Deep Learning Applied to White Light and Narrow Band Imaging Videolaryngoscopy: Toward Real‐Time Laryngeal Cancer Detection. (25th November 2021)

• Record Type: Journal Article
• Authors: Azam, Muhammad Adeel; Sampieri, Claudio; Ioppi, Alessandro; Africano, Stefano; Vallin, Alberto; Mocellin, Davide; Fragale, Marco; Guastini, Luca; Moccia, Sara; Piazza, Cesare; Mattos, Leonardo S.; Peretti, Giorgio
• Is Part Of: Laryngoscope. Volume 132:Number 9(2022)
• Page Start: 1798
• Page End: 1806
• Publication Date: 2021-11-25
• Subjects: Larynx cancer -- deep learning -- narrow band imaging -- computer‐assisted image interpretation -- videolaryngoscopy; Otolaryngology -- Periodicals; 617.51005
• DOI: 10.1002/lary.29960
• Languages: English
• ISSNs: 0023-852X

Abstract

Abstract : 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. Level of Evidence: 3 Laryngoscope, 132:1798–1806, 2022