Endoscopic navigation in the clinic: registration in the absence of preoperative imaging

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Purpose : Clinical examinations that involve endoscopic exploration of the nasal cavity and sinuses often do not have a reference preoperative image, like a computed tomography (CT) scan, to provide structural context to the clinician. The aim of this work is to provide structural context during clinical exploration without requiring additional CT acquisition. Methods : We present a method for registration during clinical endoscopy in the absence of CT scans by making use of shape statistics from past CT scans. Using a deformable registration algorithm that uses these shape statistics along with dense point clouds from video, we simultaneously achieve two goals: (1) register the statistically mean shape of the target anatomy with the video point cloud, and (2) estimate patient shape by deforming the mean shape to fit the video point cloud. Finally, we use statistical tests to assign confidence to the computed registration. Results : We are able to achieve submillimeter errors in registrations and patient shape reconstructions using simulated data. We establish and evaluate the confidence criteria for our registrations using simulated data. Finally, we evaluate our registration method on in vivo clinical data and assign confidence to these registrations using the criteria established in simulation. All registrations that are not rejected by our criteria produce submillimeter residual errors. Conclusion : Our deformable registration method can produce submillimeter registrations and reconstructions as well as statistical scores that can be used to assign confidence to the registrations.

Original languageEnglish (US)
Pages (from-to)1495-1506
Number of pages12
JournalInternational Journal of Computer Assisted Radiology and Surgery
Issue number9
StatePublished - Sep 1 2019


  • Deformable registration
  • Navigation for clinical endoscopy
  • Registration confidence
  • Shape estimation
  • Statistical shape models

ASJC Scopus subject areas

  • Health Informatics
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Surgery
  • Biomedical Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Endoscopic navigation in the clinic: registration in the absence of preoperative imaging'. Together they form a unique fingerprint.

Cite this