Artificial intelligence system for detecting superficial laryngopharyngeal cancer with high efficiency of deep learning

Atsushi Inaba, Keisuke Hori, Yusuke Yoda, Hiroaki Ikematsu, Hiroaki Takano, Hiroki Matsuzaki, Yoshiki Watanabe, Nobuyoshi Takeshita, Toshifumi Tomioka, Genichiro Ishii, Satoshi Fujii, Ryuichi Hayashi, Tomonori Yano

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)

Abstract

Background: There are no published reports evaluating the ability of artificial intelligence (AI) in the endoscopic diagnosis of superficial laryngopharyngeal cancer (SLPC). We presented our newly developed diagnostic AI model for SLPC detection. Methods: We used RetinaNet for object detection. SLPC and normal laryngopharyngeal mucosal images obtained from narrow-band imaging were used for the learning and validation data sets. Each independent data set comprised 400 SLPC and 800 normal mucosal images. The diagnostic AI model was constructed stage-wise and evaluated at each learning stage using validation data sets. Results: In the validation data sets (100 SLPC cases), the median tumor size was 13.2 mm; flat/elevated/depressed types were found in 77/21/2 cases. Sensitivity, specificity, and accuracy improved each time a learning image was added and were 95.5%, 98.4%, and 97.3%, respectively, after learning all SLPC and normal mucosal images. Conclusions: The novel AI model is helpful for detection of laryngopharyngeal cancer at an early stage.

Original languageEnglish
Pages (from-to)2581-2592
Number of pages12
JournalHead and Neck
Volume42
Issue number9
DOIs
Publication statusPublished - Sep 1 2020
Externally publishedYes

Keywords

  • artificial intelligence
  • endoscopy
  • narrow band imaging
  • object detection
  • superficial laryngopharyngeal cancer

ASJC Scopus subject areas

  • Otorhinolaryngology

Fingerprint

Dive into the research topics of 'Artificial intelligence system for detecting superficial laryngopharyngeal cancer with high efficiency of deep learning'. Together they form a unique fingerprint.

Cite this