Augmented Endobronchial Ultrasound (EBUS-TBNA) With Artificial Intelligence

Automatic Segmentation of Mediastinal Lymph Nodes and Blood Vessels in Endobronchial Ultrasound (EBUS) Images Using a Deep Neural Network

To evaluate the usefulness of Deep neural network (DNN) in the evaluation of mediastinal and hilar lymph nodes with Endobronchial ultrasound (EBUS). The study will explore the feasibility of DNN to identify lymph nodes and blood vessel examined with EBUS.

Study Overview

• Status: Recruiting
• Conditions: Lung Cancer; Artificial Intelligence; Endobronchial Ultrasound
• Intervention / Treatment: Device: machine learning algorithm

Detailed Description

Multi-center prospective feasibility study. The DNN model will be trained on ultrasound images with annotation to identifies lymph nodes and blood vessels examined with EBUS. The ability of the DNN to segment lymph nodes and vessels based on postoperative processing and static EBUS images will be evaluated in the first part of the study. In the second part of the study Real-time use of DNN in EBUS procedure will be evaluated.

• Study Type: Observational
• Enrollment (Estimated): 50

Contacts and Locations

• Study Contact: Name: Øyvind Ervik, MD; Phone Number: +4791634595; Email: oyvind.ervik@ntnu.no
• Study Contact Backup: Name: Hanne Sorger, MD,PhD; Phone Number: +4791816787; Email: hanne.sorger@ntnu.no

Study Locations

• Norway
  • Levanger, Norway, 7600
    • Recruiting
    • Department of Pulmonology, Levanger Hospital, North Trøndelag Hospital Trust
    • Contact: Øyvind Ervik, MD; Phone Number: +4791634595; Email: oyvind.ervik@ntnu.no
  • Trondheim, Norway, 7030
    • Recruiting
    • Department of Thoracic Medicine, St Olavs Hospital
    • Contact: Håkon O Leira, MD, PhD; Phone Number: +4799014967; Email: håkon.o.leira@ntnu.no

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patents with undiagnosed enlarged mediastinal and hilar lymph nodes who have been recommended for Endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA).

Description

Inclusion Criteria:

• Subjects referred to thoracic department in any of the participating hospitals with undiagnosed enlarged mediastinal and hilar lymph nodes.
• Subjects have to be ≥ 18 years of age

Exclusion Criteria:

• Pregnancy
• Any patient that the Investigator feels is not appropriate for this study for any reason.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Capability	To explore if Deep neural network (DNN) has capability to segment lymph nodes and blood vessels from EBUS images	8 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Precision	The precision the DNN has for detecting lymph nodes and blood vessels. Measured both per voxel in the EBUS images and per annotated structure (a structure is counted as detected if at least 50% of its annotated pixels are identified by the DNN).	2 months
Sensitivity	True positive rate. Correctly detected lymph nodes/blood vessel over total lymph nodes/blood vessel. Measured per pixel in the EBUS images	2 months
Specificity	Specificity = (True Negative)/(True Negative + False Positive). Measured per pixel in the EBUS images.	2 months
Dice similarity coefficient	Measures the similarity between two sets of data: Annotated by pulmonologist vs DNN.	2 months
Run-time	Is the run-time sufficiently low for real-time analysis during EBUS?	2 months
Adverse events	Procedure related adverse events or unexpected incidents registered	48 hours

Collaborators and Investigators

• Sponsor: Norwegian University of Science and Technology
• Collaborators: Helse Nord-Trøndelag HF; SINTEF Health Research
• Investigators: Study Director: Øivind Rognmo, Dr.philos, Norwegian University of Science and Technology

Study record dates

Study Major Dates

• Study Start (Actual): May 1, 2023
• Primary Completion (Estimated): May 1, 2027
• Study Completion (Estimated): December 1, 2027

Study Registration Dates

• First Submitted: February 13, 2023
• First Submitted That Met QC Criteria: February 13, 2023
• First Posted (Actual): February 22, 2023

Study Record Updates

• Last Update Posted (Actual): August 22, 2025
• Last Update Submitted That Met QC Criteria: August 18, 2025
• Last Verified: June 1, 2025

More Information

Terms related to this study

• Other Study ID Numbers: 240245

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No