Journal DOI 10.68956/journal.human-performance-futures

Creative Commons source reading · Machine learning for performance

Artificial Intelligence in Pulmonary Endoscopy: Current Evidence, Limitations, and Future Directions

Lopes S; Mascarenhas M; Fonseca J; Leite-Moreira AF

Originally published in J Imaging · 2026-04-12

From the article

Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.

Abstract

AbstractBackground: Artificial intelligence (AI) is increasingly applied in pulmonary endoscopy, including diagnostic bronchoscopy, interventional pulmonology and endobronchial imaging. Advances in computer vision, machine learning and robotic systems have expanded the potential for automated lesion detection, navigation to peripheral pulmonary lesions, and real-time procedural support. However, the current evidence base remains heterogeneous, and translational challenges persist. Methods: This review summarizes current applications and developments of AI across white-light bronchoscopy (WLB), image-enhanced bronchoscopy (e.g., narrow-band imaging and autofluorescence imaging), endobronchial ultrasound (EBUS), virtual and robotic bronchoscopies, and workflow optimization and training. The authors also examine the methodological…

7.2. Multi-Omic Predictive Models Linked to Endoscopic Findings

Future AI systems are likely to combine endoscopic imaging with radiologic, pathologic and molecular data. Integration of radiomics, digital pathology and genomic or transcriptomic information may support more refined risk stratification and personalized decision-making, particularly in LC [28,53]. Tissue obtained via advanced sampling techniques, such as cryobiopsy, may facilitate these computational approaches.

8. Conclusions and Discussion

AI is increasingly being applied in pulmonary endoscopy, with developments in image enhancement, lesion detection, navigation, staging, and procedural support. These approaches have the potential to improve diagnostic consistency, reduce operator variability, and support training in complex bronchoscopic and EBUS procedures. In particular, AI-assisted bronchoscopy and EBUS may help address challenges related to subtle mucosal disease, peripheral lesion targeting, and variability in mediastinal staging. However, the current evidence base remains limited. Most studies are retrospective, single-center, and focused on technical performance rather than clinical outcomes. Reported performance metrics in AI studies, such as accuracy and AUC, do not fully reflect real-world clinical utility. These metrics are typically derived from…

Editorial reading guide

  • What data created and tested the model, and was evaluation independent?
  • What is the cost of a false positive, false negative or out-of-distribution decision?