HKW Intellectual Property PartG mbB

Systems and methods for estimating an incident angle and trajectory of therapy devices within Intra-cardiac Echocardiography (ICE) images in real time in order to provide guidance for ICE manipulation to maintain continuous therapy device tip visibility. An ICE imaging sequence is acquired. A pre-trained ultrasound foundation model is used to extract spatial and temporal features in the sequence of ICE images. A transformer based temporal deep learning model is used that integrates the extracted spatial while incorporating historical passing points and angular information to in order to track the catheter tip within the ICE imaging plane. The tip tracking transformer based temporal deep learning model improves upon existing incident angle and trajectory model estimations in ICE procedures by improving prediction accuracy and consistency.

For pose estimation of an imaging catheter, an image or other scan data from the imaging catheter is input to a machine-learned model, which is configured by training to output the pose of the imaging catheter. A position sensor is not needed as only an image as input is sufficient for accurate pose estimation. Manual adjustment or reliance on user expertise is limited as the machine-learned model directly provides the pose.

The present invention relates to a system and method for managing asset performance in technical installation (114) using generative artificial intelligence models. The method includes obtaining input datasets associated with assets (110AN) from data sources (106A-N). The input datasets comprise multi-modal data associated with the assets (110A-N). The method includes identifying type of data format associated with the input datasets. The method includes determining a data transformation model applicable to the type of data format. The method further includes transforming the input datasets into target data format. The method includes generating graphical representation based on the input datasets. The method further includes determining anomalies associated with the plurality of assets (110A-N) and artifacts of the technical installation (114) based on the graphical representation. The method includes determining corrective actions for rectifying the anomalies. Moreover, the method includes outputting graphical representation, the anomalies, and the corrective actions on a user interface.

An expansion pad (3) for compensating for a length change of a pipe, in particular, a district heating/cooling pipe (1), when embedded in soil material (2). The expansion pad (3) comprises a protection layer (5), and a compensation layer (6) having a plurality of openings (7). The protection layer (5) is configured to prevent the soil material (2) from entering the openings (7). The expansion pad (3) is configured to compensate for the length change (4) of the district heating/cooling pipe (1) along a thickness (t) of the expansion pad (3). The expansion pad (3) is bendable around the district heating/cooling pipe (1) such that the openings (7) are deformed with respect to a relaxed state of the expansion pad (3).

For identification for medical devices, the medical device is formed by a generic electronics module and a removable identification module. By using an identifier on a removable module, the identifier may be associated with different electronics modules to form the medical device at different times. The removable module may include electronic paper, label, and/or memory for storing and/or displaying information about the medical device. The removable module may allow for settings to be provided for any connected electronics module, avoiding reconfiguring by the user. A service organization does not need to re-ship back repaired components, instead providing a replacement electronics module to form the complete medical device with the user kept identification module.

Disclosed is a method (500) and system (100) for dynamically segmenting complex digital twins (102, 402) for rendering one or more components (102A, 102B, 102C, 404A, 404B, 404C) of complex digital twin in computer simulated environment. The method comprising identifying, by a processing unit (302), components (102A, 102B, 102C, 404A, 404B, 404C) in complex digital twin (102, 402) associated with assets in industrial environment; determining relationship between identified components based on an impact of behavior of components when operational using an artificial intelligence model; segmenting components of the complex digital twin into one or more segments based on relationships; simulating each of the segments using operating parameters for determining behavior of components in segments for rendering in computer simulated environment; rendering, the one or more segments in the computer simulated environment based on the simulation and one or more requirements of a user (202).

Systems and methods for generating radiotherapy plans are provided. One or more medical images are received. One or more anatomical objects are segmented from the one or more medical images. Radiotherapy configurations for one or more objectives are determined based on the one or more medical images and the segmentations of the one or more anatomical objectives. A candidate radiotherapy plan is generated based on the radiotherapy configurations. A quality assessment of the candidate radiotherapy plan is performed. The one or more objectives are updated based on results of the quality assessment and the determining, the generating, and the performing are repeated for one or more iterations using the updated one or more objectives as the radiotherapy objectives to generate the candidate radiotherapy plan for a last iteration as a final radiotherapy plan. The final radiotherapy plan is output. Since the pipeline is automatic, the plan generation can be scaled. The data can serve large-scale AI model training.

A framework for characterizing contrast enhanced ultrasound (CEUS) images. The framework derives (204) a brightness mode (B-mode) and contrast image sequence from the sequence of contrast enhanced ultrasound (CEUS) images. B-mode images and contrast images in the B-mode and contrast image sequence are spatially co-registered and temporally sub-sampled. A region of interest may be selected (206) in a frame of the B-mode and contrast image sequence. The region of interest is then characterized (208) based on the B-mode and contrast image sequence.

A device includes an exterior surface comprising a driven element to interface with a drive element of a robotic drive, and an interior surface comprising features to fixedly couple to a rotator of a rotating hemostasis valve such that driving the driven element with the drive element causes movement of the rotator.

The present invention relates to a computer-implemented method, a computer-implemented device, a system and a computer program for determining a radiation treatment plan for a patient comprising determining a boundary condition constraining the radiation treatment plan; determining a first expected isodose surface in a body of the patient for a first specified radiation dose level based on the determined boundary condition, the first expected isodose surface comprising a plurality of dose point, defining a volume of interest in the body of the patient, the volume of interest being delimited by plurality of delimitation points, determining a plurality of metric distances between at least a selection of the plurality of dose points and of at least a first selection of the plurality of delimitation points and selecting a metric distance of the plurality of metric distances based on the boundary condition.