Monocular Vision‐Based Endoscopic Sinus Navigation: A SLAM Driven Approach With CT Integration
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".