MADRID — Artificial intelligence (AI) can enhance endobronchial ultrasound (EBUS) image processing and new techniques such as cryoEBUS to achieve significant diagnostic and prognostic breakthroughs in interventional pulmonology and general pulmonology.
Pulmonologists are witnessing a surge in new technologies for endoscopy and pulmonology in general. Some, such as AI, robotic bronchoscopy, radiomics, or improvements in electromagnetic bronchial navigation, are minimally invasive diagnostic techniques that significantly enhance the characterization of lung lesions, said Virginia Pajares, MD, a member of the Catalan Society of Pulmonology and coordinator of the Bronchoscopy Unit at Hospital de Sant Pau in Barcelona, Spain. She spoke at the XLI Pneumological Day of the Catalan Society of Pulmonology in Vilanova i la Geltrú, Spain.
Regarding AI, pulmonologists “already have platforms that enable the calculation of the malignancy risk of lung lesions and mediastinal adenopathies. In addition, some devices that allow for an initial radiological assessment of lung nodules are starting to be used,” said Dr. Pajares.
Radiomics: Histology and Markers
“At an endoscopic level, some studies have confirmed the ability of AI applied to imaging to differentiate between benign and malignant lesions, although currently the studies are limited and in the initial stages,” said Dr. Pajares. “AI in interventional pulmonology will be highly beneficial in image interpretation and patient assessment for those who require more invasive diagnostic techniques or for follow-up.”
Regarding the application of AI in medicine, “we lack knowledge and require specific training, especially concerning the learning curve of different technologies, such as electromagnetic navigation, cryoEBUS, or robotic bronchoscopy, which require significant training efforts,” said Dr. Pajares. “The use of AI without a specific goal, that is, creating a mathematical algorithm and feeding it with clinical patient data without control and validation, can lead to inaccurate conclusions. Additionally, we need to determine how to input patient data into these systems to avoid ethical issues, and, of course, legislation on this matter is essential.”
Electromagnetic Navigation
Bronchial electromagnetic navigation is a bronchoscopic technique that allows access to peripheral lung lesions. “It involves virtual route planning using the patient’s chest CT scan and subsequently performing bronchoscopy with navigation using a dirigible electromagnetic probe that allows access to the lesion,” Dr. Pajares explained. “Currently, we have navigators that can incorporate imaging techniques (fluoroscopy or cone-beam CT) to immediately correct discrepancies observed during navigation.”
These new technologies enable a greater number of precise diagnoses and may bring greater patient safety. Studies like NAVIGATE, which was published in 2022 by Folch and colleagues, confirm the diagnostic possibilities and performance of electromagnetic navigation.
In this prospective study, which followed patients for 24 months, the indications are broad. “Its most common use is as a diagnostic technique for peripheral lung nodules and for marking lung lesions for surgical resection or marking for radiotherapy field fiducial placement,” said Dr. Pajares. “Results are also beginning to be published on the treatment of lung lesions using electromagnetic navigation ablation, demonstrating its safety and efficacy in this area.”