Monocular Vision‐Based Endoscopic Sinus Navigation: A SLAM Driven Approach With CT Integration
Healthcare Technology Letters · 2025-01 · 12 (1)
DOI: 10.1049/htl2.70046 ↗Kurz gefasst
Fachartikel in der Zeitschrift Healthcare Technology Letters, online erschienen am 09.12.2025. Verfasst von Roger D Soberanis-Mukul und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science Johns Hopkins University Baltimore USA. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIBIB NIH HHS, All of Us Research Program, Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Surgical navigation is critical in sinus surgery to enhance the surgeon's spatial awareness and improve precision, particularly around occluded critical structures. While external tracker‐based navigation systems exist, vision‐based solutions are preferred for being less intrusive and for enabling endoscopic image analysis to assist surgeons. However, monocular endoscopy navigation faces challenges associated with monocular reconstruction and camera pose estimation. This paper presents a proof of concept for monocular vision‐based sinus navigation that utilizes only preoperative CT data and the endoscope video stream to navigate the sinus anatomy. We developed a vision‐based navigation system that incorporates a SLAM algorithm to estimate the camera pose and reconstruct the 3D surface of the anatomy. Given an initial semi‐automated registration, the algorithm maps the SLAM‐based trajectories to the CT space while employing the reconstructed point cloud to solve for the scale interactively. The system displays the updates in the CT triplane visualization as SLAM reconstructs the scene and recovers pose information. We tested our system by performing an off‐site navigation in ten recorded endoscopic video streaming generated from sequences obtained from eight cadaveric subjects, comparing the vision‐based navigation to reference optical tracker pose data and obtaining translation and rotation errors of 3.2 mm and 4.9 degrees, respectively. Additionally, we performed three on‐site tests of our system on two different cadaver experiments. Our work evaluates a fully integrated system that closes the loop between image‐based reconstruction and CT visualization, and discusses the challenges to address to achieve clinical level surgical navigation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Science Johns Hopkins University Baltimore USA.
- Department of Cardiothoracic Surgery Stanford University School of Medicine California USA.
- Department of Otolaryngology, Head and Neck Surgery Johns Hopkins Medical Institutions Baltimore USA.
ORCID-Profile: Roger D Soberanis-Mukul, Jan Emily Mangulabnan, Lalithkumar Seenivasan, Mohammad Salehizadeh, S Swaroop Vedula, Russell H Taylor, Gregory Hager, Mathias Unberath
Förderung
- NIBIB NIH HHS
- All of Us Research Program
- Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada
Zitieren
APA
Soberanis-Mukul, R. D., Chan, C. H. R., Chou, R., Mangulabnan, J. E., Seenivasan, L., Chen, X., Salehizadeh, M., Vedula, S. S., Taylor, R. H., Ishii, M., Hager, G., & Unberath, M. (2025). Monocular Vision‐Based Endoscopic Sinus Navigation: A SLAM Driven Approach With CT Integration. Healthcare Technology Letters, 12(1). https://doi.org/10.1049/htl2.70046
Vancouver
Soberanis-Mukul RD, Chan CHR, Chou R, Mangulabnan JE, Seenivasan L, Chen X, et al. Monocular Vision‐Based Endoscopic Sinus Navigation: A SLAM Driven Approach With CT Integration. Healthcare Technology Letters. 2025;12(1). doi:10.1049/htl2.70046
BibTeX
@article{SoberanisMukul2025,
author = {Soberanis-Mukul, Roger D and Chan, Chin Hang Ryan and Chou, Ryan and Mangulabnan, Jan Emily and Seenivasan, Lalithkumar and Chen, Xingyu and Salehizadeh, Mohammad and Vedula, S Swaroop and Taylor, Russell H and Ishii, Masaru and Hager, Gregory and Unberath, Mathias},
title = {Monocular Vision‐Based Endoscopic Sinus Navigation: A SLAM Driven Approach With CT Integration},
journal = {Healthcare Technology Letters},
year = {2025},
volume = {12},
number = {1},
doi = {10.1049/htl2.70046}
}
EUVIMED