In our previous study, we focused on the motion of cervical spines in video-fluorography (VF), and we revealed that the physiological lordosises were reduced during normal swallowing. In the study, cervical spines were required to be manually extracted in all the frames of VF. Therefore the study had a difficulty in performing the statistical analysis based on a large amount of patient data. The present study proposes an automatic tracking method of cervical spines in VF by use of the two-dimensional template matching technique. In the method, cervical spines can be extracted automatically, though templates should be set manually only in the first frame of VF. The automatic tracking method was applied to cervical spines, from C1 to C6, in actual VF of ten cases who were planned to undergo posterior cervical spinal fusion. The cervical spines were able to be tracked at the accuracy of more than 77% in the Jaccard index. The experimental results demonstrated that the proposed method was able to analyze the motion of cervical spines in VF during swallowing.
CITATION STYLE
Mekata, K., Takizawa, H., Takigawa, T., Toda, K., Ito, Y., & Kudo, H. (2018). Template-matching-based tracking of cervical spines in videofluorography during swallowing. In Smart Innovation, Systems and Technologies (Vol. 71, pp. 185–191). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-59397-5_20
Mendeley helps you to discover research relevant for your work.