Correlation and support vector machine based motion artifacts mitigation in 3D computer tomography

Abstract

Head motion during Computer Tomographic (CT) studies can adversely affects the reconstructed image through distortion and other artifacts such as blurring and doubling, thereby contributing to misdiagnosis of diseases. In this paper, we propose a method to detect and mitigate motion artifacts in three-dimensional (3D) cone-beam CT system. Motion detection is achieved by comparing the correlation coefficient between the 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 Least Square Support Vector Machine (LS-SVM) based time series prediction. The method has been evaluated on 3D Shepp-Logan phantom. In this research, Feldkamp-David-Kress (FDK) based back-projection algorithm is used for 3D reconstruction process. Computer simulation validates the motion detection and artifacts elimination mechanism.