TRAINING A MACHINE LEARNING ALGORITHM USING DIGITALLY RECONSTRUCTED RADIOGRAPHS

    公开(公告)号:US20240386603A1

    公开(公告)日:2024-11-21

    申请号:US18786398

    申请日:2024-07-26

    Applicant: Brainlab AG

    Abstract: Disclosed is a computer-implemented method of training a likelihood-based computational model for determining the position of an image representation of an annotated anatomical structure in a two-dimensional x-ray image, wherein the method encompasses inputting medical DRRs together with annotation to a machine learning algorithm to train the algorithm, i.e. to generate adapted learnable parameters of the machine learning model. The annotations may be derived from metadata associated with the DRRs or may be included in atlas data which is matched with the DRRs to establish a relation between the annotations included in the atlas data and the DRRs. The thus generated machine learning algorithm may then be used to analyse clinical or synthesized DRRs so as to appropriately add annotations to those DRRs and/or identify the position of an anatomical structure in those DRRs.

    Single-marker navigation
    2.
    发明授权

    公开(公告)号:US09987093B2

    公开(公告)日:2018-06-05

    申请号:US14902051

    申请日:2013-07-08

    Applicant: Brainlab AG

    Abstract: A medical data processing method for determining the spatial relationship of a first medical device relative to a second medical device, the method being constituted to be executed by a computer and comprising the following steps: d) acquiring first medical device position data comprising first medical device position information describing the position of the first medical device, wherein the first medical device position data is acquired based on reading, from a marker device having for example a fixed spatial relationship relative to the first medical device, the first medical device position information or information which allows access to the first medical device position information; e) acquiring second medical device position data comprising second medical position information describing the position of the second medical device; f) determining, based on the first medical device position data and the second medical device position data, relative position data comprising relative position information describing the spatial relationship of the second medical device relative to the first medical device.

    Inline-View Determination
    4.
    发明申请

    公开(公告)号:US20200100841A1

    公开(公告)日:2020-04-02

    申请号:US15781982

    申请日:2017-04-19

    Applicant: Brainlab AG

    Abstract: The present invention relates to a computer-implemented medical data processing method for determining a 2D-view within an acquired 3D-image-dataset of a patient, wherein the method comprises executing, on a processor of a computer, the following steps: a) a representation of at least one anatomical structure (2) of interest is identified in the 3D-image-dataset and registered with the at least one anatomical structure (2); b) the spatial position of the at least one anatomical structure (2) and the spatial position of a predetermined section of a medical instrument (1) are determined in real space; c) the 2D-view is determined within the 3D-image-dataset, wherein the view-plane of the 2D-view is defined on the basis of the spatial position of the medical instrument (1), and wherein the view-center (B) of the 2D-view is defined on the basis of the relative spatial position of a predetermined section of the medical instrument (1) and the at least one anatomical structure (2); d) the relative position of the defined view-center with respect to a predetermined section of the medical instrument (1) is maintained in the 2D-view. The present invention further relates to a corresponding computer program, a corresponding program storage medium and a corresponding system for performing such method.

    Inline-view determination
    7.
    发明授权

    公开(公告)号:US10667864B2

    公开(公告)日:2020-06-02

    申请号:US15781982

    申请日:2017-04-19

    Applicant: Brainlab AG

    Abstract: The present invention relates to a computer-implemented medical data processing method for determining a 2D-view within an acquired 3D-image-dataset of a patient, wherein the method comprises executing, on a processor of a computer, the following steps: a) a representation of at least one anatomical structure (2) of interest is identified in the 3D-image-dataset and registered with the at least one anatomical structure (2); b) the spatial position of the at least one anatomical structure (2) and the spatial position of a predetermined section of a medical instrument (1) are determined in real space; c) the 2D-view is determined within the 3D-image-dataset, wherein the view-plane of the 2D-view is defined on the basis of the spatial position of the medical instrument (1), and wherein the view-center (B) of the 2D-view is defined on the basis of the relative spatial position of a predetermined section of the medical instrument (1) and the at least one anatomical structure (2); d) the relative position of the defined view-center with respect to a predetermined section of the medical instrument (1) is maintained in the 2D-view. The present invention further relates to a corresponding computer program, a corresponding program storage medium and a corresponding system for performing such method.

Patent Agency Ranking