Artificial intelligence for automatic detection and segmentation of nasal polyposis: a pilot study

• Published in: European archives of oto-rhino-laryngology Vol. 281; no. 11; pp. 5815 - 5821
• Main Authors: Rampinelli, Vittorio, Paderno, Alberto, Conti, Carlo, Testa, Gabriele, Modesti, Claudia Lodovica, Agosti, Edoardo, Dohin, Isabelle, Saccardo, Tommaso, Vinciguerra, Alessandro, Ferrari, Marco, Schreiber, Alberto, Mattavelli, Davide, Nicolai, Piero, Holsinger, Chris, Piazza, Cesare
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2024; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Chronic Disease; Endoscopy - methods; Female; Head and Neck Surgery; Humans; Image Processing, Computer-Assisted - methods; Male; Medicine; Medicine & Public Health; Nasal Polyps - complications; Nasal Polyps - diagnosis; Nasal Polyps - diagnostic imaging; Neurosurgery; Otorhinolaryngology; Pilot Projects; Retrospective Studies; Rhinitis - diagnosis; Rhinitis - diagnostic imaging; Rhinology; Sinusitis - diagnosis; Sinusitis - diagnostic imaging; Data analysis; Diagnosis; Nasal polyps; Artificial intelligence; Sinusitis
• ISSN: 0937-4477; 1434-4726; 1434-4726
• DOI: 10.1007/s00405-024-08809-4

Purpose Accurate diagnosis and quantification of polyps and symptoms are pivotal for planning the therapeutic strategy of Chronic rhinosinusitis with nasal polyposis (CRSwNP). This pilot study aimed to develop an artificial intelligence (AI)-based image analysis system capable of segmenting nasal polyps from nasal endoscopy videos. Methods Recorded nasal videoendoscopies from 52 patients diagnosed with CRSwNP between 2019 and 2022 were retrospectively analyzed. Images extracted were manually segmented on the web application Roboflow. A dataset of 342 images was generated and divided into training (80%), validation (10%), and testing (10%) sets. The Ultralytics YOLOv8.0.28 model was employed for automated segmentation. Results The YOLOv8s-seg model consisted of 195 layers and required 42.4 GFLOPs for operation. When tested against the validation set, the algorithm achieved a precision of 0.91, recall of 0.839, and mean average precision at 50% IoU (mAP50) of 0.949. For the segmentation task, similar metrics were observed, including a mAP ranging from 0.675 to 0.679 for IoUs between 50% and 95%. Conclusions The study shows that a carefully trained AI algorithm can effectively identify and delineate nasal polyps in patients with CRSwNP. Despite certain limitations like the focus on CRSwNP-specific samples, the algorithm presents a promising complementary tool to existing diagnostic methods.