+1 877 705 1914• 24 / 7
HIPAA Compliant
ISO 27001 Certified

Actively Recruiting

Age: 18Years +
All Genders
ID05739331

Evaluating Deep Neural Network for Automatic Identification of Lymph Nodes and Blood Vessels During Endobronchial Ultrasound in Lung Cancer

Led by Norwegian University of Science and Technology · Updated on 2026-09-30

50

Participants Needed

2

Research Sites

30 weeks

Total Duration

AI-Summary

What This Trial Is About

Researchers are exploring the use of a Deep Neural Network DNN to improve the evaluation of mediastinal and hilar lymph nodes during Endobronchial Ultrasound EBUS procedures. This study aims to assess how well the DNN can identify lymph nodes and blood vessels in ultrasound images, which may aid in diagnosing conditions like lung cancer. The study is a multi-center, prospective feasibility study focused on artificial intelligence applications in medical imaging. The study has two main parts. First, the DNN model will be trained and tested on static ultrasound images with annotations to detect lymph nodes and blood vessels after the procedure. In the second part, the DNN will be used in real-time during EBUS procedures to label lymph nodes and their levels. The intervention involves running a machine learning algorithm on EBUS images to assist in real-time identification. Participants referred to thoracic departments with undiagnosed enlarged lymph nodes will be involved. Various measures will be taken to evaluate the DNNs performance, including capability, precision, sensitivity, specificity, Dice similarity coefficient, and run-time. Adverse events will be recorded within 48 hours after procedures. The study spans from May 2023 to December 2027, with ongoing assessments to monitor the technologys accuracy and safety.

CONDITIONS

Brief Title

Augmented Endobronchial Ultrasound (EBUS-TBNA) With Artificial Intelligence

Research Team

Ø

Øyvind Ervik, MD

H

Hanne Sorger, MD,PhD

Not the Right Trial for You?

Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.

Already have an account? Log in here