Intraoperative localized constrained registration in navigated bronchoscopy

Hofstad, Erlend Fagertun; Sorger, Hanne; Bakeng, Janne Beate Lervik; Gruionu, Lucian Gheorghe; Leira, Håkon Lasse; Amundsen, Tore; Langø, Thomas

doi:10.1002/mp.12361

Cited by 15 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rojas-Solano et al robotic technology being applied to assist bronchoscopy [7,8], but none yet in the realms of tracheal intubation. These reports, along with the data presented by Biro et al [3], raise a number of questions relating to feasibility and clinical relevance.…”

Section: Airway Robotsmentioning

confidence: 99%

“…This included: the continuous visualisation of suspected lesions; the precise control of the bronchoscope's movements; the locking capability of the bronchoscope; and thorough training of the participants before starting the study. There are other examples of robotic technology being applied to assist bronchoscopy[7,8], but none yet in the realms of tracheal intubation.These reports, along with the data presented by Biro et al[3], raise a number of questions relating to feasibility and clinical relevance. For example, if robot-assisted tracheal intubation were to be implemented, would it lead to a significant step change in safety of airway management,…”

mentioning

confidence: 99%

See 1 more Smart Citation

Embracing the robotic revolution into anaesthetic practice

2020

View full text Add to dashboard Cite

Section: Airway Robotsmentioning

confidence: 99%

mentioning

confidence: 99%

Embracing the robotic revolution into anaesthetic practice

2020

View full text Add to dashboard Cite

“…The distance bias of landmark points is commonly utilized to evaluate the spatial accuracy of registration algorithms. 17,18 Matching Points Annotator (MPA), a publicly available semi-automatic landmark annotation software program, 19,20 was used to define and record landmark points from two images. The EE phase CT image was used to generate the reference point set.…”

Section: C Landmark Annotationmentioning

confidence: 99%

Thorax x‐ray and CT interventional dataset for nonrigid 2D/3D image registration evaluation

Wei

Jin

et al. 2018

Medical Physics

View full text Add to dashboard Cite

Purpose The aim of this paper is to provide a novel, publicly available standard image dataset with a useful evaluation framework for assessing nonrigid two‐/three‐dimensional (2D/3D) registration algorithms. Acquisition and validation methods A pig lung model was used to obtain the image dataset. Inflated with different amounts of oxygen, a sequence of 3D volume data was acquired with computed tomography (CT), which ideally simulated different respiratory phases. With the model inflated and kept in certain states, 3D CT, 2D CT scout image and 2D x‐ray were acquired for the same respiratory phases, making them suitable to establish the evaluation dataset for 2D/3D registration algorithms. A total of 120 well‐distributed landmarks in every 3D volume were manually annotated and checked by several radiologists using semi‐automatic software to generate the dataset. Data format and usage notes All 3D image data were stored in both DICOM and ITK Meta format, and 2D image data were stored in DICOM format. A total of 120 landmarks were manually annotated for each 3D image. Among these landmarks, eight landmarks located on large branch of the bronchial tree were also annotated in 2D images. The landmark coordinates were stored in a text file. The detailed usage including a standard evaluation framework for the proposed dataset is also provided. The dataset can be downloaded from the Zenodo repository (https://doi.org/10.5281/zenodo.997887). Potential applications Our standard dataset was acquired with advanced clinical imaging devices and is quite suitable for quantitatively evaluating state‐of‐art, nonrigid 2D/3D registration algorithms.

show abstract

“…One way to achieve this is to register electromagnetic (EM) tracking data captured from the bronchoscope to the segmented airway tree of the pre-operative CT-scan [24,10,14]. In addition to the sensory errors caused by electromagnetic distortion, anatomical deformations are a principal challenge for EM-based approaches.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation

Karaoglu¹,

Brasch²,

Stollenga³

et al. 2021

Preprint

View full text Add to dashboard Cite

Depth estimation from monocular images is an important task in localization and 3D reconstruction pipelines for bronchoscopic navigation. Various supervised and self-supervised deep learning-based approaches have proven themselves on this task for natural images. However, the lack of labeled data and the bronchial tissue's feature-scarce texture make the utilization of these methods ineffective on bronchoscopic scenes. In this work, we propose an alternative domain-adaptive approach. Our novel two-step structure first trains a depth estimation network with labeled synthetic images in a supervised manner; then adopts an unsupervised adversarial domain feature adaptation scheme to improve the performance on real images. The results of our experiments show that the proposed method improves the network's performance on real images by a considerable margin and can be employed in 3D reconstruction pipelines.

show abstract

Intraoperative localized constrained registration in navigated bronchoscopy

Cited by 15 publications

References 21 publications

Embracing the robotic revolution into anaesthetic practice

Embracing the robotic revolution into anaesthetic practice

Thorax x‐ray and CT interventional dataset for nonrigid 2D/3D image registration evaluation

Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation

Contact Info

Product

Resources

About