Automatic Tracking of Cervical Spine using Fluoroscopic Sequences

In this paper an automatic tracking approach is proposed for the measurement of the cervical spine using Kanade-Lucas-Tomasi (KLT) feature tracking algorithm through fluoroscopic sequences. Previous research related to cervical vertebrae shows that abnormalities in the cervical vertebrae structures may affect the movement of the cervical spine. The aim of this paper is to automate the detection of range of movement in a lateral view of the spine during a flexion-extension cycle. The parameters analyzed were translation and in-plane rotation of the individual vertebrae. For analysis of these parameters, fluoroscopic recordings of three individuals were used. The algorithm marked landmarks on first frame, considered them as reference position and extracted translation and rotation of these vertebrae landmarks in the successive frames using Harris corner detector and use link motion vector for trajectory. Manual selection of vertebrae C3 to C6 (annotated data) were used for the validation of the proposed algorithm. The automated results are very close and uniform to the manual selection.