A Comparison of 2D-3D Intensity-Based Registration and Feature-Based Registration for Neurointerventions

Robert A. McLaughlin, John H. Hipwell, David J. Hawkes, J. Alison Noble, James V. Byrne, Tim C. S. Cox

Abstract

Registration of 2D-3D data can improve visualisation during minimally-invasive neurointerventions. Using four clinical data sets, we quantitatively compared two approaches: an intensity-based algorithm and a feature-based algorithm. The intensity-based approach was found to be more accurate, with an average registration accuracy of 1.4mm, compared to the feature-based algorithm with an average accuracy of 2.3mm. The intensity-based algorithm was also found to be more reliable. Reliability of the feature-based algorithm was found to be more sensitive to the complexity of the vasculature structure.
BibTeX
@inproceedings{mclaughlin2002comparison,
  author = {Robert A. McLaughlin and John H. Hipwell and David J. Hawkes and J. Alison Noble and James V. Byrne and Tim C. S. Cox},
  title = {{A Comparison of 2D-3D Intensity-Based Registration and Feature-Based Registration for Neurointerventions}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2002},
  doi = {10.1007/3-540-45787-9\_65},
}
Figure