Detection of oral cancer and oral potentially malignant disorders using artificial intelligence‐based image analysis

• Published in: Head & Neck Vol. 46; no. 9; pp. 2253 - 2260
• Main Authors: Kouketsu, Atsumu, Doi, Chiaki, Tanaka, Hiroaki, Araki, Takashi, Nakayama, Rina, Toyooka, Tsuguyoshi, Hiyama, Satoshi, Iikubo, Masahiro, Osaka, Ken, Sasaki, Keiichi, Nagai, Hirokazu, Sugiura, Tsuyoshi, Yamauchi, Kensuke, Kuroda, Kanako, Yanagisawa, Yuta, Miyashita, Hitoshi, Kajita, Tomonari, Iwama, Ryosuke, Kurobane, Tsuyoshi, Takahashi, Tetsu
• Format: Journal Article
• Language: English
• Published: Hoboken, USA Wiley 01.09.2024; John Wiley & Sons, Inc; Wiley Subscription Services, Inc
• Subjects: Adult; Aged; Artificial Intelligence; Carcinoma, Squamous Cell - diagnostic imaging; Carcinoma, Squamous Cell - pathology; deep learning; Female; Head & neck cancer; Humans; Image processing; Image Processing, Computer-Assisted; Leukokeratosis; Leukoplakia, Oral - diagnosis; Leukoplakia, Oral - diagnostic imaging; Leukoplakia, Oral - pathology; Male; Middle Aged; Mouth Neoplasms - diagnosis; Mouth Neoplasms - diagnostic imaging; Mouth Neoplasms - pathology; Oral cancer; Oral carcinoma; Oral cavity; Oral diseases; Oral squamous cell carcinoma; Sensitivity and Specificity; Squamous cell carcinoma; deep learning; oral squamous cell carcinoma; artificial intelligence; oral cancer
• ISSN: 1043-3074; 1097-0347; 1097-0347
• DOI: 10.1002/hed.27843

Background We aimed to construct an artificial intelligence‐based model for detecting oral cancer and dysplastic leukoplakia using oral cavity images captured with a single‐lens reflex camera. Subjects and methods We used 1043 images of lesions from 424 patients with oral squamous cell carcinoma (OSCC), leukoplakia, and other oral mucosal diseases. An object detection model was constructed using a Single Shot Multibox Detector to detect oral diseases and their locations using images. The model was trained using 523 images of oral cancer, and its performance was evaluated using images of oral cancer (n = 66), leukoplakia (n = 49), and other oral diseases (n = 405). Results For the detection of only OSCC versus OSCC and leukoplakia, the model demonstrated a sensitivity of 93.9% versus 83.7%, a negative predictive value of 98.8% versus 94.5%, and a specificity of 81.2% versus 81.2%. Conclusions Our proposed model is a potential diagnostic tool for oral diseases.