公开(公告)号：US10957066B2

公开(公告)日：2021-03-23

申请号：US16357868

申请日：2019-03-19

Applicant: General Electric Company

Inventor： Huan Tan ,  Li Zhang ,  Yakov Polishchuk ,  Bo Wang

IPC: G06T7/70 ,  G06T7/292 ,  G06K9/00 ,  G06K9/62 ,  G01S13/74 ,  G01S15/74

Abstract: A system including at least three robots. Each robot including a proximity sensor unit and an imaging device. At least one robot including a processor to perform a method of estimating a pose of a human, the method including obtaining a first pose estimate for the human, the first pose estimate based on proximity sensor information, obtaining a second pose estimate for the human, the second pose estimate based on imaging device information, and generating a refined pose estimate for the human by fusing the first pose estimate with the second pose estimate, where the first pose information provides predictive values and the second pose estimate provides correction values. The method including applying a deep neural network (DNN) human model, and applying a DNN human pose model. A method to generate a refined pose estimation for a human and a non-transitory computer readable medium are also disclosed.

公开(公告)号：US20210000445A1

公开(公告)日：2021-01-07

申请号：US16458487

申请日：2019-07-01

Applicant: General Electric Company

Inventor： Huan Tan ,  Bo Wang ,  Heather Chan ,  David Martin Mills ,  Aaron Mark Dentinger ,  David Andrew Shoudy ,  Steven Robert Gray ,  John Robert Hoare

IPC: A61B8/00 ,  G01S7/52 ,  G01S15/89 ,  A61B8/08

Abstract: A robotic body scanning system includes a robotic manipulator, a force sensor, a probe, a surface sensing system, and a computing device. The probe is attached to the robotic manipulator and configured to scan the portion of the human body. The surface sensing system is configured to detect a surface of the portion of the human body and generate data representing the portion of the human body. The computing device is configured to receive data representing the portion of the human body from said surface sensing system and generate two or three-dimensional representations of the portion of the human body. The computing device includes a trajectory generation module configured to generate an adapted trajectory for the probe to follow based on the two or three-dimensional representations. The robotic manipulator is configured to move the probe along the adapted trajectory along the portion of the human body.

公开(公告)号：US20200146635A1

公开(公告)日：2020-05-14

申请号：US16184690

申请日：2018-11-08

Applicant: General Electric Company

Inventor： Bo Wang ,  Thomas Kwok-Fah Foo ,  Desmond Teck Beng Yeo ,  Jhimli Mitra

IPC: A61B5/00 ,  A61B8/08 ,  G06K9/66 ,  G06T7/37 ,  A61B8/00 ,  A61B5/055 ,  G01R33/48 ,  G01R33/56

Abstract: A method is provided. The method includes acquiring simultaneously multiple magnetic resonance (MR) images and multiple ultrasound images of an anatomical region of a subject over a scanned duration. The method also includes training an unsupervised deep learning-based deformable registration network. This training includes training a MR registration subnetwork based on the multiple MR images to generate MR deformation and transformation vectors, training an ultrasound registration subnetwork based on the multiple ultrasound images to generate ultrasound deformation and transformation vectors, and training a MR-to-ultrasound subnetwork based the multiple MR images and the multiple ultrasound images to generate MR-to-ultrasound deformation and transformation vectors between corresponding pairs of MR images and ultrasound images at each time point.

公开(公告)号：US20190219647A1

公开(公告)日：2019-07-18

申请号：US15870519

申请日：2018-01-12

Applicant: General Electric Company ,  Wisconsin Alumni Research Foundation

Inventor： Thomas Kwok-Fah Foo ,  Jhimli Mitra ,  Bo Wang ,  Lowell Scott Smith ,  David Martin Mills ,  Warren Lee ,  James Hartman Holmes ,  Bryan Bednarz ,  Roberta Marie Strigel

IPC: G01R33/28 ,  A61B8/08

CPC classification number: G01R33/285 ,  A61B6/502 ,  A61B8/0841 ,  A61B8/5269 ,  A61B10/0233 ,  A61B2090/378

Abstract: A system and method for providing virtual real-time MRI-guidance for a biopsy outside of a conventional MRI scanner is described. MR images and ultrasound images of a region of a patient's body are simultaneously acquired during a pre-biopsy procedure. Respiratory states that the patient may experience during the biopsy are then determined from the acquired ultrasound images, and each respiratory state is associated with corresponding MR images. The MR images are indexed with their corresponding respiratory state. Ultrasound images are then acquired of the patient during a biopsy procedure. The respiratory state of the patient is determined from the ultrasound images, and the corresponding indexed MR images are displayed.