered with one another, determining synthetic image data by applying a trainable function to the first medical image data, determining a measure of similarity with a similarity function by comparison of the synthetic image data and the second medical image data, adjusting at least one parameter of the trainable function by optimization of the similarity function based on the measure of similarity, provision of the trainable function.

Abstract: A power semiconductor module has a first and second intermediate circuit rail, an AC potential rail and with a packaged first and second power semiconductor switch. The respective power semiconductor switch has a first and second load current terminal and a control terminal, wherein the first power semiconductor switch is between the first intermediate circuit rail and the AC potential rail and the second power semiconductor switch is between the second intermediate circuit rail and the AC potential rail. The first load terminal of the first power semiconductor switch is contacted to the first intermediate circuit rail and the second load terminal of the first power semiconductor switch is electrically conductively contacted to the AC potential rail.

Abstract: A system and a method are provided for a parameter update. In an embodiment, the method includes obtaining, by a first entity, a function and parameter data from a second entity; selecting data samples provided by the first entities; providing a plurality of mutually isolated computing instances; assigning and providing the selected data samples to the computing instances; calculating, within each computing instance, results of the function; calculating averages over the results; determining whether the function fulfils a security criterion, and, if so: providing the calculated average for the gradient of the loss function and/or the calculated average of the output value and/or updated parameter data to the second entity.

Abstract: A system and a method are provided for a parameter update. In an embodiment, the method includes obtaining, by a first entity, a function and parameter data from a second entity; selecting data samples provided by the first entities; providing a plurality of mutually isolated computing instances; assigning and providing the selected data samples to the computing instances; calculating, within each computing instance, results of the function; calculating averages over the results; determining whether the function fulfils a security criterion, and, if so: providing the calculated average for the gradient of the loss function and/or the calculated average of the output value and/or updated parameter data to the second entity.

Abstract: A method and a system are for performing at least one inference task on medical input data. In an embodiment, the system includes: a computing device configured to implement an artificial neural network, ANN. The ANN is configured to receive medical input data as an input and to perform at least one inference task based on the medical input data. The ANN includes an output layer with, for at least one inference task of the at least one inference task, a plurality of output nodes. Each output node corresponds to one quantile out of a plurality of defined quantiles.

Abstract: A power semiconductor module has a first and second intermediate circuit rail, an AC potential rail and with a packaged first and second power semiconductor switch. The respective power semiconductor switch has a first and second load current terminal and a control terminal, wherein the first power semiconductor switch is between the first intermediate circuit rail and the AC potential rail and the second power semiconductor switch is between the second intermediate circuit rail and the AC potential rail. The first load terminal of the first power semiconductor switch is contacted to the first intermediate circuit rail and the second load terminal of the first power semiconductor switch is electrically conductively contacted to the AC potential rail.

Abstract: A meta-learning system includes an inner function computation module, adapted to compute output data from applied input data according to an inner model function, depending on model parameters; an error computation module, adapted to compute errors indicating mismatches between the computed output data and target values; a state update module, adapted to update the model parameters of the inner model function according to an updated state, updated based on a current state of the state update module, in response to an error received from the error computation module. The state update module is learned to adjust the model parameters of the inner model function, such that a following training of the inner model function with training data is improved.