A FLEXIBLE METHOD TO REDUCE THE AMOUNT OF DATA TO BE TRANSFERRED BETWEEN DEVICES

    公开(公告)号:EP4322175A1

    公开(公告)日:2024-02-14

    申请号:EP22189479.3

    申请日:2022-08-09

    IPC分类号: G16H30/20 G16H30/40 G16H10/60

    摘要: In order to reduce the transfer time of medical data, an apparatus for transferring medical data from a clinical-data infrastructure to a cloud-service provider. The apparatus comprises an input unit, a processing unit, and an output unit. The input unit is configured to receive, at the clinical-data infrastructure, medical data to be sent to the cloud-service provider with at least one available cloud service for analyzing the medical data. The processing unit is configured to select a data reduction algorithm from one or more data reduction algorithms based on a data reduction requirement of the at least one available cloud service, and to apply the selected data reduction algorithm to the medical data to generate reduced medical data. The output unit is configured to transmit the reduced medical data to the cloud-service provider.

    TRAINING METHOD, DEVICE AND IMAGE REPRESENSTATION SYSTEM FOR IMAGE STITCHING

    公开(公告)号:EP4418198A1

    公开(公告)日:2024-08-21

    申请号:EP23157474.0

    申请日:2023-02-20

    IPC分类号: G06T3/40

    CPC分类号: G06T3/4038 G06T3/4046

    摘要: The invention concerns an image processing system configured for carrying out a computer-implemented method for generating an image representation based on image stitching with a convolutional neural network, a computer-implemented method for generating an image representation based on image stitching with a convolutional neural network, and a method of training a convolutional neural network, for determining an image representation for image stitching. The training of the convolutional neural network comprises receiving image data, wherein the image data comprises at least two images, overlapping each other in an overlapping area in which the images overlapping each other in a target anatomy, and wherein the overlapping area comprises an optimum displacement between the two images such that the two images can be correctly combined for image stitching, determining a cost function of the displacement of the two images in the overlapping area, determining a deviation of the cost function from a reference cost function, and optimizing the CNN based on the deviation.

    X-RAY IMAGE PROCESSING SYSTEM, X-RAY IMAGING SYSTEM AND METHOD FOR PROCESSING AN X-RAY IMAGE

    公开(公告)号:EP4197443A1

    公开(公告)日:2023-06-21

    申请号:EP21215009.8

    申请日:2021-12-16

    IPC分类号: A61B6/00

    摘要: The invention relates to an X-ray image processing system (4) comprising an X-ray image input interface (8), a computing unit (9) and an X-ray image output interface (11). The X-ray image input interface (8) is configured to receive original X-ray images taken by an X-ray imaging system (1) comprising an X-ray source (2) and an X-ray detector (3). The computing unit (9) is connected to the X-ray image input interface (8) and is configured to obtain at least one original X-ray image from the X-ray image input interface (8), obtain information relating to the relative detector pose of the X-ray detector (3) relative to the X-ray source (2) and obtain a point of interest (P) in the original X-ray image. The computing unit (9) is further configured to apply a perspective transformation to the original X-ray image to obtain a transformed X-ray image, wherein the transformed X-ray image corresponds to a perspective where the X-ray detector (3) is perpendicular to an X-ray beam (6) from the X-ray source (2) to the point of interest (P). Finally, the X-ray image output interface (11) is configured to transmit the transformed X-ray image.