Automatic masking for robust 3D-2D image registration in image-guided spine surgery

M. D. Ketcha, T. De Silva, A. Uneri, G. Kleinszig, S. Vogt, J. P. Wolinsky, J. H. Siewerdsen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

During spinal neurosurgery, patient-specific information, planning, and annotation such as vertebral labels can be mapped from preoperative 3D CT to intraoperative 2D radiographs via image-based 3D-2D registration. Such registration has been shown to provide a potentially valuable means of decision support in target localization as well as quality assurance of the surgical product. However, robust registration can be challenged by mismatch in image content between the preoperative CT and intraoperative radiographs, arising, for example, from anatomical deformation or the presence of surgical tools within the radiograph. In this work, we develop and evaluate methods for automatically mitigating the effect of content mismatch by leveraging the surgical planning data to assign greater weight to anatomical regions known to be reliable for registration and vital to the surgical task while removing problematic regions that are highly deformable or often occluded by surgical tools. We investigated two approaches to assigning variable weight (i.e., «masking») to image content and/or the similarity metric: (1) masking the preoperative 3D CT («volumetric masking»); and (2) masking within the 2D similarity metric calculation («projection masking»). The accuracy of registration was evaluated in terms of projection distance error (PDE) in 61 cases selected from an IRB-approved clinical study. The best performing of the masking techniques was found to reduce the rate of gross failure (PDE > 20 mm) from 11.48% to 5.57% in this challenging retrospective data set. These approaches provided robustness to content mismatch and eliminated distinct failure modes of registration. Such improvement was gained without additional workflow and has motivated incorporation of the masking methods within a system under development for prospective clinical studies.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2016
Subtitle of host publicationImage-Guided Procedures, Robotic Interventions, and Modeling
EditorsRobert J. Webster, Ziv R. Yaniv
PublisherSPIE
ISBN (Electronic)9781510600218
DOIs
StatePublished - 2016
EventMedical Imaging 2016: Image-Guided Procedures, Robotic Interventions, and Modeling - San Diego, United States
Duration: Feb 28 2016Mar 1 2016

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume9786
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2016: Image-Guided Procedures, Robotic Interventions, and Modeling
CountryUnited States
CitySan Diego
Period2/28/163/1/16

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'Automatic masking for robust 3D-2D image registration in image-guided spine surgery'. Together they form a unique fingerprint.

  • Cite this

    Ketcha, M. D., De Silva, T., Uneri, A., Kleinszig, G., Vogt, S., Wolinsky, J. P., & Siewerdsen, J. H. (2016). Automatic masking for robust 3D-2D image registration in image-guided spine surgery. In R. J. Webster, & Z. R. Yaniv (Eds.), Medical Imaging 2016: Image-Guided Procedures, Robotic Interventions, and Modeling [97860A] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9786). SPIE. https://doi.org/10.1117/12.2216913