Neural Radiance Fields (NeRF) for 3D Reconstruction of Monocular Endoscopic Video in Sinus Surgery
Otolaryngology–Head and Neck Surgery · 2025-04 · 172 (4) · 1435-1441
DOI: 10.1002/ohn.1105 ↗Kurz gefasst
Fachartikel in der Zeitschrift Otolaryngology–Head and Neck Surgery, online erschienen am 10.01.2025. Verfasst von Jeremy S Ruthberg und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology-Head and Neck Surgery, University of Washington, Seattle, Washington, USA. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional, Endoscopy, Paranasal Sinuses. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDCD NIH HHS.
Abstract (Originalsprache)
Objective
To validate the use of neural radiance fields (NeRF), a state‐of‐the‐art computer vision technique, for rapid, high‐fidelity 3‐dimensional (3D) reconstruction in endoscopic sinus surgery (ESS). Study Design An experimental cadaveric pilot study.
Setting
Academic medical center.
Methods
Complete bilateral endoscopic sinus surgery was performed on 3 cadaveric specimens, followed by postsurgical nasal endoscopy using a 0° rigid endoscope. NeRF was utilized to generate 3D reconstructions from the monocular endoscopic video feed. Reconstructions were calibrated, scaled, and then co‐registered to postoperative computed tomography (CT) image sets to assess accuracy. Reconstruction error was determined by comparing ethmoid sinus measurements on NeRF reconstructions and CT image sets.
Results
NeRF‐based 3D scene reconstructions were successfully generated and co‐registered to corresponding CT images for 5 out of 6 cadaveric nasal cavity sides. The mean reconstruction errors and standard error of the mean (SEM) for ethmoid length and height were 0.17 (SEM 0.59) and 0.70 (SEM 0.44) mm, respectively.
Conclusion
NeRF demonstrates significant potential for dynamic, high‐fidelity 3D surgical field reconstruction in ESS, offering submillimeter accuracy comparable to postoperative CT data in cadaveric specimens. This innovative approach may ultimately augment dynamic real‐time intraoperative navigation through co‐registration of the 3D reconstruction with preoperative imaging to potentially reduce the risk of injury to critical structures, optimize surgical completeness and, thereby, improve surgical outcomes. Further refinement and validation in live surgical settings are necessary to fully realize its clinical utility.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Otolaryngology-Head and Neck Surgery, University of Washington, Seattle, Washington, USA.
- Department of Mechanical Engineering, University of Washington, Seattle, Washington, USA.
- School of Medicine, University of Washington, Seattle, Washington, USA.
ORCID-Profile: Jeremy S Ruthberg
Förderung
- NIDCD NIH HHS
Zitieren
APA
Ruthberg, J. S., Bly, R., Gunderson, N., Chen, P., Alighezi, M., Seibel, E. J., & Abuzeid, W. M. (2025). Neural Radiance Fields (NeRF) for 3D Reconstruction of Monocular Endoscopic Video in Sinus Surgery. Otolaryngology–Head and Neck Surgery, 172(4), 1435-1441. https://doi.org/10.1002/ohn.1105
Vancouver
Ruthberg JS, Bly R, Gunderson N, Chen P, Alighezi M, Seibel EJ, et al. Neural Radiance Fields (NeRF) for 3D Reconstruction of Monocular Endoscopic Video in Sinus Surgery. Otolaryngology–Head and Neck Surgery. 2025;172(4):1435-1441. doi:10.1002/ohn.1105
BibTeX
@article{Ruthberg2025,
author = {Ruthberg, Jeremy S and Bly, Randall and Gunderson, Nicole and Chen, Pengcheng and Alighezi, Mahdi and Seibel, Eric J and Abuzeid, Waleed M},
title = {Neural Radiance Fields (NeRF) for 3D Reconstruction of Monocular Endoscopic Video in Sinus Surgery},
journal = {Otolaryngology–Head and Neck Surgery},
year = {2025},
volume = {172},
number = {4},
pages = {1435--1441},
doi = {10.1002/ohn.1105}
}
EUVIMED