Objectives: To assess a new application of artificial intelligence for real-time detection of laryngeal squamous cell carcinoma (LSCC) in both white light (WL) and narrow-band imaging (NBI) videolaryngoscopies based on the You-Only-Look-Once (YOLO) deep learning convolutional neural network (CNN).Study Design: Experimental study with retrospective data. Methods: Recorded videos of LSCC were retrospectively collected from in-office transnasal videoendoscopies and intraoperative rigid endoscopies. LSCC videoframes were extracted for training, validation, and testing of various YOLO models. Different techniques were used to enhance the image analysis: contrast limited adaptive histogram equalization, data augmentation techniques, and test time augmentation (TTA). The best-performing model was used to assess the automatic detection of LSCC in six videolaryngoscopies.Results: Two hundred and nineteen patients were retrospectively enrolled. A total of 624 LSCC videoframes were extracted. The YOLO models were trained after random distribution of images into a training set (82.6%), validation set (8.2%), and testing set (9.2%). Among the various models, the ensemble algorithm (YOLOv5s with YOLOv5m-TTA) achieved the best LSCC detection results, with performance metrics in par with the results reported by other state-of-the-art detection models: 0.66 Precision (positive predicted value), 0.62 Recall (sensitivity), and 0.63 mean Average Precision at 0.5 intersection over union. Tests on the six videolaryngoscopies demonstrated an average computation time per videoframe of 0.026 seconds. Three demonstration videos are provided.Conclusion: This study identified a suitable CNN model for LSCC detection in WL and NBI videolaryngoscopies. Detection performances are highly promising. The limited complexity and quick computational times for LSCC detection make this model ideal for real-time processing.

SUMMARY Objective The COVID-19 pandemic was an extraordinary challenge for the global healthcare system not only for the number of patients affected by pulmonary disease, but also for the incidence of long-term sequalae. In this regard, laryngo-tracheal stenosis (LTS) represents one of the most common complications of invasive ventilation. Methods A case series of patients who underwent tracheal resection and anastomosis (TRA) for post-COVID-19 LTS was collected from June 2020 to September 2021. Results Among 14 patients included, 50% had diabetes and 64.3% were obese. During intensive care unit stay, mean duration of orotracheal intubation (OTI) was 15.2 days and 10 patients (71.4%) underwent tracheostomy, which was maintained in 7 for an average of 31 days. According to the European Laryngological Society classification, 13 patients (92.9%) had a grade IIIa LTS and one a grade IIIa+. All patients underwent Type A TRA, according to the authors’ classification. No major perioperative complications were reported and at the last follow-up all patients were asymptomatic. Conclusions With the appropriate indications, TRA represents an effective treatment in post-COVID-19 LTS patients. Short OTI times and careful tracheostomy are required in order to reduce the incidence of airway injury.

No abstract