×

SYSTEM AND METHOD FOR MOTION ESTIMATION USING ARTIFICIAL INTELLIGENCE IN HELICAL COMPUTED TOMOGRAPHY

  • US 20190328341A1
  • Filed: 05/14/2019
  • Published: 10/31/2019
  • Est. Priority Date: 11/16/2016
  • Status: Active Grant
First Claim
Patent Images

1. A method for estimating and compensating for motion by reducing motion artifacts in an image reconstruction from helical computed tomography (CT) scan data of an object of interest, the method comprising:

  • collecting helical computer tomography (CT) scan data of an object of interest, wherein the scan data is acquired using a radiation source to generate a cone beam and a radiation detector to detect the cone beam;

    selecting a plurality of center-points along a trajectory of the radiation source;

    identifying a plurality of pairs of sections along the trajectory of the radiation source, wherein each of the plurality of pairs of sections is associated with one of the plurality of center-points and wherein a first section of each of the pairs of sections and a second section of each of the pairs of sections are positioned on opposite sides of the center-point;

    selecting a subset of the plurality of pairs of sections;

    reconstructing, for each pair of the subset, a first partial image from the scan data of the first section and a second partial image from the scan data of the second section;

    performing image registration of the first partial image and the second partial image for each pair of the subset to estimate a deformation that transforms the first partial image into the second partial image, wherein the deformation is representative of motion of the object of interest during the scan and wherein the image registration is performed using an artificial intelligence based method; and

    generating a motion compensated image by reconstructing the object of interest using the scan data and the estimated deformation.

View all claims
  • 3 Assignments
Timeline View
Assignment View
    ×
    ×