Automatic detection of patient motion in cone-beam computed tomography

Abstract

Some computed tomography (CT) applications, for example micro- or dental-CT, have long acquisition sequences and consequently motion of the object is likely to occur. The common motion correction method, not using optical techniques for patient motion measurement, is data-driven motion-correction (DDMC). This method is based on subdivision of the projection data into motion free subsections. Therefore, motion positions have to be determined. In this work, an approach for motion position detection in cone-beam CT data is described. Distance metric values, computed from two successive projection images, provide information of the incorporation of movement. Quantitative evaluation of motion detection is possible due to utilization of CT data with known movement positions, using generated dental cone-beam CT datasets. The proposed method uses nothing but information contained in the cone-beam projections. Therefore, it is generally applicable for motion detection in cone-beam CT. A correct detection rate of 99.89% is achieved by using a structural similarity index as a distance measure.