Abstract: A device and a computer-implemented method for data-efficient active machine learning. Annotated data are provided. A model is trained for a classification of the data as a function of the annotated data. For unannotated data, values of an acquisition function of the unannotated data are determined, and the unannotated data for the active machine learning whose values for the acquisition function satisfy a criterion are acquired from the unannotated data. An autocorrelation is determined via a feature representation for a sample from the unannotated data to be assessed, in particular from at least one layer of the model. The value of the acquisition function of this sample is determined as a function of a root mean square via the autocorrelation, in particular in at least one dimension.

Abstract: A device and a computer-implemented method for data-efficient active machine learning. Annotated data are provided. A model is trained for a classification of the data as a function of the annotated data. The model trained in this way is calibrated, as a function of the annotated data, with regard to confidence for a correctness of the classification of the annotated data by the model. For unannotated data, the confidence for the correctness of the classification of the unannotated data is determined, using the model calibrated in this way. The unannotated data for the active machine learning whose confidence satisfies a criterion is acquired from the unannotated data.

Abstract: A method and a device for generating labeled data, for example training data, in particular for a neural network.

Abstract: The invention relates to an assistance device, an assistance system and an assistance method for assisting a practitioner in an interventional hemodynamic (e.g fractional flow reserve (FFR)) measurement on a subject. The FFR pressure measurements are combined with an, for example, angiography-based assessment of the coronary vessel geometry. An advanced computational fluid dynamics model may be employed to add flow and myocardial resistance data based on the interventional pressure values and on a vascular model generated prior to the intervention. In case that these data are available prior to the intervention, the location of most optimal positions for pressure measurements can be pre-calculated and by overlay of the vessel tree, for example, on the X-ray projection, advice can be given for the interventional cardiologist during the intervention.

Abstract: An apparatus for assessing a coronary vasculature and a corresponding method are provided which allow to globally assess a coronary artery disease directly from the contrast agent dynamics as derived from diagnostic images acquired using an invasive medical imaging modality by following the time course of the area occupied by the vessels in the diagnostic images.

Abstract: Mechanical image acquisition systems (such as medical C-arms) frequently accumulate geometrical errors which must be calibrated out using a calibration phantom. A more frequent regime of system calibration implies a less frequent use of the C-arm for clinical applications. The present application proposes to identify common biases between the acquired projection frame sequences from the same mechanical image acquisition system in first and second acquisitions, and to compare this to expected calibration data of the mechanical image acquisition system to generate frame deviation measures. If a resemblance between the first and second sequences of frame deviation measures is obtained, one or more calibration actions are performed (such as alerting the user that calibration should be provided, and/or automatically correcting for the geometry deviation).

Abstract: A method for training a machine learning model for determining a quality grade of data sets from each of a plurality of sensors. The sensors are configured to generate surroundings representations. The method includes: providing data sets of each of the sensors from corresponding surroundings representations; providing attribute data of ground truth objects of the surroundings representations; determining a quality grade of the respective data set of each of the sensors using a metric, the metric comparing at least one variable, which is determined using the respective data set, with at least one attribute datum of at least one associated ground truth object of the surroundings representation; and training the machine learning model using the data sets of each of the sensors and the respectively assigned determined quality grades.

Abstract: The present invention relates to a determination of a physiological functional parameter of a living being. Ultrasound image data and Doppler image data of a vessel structure are provided (101) and registered (102). The vessel structure is segmented (103) to generate (104) a representation of the vessel structure. The flow velocity inside a vessel of the vessel structure is determined (105) based on the Doppler image data. A physiological functional parameter determination model defining a value of a functional physiological parameter in dependence of a representation of a vessel structure and a flow velocity inside a vessel of the vessel structure is used (106) to determine (107) the physiological functional parameter inside the vessel of the vessel structure. The representation of the vessel structure and/or the flow velocity values can be constantly updated upon receipt of further input images to provide an estimation of the functional physiological parameter in real-time.

Abstract: The present invention is related to a compound of formula (I) wherein R1 is selected from the group consisting of hydrogen, methyl and cyclopropylmethyl; AA-COOH is an amino acid selected from the group consisting of 2-amino-2-adamantane carboxylic acid, cyclohexylglycine and 9-amino-bicyclo[3.3.1]nonane-9-carboxylic acid; R2 is selected from the group consisting of (C1-C6)alkyl, (C3-C8)cycloalkyl, (C3-C5)cycloalkylmethyl, halogen, nitro and trifluoromethyl; ALK is (C2-C5)alkylidene; R3, R4 and R5 are each and independently selected from the group consisting of hydrogen and (C1-C4)alkyl under the proviso that one of R3, R4 and R5 is of the formula (II) wherein ALK? is (C2-C5)alkylidene; R6 is selected from the group consisting of hydrogen and (C1-C4)alkyl; and R7 is selected from the group consisting of H and an Effector moiety; or a pharmacologically acceptable salt, solvate or hydrate thereof.

Abstract: The present invention is related to a compound of formula (I) wherein R1 is selected from the group consisting of hydrogen, methyl and cyclopropylmethyl; AA-COOH is an amino acid selected from the group consisting of 2-amino-2-adamantane carboxylic acid, cyclohexylglycine and 9-amino-bicyclo[3.3.1]nonane-9-carboxylic acid; R2 is selected from the group consisting of (C1-C6)alkyl, (C3-C8)cycloalkyl, (C3-C8)cycloalkylmethyl, halogen, nitro and trifluoromethyl; ALK is (C2-C5)alkylidene; R3, R4 and R5 are each and independently selected from the group consisting of hydrogen and (C1-C4)alkyl under the proviso that one of R3, R4 and R5 is of the formula (II) wherein ALK? is (C2-C5)alkylidene; R6 is selected from the group consisting of hydrogen and (C1-C4)alkyl; and R7 is selected from the group consisting of H and an Effector moiety; or a pharmacologically acceptable salt, solvate or hydrate thereof.

Abstract: An anti-glare headlamp for a motor vehicle, including a large number of light units, each of the light units having: a light source element, which is configured to emit light along a first optical axis in the direction of a space; a projection optic, which is disposed behind the light source element in the direction of the emitted light and is configured to project the light emitted by the light source element into the space at a solid angle; and a photodetector, which is situated in front of the projection optic in the direction of the emitted light and is configured to detect the light projected into the space by the projection optic and reflected from an object in the space, along a second optical axis back to the projection optic.

Abstract: Stenosis information is obtained by obtaining photographic image data (302) from a displayed image of a blood vessel (103, 203) containing the stenosis. Contours of the blood vessel and the stenosis are detected and dimensions are estimated from the photographic image data. A blood vessel model is reconstructed and fractional flow reserve data is calculated using the blood vessel model.

Abstract: Cone beam computed tomography image acquisition protocols typically acquire a series of 2D projection images around a region of interest of a patient. The time required for a C-arm to travel around an acquisition orbit around the region of interest of a patient is non-trivial, and as a result, a patient being imaged may move during the acquisition. This is problematic because many computed tomography image acquisition algorithms assume that a patient is perfectly still during the acquisition time. If patient moves as the series of 2D projection images is being obtained, a 3D reconstruction will be affected by image artefacts. This application proposes to identify and to remove image artefacts caused by the relative motion of at least two rigid objects in the region of interest (For example, a mandible moving with respect to a skull during the acquisition).

Abstract: An apparatus for assessing a hemodynamic property in a coronary vasculature and a corresponding method are provided in which diagnostic data of a vessel of interest is used to identify a first and second measurement position at which a first and a second value for a first hemodynamic property may be obtained whereby these first and second values are suitable to derive at least one diagnostic parameter indicative of a second hemodynamic 5 property that cannot or should not be measured directly.

Abstract: The present invention relates to a device for interacting with vessel images, the device (14) comprising: an interface unit (22); a processing unit (20); wherein the interface unit (22) comprises: a display (21); and an input setup (23); wherein the display (21) is configured to display a vessel image (24); wherein the input setup (23) is configured to receive a user input in relation to the vessel image (24); wherein the processing unit (20) is configured to: determine, for at least one vessel (26) in the vessel image (24), a vessel contour (30); determine, from the user input, an identifier position (36) in the vessel image (24); indicate at least a portion (38) of the vessel contour (30) in the vessel image (24), if the determined identifier position (36) is spaced apart from the vessel contour (30) by a distance (37) within a predefined distance range; determine, from the user input, a drag direction (42); and move the indicated portion (38) along the vessel contour (30) based on the determined drag direc

Abstract: The invention discloses an apparatus (2), a system (1) and a method (100) for characterization of vessels and for vessel modeling. The cross sectional area (A1) of the vessel is derived from pressure measurements (p1,p2) obtained by an instrument (3) from within the vessel. When multiple cross sectional areas (A1,A2) are derived for multiple reference positions (r1,r2) based on pressure measurements (p1,p2,p3) along the vessel, a representation (20,30) of the vessel can be rendered, without requiring any imaging modality. Furthermore, the effect of the pulsatile blood flow on the elasticity of the vessel walls can be visualized, supporting assessment of a stenosis or an aneurysm formation along the vessel.

Abstract: The present invention is related to a conjugate comprising a structure of general formula (1) [TM1]-[AD1]-[LM]-[AD2]-[TM2] (1), wherein TM1 is a first targeting moiety, wherein the first targeting moiety is capable of binding to a first target, AD1 is a first adapter moiety or is absent, LM is a linker moiety or is absent, AD2 is a second adapter moiety or is absent, and TM2 is a second targeting moiety, wherein the second targeting moiety is capable of binding to a second target; wherein the first targeting moiety and/or the second targeting moiety is a compound of formula (2): wherein R1 is selected from the group consisting of hydrogen, methyl and cyclopropylmethyl; AA-COOH is an amino acid selected from the group consisting of 2-amino-2 adamantane carboxylic acid, cyclohexylglycine and 9-amino-bicyclo[3.3.

Abstract: An apparatus for analyzing coronary vessels and a corresponding method are provided in which simulated pullback data obtained from (non-invasively) acquired diagnostic images is co-registered with invasively acquired intravascular pullback data and the co-registration is used to identify disparities in the pullback data obtained using the two modalities. These disparities allow for deriving further information about the vessel geometry and/or the blood flow through the vessel. They may therefore be used to improve the physiological model.

Abstract: The invention relates to a system and a method for guiding an intravascular ultrasound catheter device comprising an ultrasound probe to a potential lesion in a vascular tree (31). In the system, position information of the probe are provided for displaying to a user and/or for an automated processing of the position information. An evaluation unit is configured to receive a diagnostic image of the vascular tree, to determine values of at least one vessel parameter for a plurality of locations in the vascular tree, and to identify at least one location associated with an abnormal value of the at least one vessel parameter. Further, a mapping unit is configured to provide a visual indication (32) of the at least one location in the visualization of the vascular tree and/or to provide information about the at least one location for use in the automated processing of the position information.

Abstract: An apparatus for assessing a patient's vasculature and a corresponding method are provided, in which the bifurcations in a vessel of interest are identified on the basis of a local change in at least one geometric parameter value of the vessel of interest and the fluid dynamics inside the vessel of interest are adjusted to take account for said bifurcations.