Saved in:
Bibliographic Details
Main Authors: Shu, Hongchao, Soberanis-Mukul, Roger D., Xu, Jiru, Ding, Hao, Ringel, Morgan, Shen, Mali, Sayed, Saif Iftekar, Rafii-Tari, Hedyeh, Unberath, Mathias
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.09443
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915613048307712
author Shu, Hongchao
Soberanis-Mukul, Roger D.
Xu, Jiru
Ding, Hao
Ringel, Morgan
Shen, Mali
Sayed, Saif Iftekar
Rafii-Tari, Hedyeh
Unberath, Mathias
author_facet Shu, Hongchao
Soberanis-Mukul, Roger D.
Xu, Jiru
Ding, Hao
Ringel, Morgan
Shen, Mali
Sayed, Saif Iftekar
Rafii-Tari, Hedyeh
Unberath, Mathias
contents Accurate intra-operative localization of the bronchoscope tip relative to patient anatomy remains challenging due to respiratory motion, anatomical variability, and CT-to-body divergence that cause deformation and misalignment between intra-operative views and pre-operative CT. Existing vision-based methods often fail to generalize across domains and patients, leading to residual alignment errors. This work establishes a generalizable foundation for bronchoscopy navigation through a robust vision-based framework and a new synthetic benchmark dataset that enables standardized and reproducible evaluation. We propose a vision-based pose optimization framework for frame-wise 2D-3D registration between intra-operative endoscopic views and pre-operative CT anatomy. A fine-tuned modality- and domain-invariant encoder enables direct similarity computation between real endoscopic RGB frames and CT-rendered depth maps, while a differentiable rendering module iteratively refines camera poses through depth consistency. To enhance reproducibility, we introduce the first public synthetic benchmark dataset for bronchoscopy navigation, addressing the lack of paired CT-endoscopy data. Trained exclusively on synthetic data distinct from the benchmark, our model achieves an average translational error of 2.65 mm and a rotational error of 0.19 rad, demonstrating accurate and stable localization. Qualitative results on real patient data further confirm strong cross-domain generalization, achieving consistent frame-wise 2D-3D alignment without domain-specific adaptation. Overall, the proposed framework achieves robust, domain-invariant localization through iterative vision-based optimization, while the new benchmark provides a foundation for standardized progress in vision-based bronchoscopy navigation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_09443
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BronchOpt : Vision-Based Pose Optimization with Fine-Tuned Foundation Models for Accurate Bronchoscopy Navigation
Shu, Hongchao
Soberanis-Mukul, Roger D.
Xu, Jiru
Ding, Hao
Ringel, Morgan
Shen, Mali
Sayed, Saif Iftekar
Rafii-Tari, Hedyeh
Unberath, Mathias
Computer Vision and Pattern Recognition
Artificial Intelligence
Accurate intra-operative localization of the bronchoscope tip relative to patient anatomy remains challenging due to respiratory motion, anatomical variability, and CT-to-body divergence that cause deformation and misalignment between intra-operative views and pre-operative CT. Existing vision-based methods often fail to generalize across domains and patients, leading to residual alignment errors. This work establishes a generalizable foundation for bronchoscopy navigation through a robust vision-based framework and a new synthetic benchmark dataset that enables standardized and reproducible evaluation. We propose a vision-based pose optimization framework for frame-wise 2D-3D registration between intra-operative endoscopic views and pre-operative CT anatomy. A fine-tuned modality- and domain-invariant encoder enables direct similarity computation between real endoscopic RGB frames and CT-rendered depth maps, while a differentiable rendering module iteratively refines camera poses through depth consistency. To enhance reproducibility, we introduce the first public synthetic benchmark dataset for bronchoscopy navigation, addressing the lack of paired CT-endoscopy data. Trained exclusively on synthetic data distinct from the benchmark, our model achieves an average translational error of 2.65 mm and a rotational error of 0.19 rad, demonstrating accurate and stable localization. Qualitative results on real patient data further confirm strong cross-domain generalization, achieving consistent frame-wise 2D-3D alignment without domain-specific adaptation. Overall, the proposed framework achieves robust, domain-invariant localization through iterative vision-based optimization, while the new benchmark provides a foundation for standardized progress in vision-based bronchoscopy navigation.
title BronchOpt : Vision-Based Pose Optimization with Fine-Tuned Foundation Models for Accurate Bronchoscopy Navigation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.09443