Embedded Files
This work is a collaboration between the RoPeRT research lab from Universidad de Zaragoza and Hospital Universitario Miguel Servet, Zaragoza.
Participants: Clara Tomasini, Javier Rodríguez-Puigvert, Dinora Polanco, Manuel Viñuales, Luis Riazuelo, Ana C. Murillo.
Brief Description
Brief Description
Subglottic stenosis refers to the narrowing of the subglottis, the airway between the vocal cords and the trachea. Its severity is typically evaluated by estimating the percentage of obstructed airway. In this project, we demonstrate how to automate the evaluation of subglottic stenosis severity using only bronchoscopy. Our approach can assist with and shorten the diagnosis and monitoring procedures, with automated and repeatable measurements and less exploration time, and save radiation exposure to patients as no CT is required. Additionally, we release the first public benchmark for subglottic stenosis severity assessment.
We propose a pipeline for automated subglottic stenosis severity estimation during the bronchoscopy exploration, without requiring the physician to traverse the stenosed region. Our approach exploits the physical effect of illumination decline in endoscopy to segment and track the lumen and obtain a 3D model of the airway. This 3D model is obtained from a single frame and is used to measure the airway narrowing.
The results show consistency with ground-truth estimations from CT scans and expert estimations, and reliable repeatability across multiple measurements on the same patient. Our evaluation is performed on our new Subglottic Stenosis Dataset of real bronchoscopy procedures data.
Subglottic Stenosis Dataset
Subglottic Stenosis Dataset
Publication: Tomasini, C., Rodriguez-Puigvert, J., Polanco, D., Viñuales, M., Riazuelo, L., & Murillo, A. C. (2025). Automated vision-based assistance tools in bronchoscopy: stenosis severity estimation. International Journal of Computer Assisted Radiology and Surgery, 1-8. [paper] [arxiv]
Data and annotations [Dataset]
Code (Data use + Lumen segmentation & tracking (step 1)) [github]
Page updated
Report abuse