公开(公告)号：US20200160509A1

公开(公告)日：2020-05-21

申请号：US16192551

申请日：2018-11-15

Applicant: General Electric Company

Inventor： Jed Douglas Pack ,  Peter Michael Edic ,  Xin Wang ,  Xia Li ,  Prem Venugopal ,  James Vradenburg Miller

IPC: G06T7/00 ,  G06N3/08 ,  G16H50/20 ,  G16H30/40

Abstract: The present disclosure relates to training one or more neural networks for vascular vessel assessment using synthetic image data for which ground-truth data is known. In certain implementations, the synthetic image data may be based in part, or derived from, clinical image data for which ground-truth data is not known or available. Neural networks trained in this manner may be used to perform one or more of vessel segmentation, decalcification, Hounsfield unit scoring, and/or estimation of a hemodynamic parameter.

公开(公告)号：US20140187946A1

公开(公告)日：2014-07-03

申请号：US13731213

申请日：2012-12-31

Applicant: GENERAL ELECTRIC COMPANY

Inventor： James Vradenburg Miller ,  Kedar Anil Patwardhan

IPC: A61B8/08 ,  A61B8/00

CPC classification number: A61B8/5207 ,  A61B8/0833 ,  A61B8/4245 ,  A61B8/463 ,  A61B8/469 ,  A61B8/5215 ,  A61B8/54 ,  G01S7/5205 ,  G01S7/52074

Abstract: A computer-implemented method for active control of ultrasound image acquisition includes accessing image data representing a series of ultrasound images acquired over a period of time from an ultrasound probe and identifying an object of interest in at least one of the images. The method further includes detecting changes in a position of the ultrasound probe and/or an orientation of the ultrasound probe over the period of time with respect to the object of interest, or changes in a position of the object of interest and/or an orientation of the object of interest over the period of time with respect to the ultrasound probe. The method further includes adjusting at least one ultrasound image acquisition parameter based on the detected changes in the position and/or the orientation of the ultrasound probe and/or based on the detected changes in the position and/or the orientation of the object of interest.

Abstract translation: 用于主动控制超声图像获取的计算机实现方法包括访问表示在一段时间内从超声波探头获取的一系列超声图像的图像数据，并在至少一个图像中识别感兴趣对象。 所述方法还包括在相对于感兴趣对象的一段时间内检测超声探头位置的变化和/或超声波探头的取向，或者感兴趣对象的位置的改变和/或取向 相对于超声波探头在一段时间内的感兴趣对象。 该方法还包括基于检测到的超声探头的位置和/或取向的变化和/或基于检测到的感兴趣对象的位置和/或取向的变化来调整至少一个超声图像采集参数 。