Actively Recruiting
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