利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

119 records (took 0.02 seconds)

    DUAL DOMAIN TRACKING OF TARGET STRUCTURES
    2.
    发明申请
    DUAL DOMAIN TRACKING OF TARGET STRUCTURES 审中-公开

    公开(公告)号：WO2022200283A1

    公开(公告)日：2022-09-29

    申请号：PCT/EP2022/057371

    申请日：2022-03-21

    Applicant: VARIAN MEDICAL SYSTEMS INTERNATIONAL AG

    Inventor： PAYSAN, Pascal ,  WALCZAK, Michal ,  ZHU, Liangjia ,  ROGGEN, Toon ,  SCHEIB, Stefan

    IPC: G06T7/246

    Abstract: Embodiments described herein provide for determining a probability distribution of a three- dimensional point in a template feature map matching a three-dimensional point in space. A dual-domain target structure tracking end-to-end system receives projection data in one dimension or two dimensions and a three-dimensional simulation image. The end-to-end system extracts a template feature map from the simulation image using segmentation. The end-to-end system extracts (206) features from the projection data, transforms the features of the projection data into three-dimensional space, and sequences the three-dimensional space to generate a three-dimensional feature map. The end-to-end system compares (210) the template feature map to the generated three-dimensional feature map, determining (212) an instantaneous probability distribution of the template feature map occurring in the three-dimensional feature map.

    TRAINING ARTIFICIAL INTELLIGENCE MODELS FOR RADIATION THERAPY
    3.
    发明申请
    TRAINING ARTIFICIAL INTELLIGENCE MODELS FOR RADIATION THERAPY 审中-公开

    公开(公告)号：WO2022129144A1

    公开(公告)日：2022-06-23

    申请号：PCT/EP2021/085848

    申请日：2021-12-15

    Applicant: VARIAN MEDICAL SYSTEMS INTERNATIONAL AG

    Inventor： BASIRI, Shahab ,  HAKALA, Mikko ,  KUUSELA, Esa ,  CZEIZLER, Elena

    IPC: G16H20/40

    Abstract: Disclosed herein are systems and methods for iteratively training artificial intelligence models using reinforcement learning techniques. With each iteration, a training agent applies a random radiation therapy treatment attribute corresponding to the radiation therapy treatment attribute associated with previously performed radiation therapy treatments when an epsilon value indicative of a likelihood of exploration and exploitation training of the artificial intelligence model satisfies a threshold. When the epsilon value does not satisfy the threshold, the agent generates (242), using an existing policy, a first predicted radiation therapy treatment attribute, and generates (244), using a predefined model, a second predicted radiation therapy treatment attribute. The agent applies (246) one of the first predicted radiation therapy treatment attribute or the second predicted radiation therapy treatment attribute that is associated with a higher reward. The agent iteratively repeats (248) training the artificial intelligence model until the existing policy satisfies an accuracy threshold.

    RADIOABLATION TREATMENT SYSTEMS AND METHODS
    5.
    发明申请
    RADIOABLATION TREATMENT SYSTEMS AND METHODS 审中-公开

    公开(公告)号：WO2022005487A1

    公开(公告)日：2022-01-06

    申请号：PCT/US2020/040808

    申请日：2020-07-03

    Applicant: VARIAN MEDICAL SYSTEMS, INC. ,  VARIAN MEDICAL SYSTEMS INTERNATIONAL AG

    Inventor： JOHNSON, Leigh Scott ,  HONEGGER, Jonas Michael ,  KUNZ, Patrik Niklaus ,  SCHEIB, Stefan Georg ,  ATTANASI, Francesca ,  MORGAN, Andrea

    IPC: G16B20/40

    Abstract: Systems and methods for cardiac radioablation treatment planning are disclosed. In some examples, a computing device receives a first signal identifying a first event within a first workspace from a second computing device. The computing device determines a first action to apply to a first image displayed within a second workspace based on the first signal. The computing device generates a second image based on applying the first action to the first image within the second workspace, and displays the second image within the second workspace. In some examples, the first workspace is a radiation oncologist workspace and the second workspace is an electrophysiologist workspace. In some examples, the first workspace is an electrophysiologist oncologist workspace and the second workspace is a radiation oncologist workspace.

    USING ISODOSE SURFACES FOR OPTIMIZING DOSE DISTRIBUTION IN RADIATION TREATMENT PLANNING
    8.
    发明申请
    USING ISODOSE SURFACES FOR OPTIMIZING DOSE DISTRIBUTION IN RADIATION TREATMENT PLANNING 审中-公开

    公开(公告)号：WO2020200849A1

    公开(公告)日：2020-10-08

    申请号：PCT/EP2020/057847

    申请日：2020-03-20

    Applicant: VARIAN MEDICAL SYSTEMS INTERNATIONAL AG

    Inventor： KUUSELA, Esa ,  LAAKSONEN, Hannu ,  HALKO, Lauri

    IPC: A61N5/10

    Abstract: Cost functions and cost function gradients for use in radiation treatment planning can be computed based on an approximation of an "isodose" surface. Where a clinical goal is expressed by reference to a threshold isodose surface, a corresponding cost function component can be defined directly by reference to that isodose surface 1004, and a corresponding contribution to the cost function gradient can be approximated by identifying voxels that are intersected by the threshold isodose surface and approximating the gradient of the dose distribution within each such voxel.

    MULTILEAF COLLIMATOR WITH ALTERNATING TRAPEZOIDAL LEAF GEOMETRY DESIGN
    9.
    发明申请
    MULTILEAF COLLIMATOR WITH ALTERNATING TRAPEZOIDAL LEAF GEOMETRY DESIGN 审中-公开

    公开(公告)号：WO2020139590A1

    公开(公告)日：2020-07-02

    申请号：PCT/US2019/066430

    申请日：2019-12-16

    Applicant: VARIAN MEDICAL SYSTEMS, INC. ,  VARIAN MEDICAL SYSTEMS INTERNATIONAL AG

    Inventor： RIEGER, Rachel ,  KAUPPINEN, Juha ,  MAGLIARI, Anthony ,  BAIC, Dusan

    IPC: A61N5/10

    Abstract: A multileaf collimator includes a plurality of beam-blocking leaves of a first type and a plurality of beam-blocking leaves of a second type. The beam-blocking leaves of the first type are alternatingly arranged with the beam-blocking leaves of the second type side by side. Each of the beam-blocking leaves of the first type has a trapezoidal geometry viewed in the leaf longitudinal moving direction comprising a wider end and a narrower end with the wider end being proximal to a source. Each of the beam-blocking leaves of the second type has a trapezoidal geometry viewed in the leaf longitudinal moving direction comprising a wider end and a narrower end with the wider end being distal to the source.

Patent Agency Ranking