• DocumentCode
    2508058
  • Title

    A correlation and LS-SVM based approach to mitigate motion artifacts in FDK based 3D cone-beam tomography

  • Author

    Bhowmik, Ujjal Kumar ; Adhami, Reza R.

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Univ. of Alabama in Huntsville, Huntsville, AL, USA
  • fYear
    2011
  • fDate
    Aug. 30 2011-Sept. 3 2011
  • Firstpage
    8471
  • Lastpage
    8474
  • Abstract
    Head motion during brain CT studies can degrade the reconstructed image by introducing distortion and loss of resolution, thereby contributing to misdiagnosis of diseases. In this paper, we have proposed a correlation coefficient and Least Squares Support Vector Machines (LS-SVM) based approach to detect and mitigate motion artifacts in FDK based three-dimensional cone-beam tomography. Motion is detected using correlation between adjacent x-ray projections. Artifacts, caused by motion, are mitigated either by replacing motion corrupted projections with their counterpart 180° apart projections under certain conditions, or by estimating motion corrupted projections using LS-SVM based time series prediction. The method has been evaluated on 3D Shepp-Logan phantom. Simulation results validate our claims.
  • Keywords
    computerised tomography; correlation methods; image reconstruction; image resolution; least squares approximations; medical image processing; motion compensation; phantoms; support vector machines; time series; 3D Shepp-Logan phantom; FDK based 3D cone-beam tomography; LS-SVM based approach; LS-SVM based time series prediction; adjacent X-ray projections; brain CT; correlation based approach; disease misdiagnosis; head motion; least squares support vector machine based approach; motion artifacts; reconstructed image; Computed tomography; Detectors; Ellipsoids; Head; Image reconstruction; Phantoms; Three dimensional displays; FDK; LS-SVM; Motion Artifacts; Motion Detection; Three-dimensional CT; Time series prediction; Algorithms; Artifacts; Cone-Beam Computed Tomography; Imaging, Three-Dimensional; Least-Squares Analysis; Motion; Phantoms, Imaging; Rotation; Support Vector Machines;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE
  • Conference_Location
    Boston, MA
  • ISSN
    1557-170X
  • Print_ISBN
    978-1-4244-4121-1
  • Electronic_ISBN
    1557-170X
  • Type

    conf

  • DOI
    10.1109/IEMBS.2011.6092090
  • Filename
    6092090