利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

11 条记录 (耗时 0.013 秒)

    AUTOMATIC CHANGE DETECTION IN MEDICAL IMAGES
    3.
    发明公开
    AUTOMATIC CHANGE DETECTION IN MEDICAL IMAGES 审中-公开

    公开(公告)号：EP3444777A1

    公开(公告)日：2019-02-20

    申请号：EP18189306.6

    申请日：2018-08-16

    申请人： Siemens Healthcare GmbH

    发明人： PHEIFFER, Thomas ,  MIAO, Shun ,  LIAO, Rui ,  DYBAN, Pavlo ,  SÜHLING, Michael ,  MANSI, Tommaso

    IPC分类号： G06T7/00

    摘要： Systems and methods are provided for identifying pathological changes in follow up medical images. Reference image data is acquired. Follow up image data is acquired. A deformation field is generated for the reference image data and the follow up data using a machine-learned network trained to generate deformation fields describing healthy, anatomical deformation between input reference image data and input follow up image data. The reference image data and the follow up image data are aligned using the deformation field. The co-aligned reference image data and follow up image data are analyzed for changes due to pathological phenomena.

    CROSS-DOMAIN IMAGE ANALYSIS AND CROSS-DOMAIN IMAGE SYNTHESIS USING DEEP IMAGE-TO-IMAGE NETWORKS AND ADVERSARIAL NETWORKS
    5.
    发明公开
    CROSS-DOMAIN IMAGE ANALYSIS AND CROSS-DOMAIN IMAGE SYNTHESIS USING DEEP IMAGE-TO-IMAGE NETWORKS AND ADVERSARIAL NETWORKS 审中-公开

    公开(公告)号：EP3511942A3

    公开(公告)日：2019-10-16

    申请号：EP19151565.9

    申请日：2019-01-14

    申请人： Siemens Healthcare GmbH

    发明人： ZHOU, Shaohua Kevin ,  MIAO, Shun ,  LIAO, Rui ,  TUYSUZOGLU, Ahmet ,  ZHENG, Yefeng

    IPC分类号： G16H30/40 ,  G06N3/04 ,  G06T7/00 ,  G06N3/08

    摘要： Methods and apparatus for cross-domain medical image analysis and cross-domain medical image synthesis using deep image-to-image networks and adversarial networks are disclosed. In a method for cross-domain medical image analysis a medical image of a patient from a first domain is received. The medical image is input to a first encoder of a cross-domain deep image-to-image network (DI2IN) that includes the first encoder for the first domain, a second encoder for a second domain, and a decoder. The first encoder converts the medical image to a feature map and the decoder generates an output image that provides a result of a medical image analysis task from the feature map. The first encoder and the second encoder are trained together at least in part based on a similarity of feature maps generated by the first encoder from training images from the first domain and feature maps generated by the second encoder from training images from the second domain, and the decoder is trained to generate output images from feature maps generated by the first encoder or the second encoder.

    METHOD AND SYSTEM FOR IMAGE REGISTRATION USING AN INTELLIGENT ARTIFICIAL AGENT
    7.
    发明公开
    METHOD AND SYSTEM FOR IMAGE REGISTRATION USING AN INTELLIGENT ARTIFICIAL AGENT 审中-公开
    使用智能人工智能体进行图像配准的方法和系统

    公开(公告)号：EP3246875A3

    公开(公告)日：2018-04-11

    申请号：EP17171689.7

    申请日：2017-05-18

    申请人： Siemens Healthcare GmbH

    发明人： LIAO, Rui ,  GRBIC, Sasa ,  MIAO, Shun ,  MANSI, Tommaso ,  ZHANG, Li ,  KAMEN, Ali ,  GEORGESCU, Bogdan ,  DE TOURNEMIRE, Pierre ,  COMANICIU, Dorin ,  GHESU, Florin Cristian ,  KREBS, Julian ,  SINGH, Vivek Kumar ,  XU, Daguang

    IPC分类号： G06T7/30

    CPC分类号： G06T7/0012 ,  A61B5/7267 ,  G06T7/30 ,  G06T2207/20081

    摘要： Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.

    摘要翻译： 公开了使用智能人造代理进行图像配准的方法和系统。 在基于智能人造药剂的配准方法中，基于待配准的医学图像和当前转换参数来确定人造药剂的当前状态观察。 使用基于机器学习的模型（诸如训练的深度神经网络（DNN）），基于当前状态观察，针对人造代理可用的多个动作来计算动作值。 这些动作对应于转换参数的预定调整。 从多个动作中选择具有最高动作值的动作，并通过对应于所选动作的预定调整来调整转换参数。 对多次迭代重复确定，计算和选择步骤，并且使用从多次迭代产生的最终变换参数来登记医学图像。

    A METHOD FOR DETERMINING A CORRESPONDENCE BETWEEN A SOURCE IMAGE AND A REFERENCE IMAGE
    9.
    发明公开
    A METHOD FOR DETERMINING A CORRESPONDENCE BETWEEN A SOURCE IMAGE AND A REFERENCE IMAGE 审中-公开

    公开(公告)号：EP3605465A1

    公开(公告)日：2020-02-05

    申请号：EP18186293.9

    申请日：2018-07-30

    申请人： Siemens Healthcare GmbH

    发明人： MANSI, Tommaso ,  MAILHE, Boris ,  LIAO, Rui ,  MIAO, Shun

    IPC分类号： G06T7/35 ,  G06K9/62

    摘要： A computer-implemented method of determining a correspondence between a source image and a reference image includes holding, in a memory: a generative model corresponding to a prior probability distribution of deformation fields, each deformation field corresponding to a respective co-ordinate transformation; and a conditional model for generating a style transfer probability distribution of reference images, given a source image and a deformation field. The method includes receiving first image data comprising the source image, receiving second image data comprising the reference image, determining an initial first deformation field, and
    iteratively performing an update process, until convergence, to update the first deformation field, to generate a converged deformation field representing the correspondence between the source image and the reference image. The update process includes: determining a change in one or more characteristics of the first deformation field to increase a posterior probability density associated with the first deformation field, given the source image and reference image; and changing the one or more characteristics in accordance with the determined change. The posterior probability density is based on a prior probability density associated with the first deformation field, the prior probability density determined using the generative model, and also a style transfer probability density associated with the reference image, given the source image and the first deformation field, the style transfer probability density determined using the conditional model.

    CROSS-DOMAIN IMAGE ANALYSIS AND CROSS-DOMAIN IMAGE SYNTHESIS USING DEEP IMAGE-TO-IMAGE NETWORKS AND ADVERSARIAL NETWORKS
    10.
    发明公开
    CROSS-DOMAIN IMAGE ANALYSIS AND CROSS-DOMAIN IMAGE SYNTHESIS USING DEEP IMAGE-TO-IMAGE NETWORKS AND ADVERSARIAL NETWORKS 审中-公开

    公开(公告)号：EP3511942A2

    公开(公告)日：2019-07-17

    申请号：EP19151565.9

    申请日：2019-01-14

    申请人： Siemens Healthcare GmbH

    发明人： ZHOU, Shaohua Kevin ,  MIAO, Shun ,  LIAO, Rui ,  TUYSUZOGLU, Ahmet ,  ZHENG, Yefeng

    IPC分类号： G16H30/40 ,  G06N3/04 ,  G06T7/00 ,  G06N3/08

    摘要： Methods and apparatus for cross-domain medical image analysis and cross-domain medical image synthesis using deep image-to-image networks and adversarial networks are disclosed. In a method for cross-domain medical image analysis a medical image of a patient from a first domain is received. The medical image is input to a first encoder of a cross-domain deep image-to-image network (DI2IN) that includes the first encoder for the first domain, a second encoder for a second domain, and a decoder. The first encoder converts the medical image to a feature map and the decoder generates an output image that provides a result of a medical image analysis task from the feature map. The first encoder and the second encoder are trained together at least in part based on a similarity of feature maps generated by the first encoder from training images from the first domain and feature maps generated by the second encoder from training images from the second domain, and the decoder is trained to generate output images from feature maps generated by the first encoder or the second encoder.