Related Experiment Video
Updated: Jun 9, 2025
05:56
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
2.4K
Diagnostic accuracy of deep learning-based algorithms in laryngoscopy: a systematic review and meta-analysis
Shengyi Du1,2,3, Jin Guo1,2,3, Donghai Huang1,2,3,4
1Department of Otolaryngology Head and Neck Surgery, Xiangya Hospital, Central South University, No. 87 Xiangya Road, Changsha, Hunan, 410008, The People's Republic of China.
Summary
Deep learning shows high accuracy for diagnosing laryngeal cancer using laryngoscopy images. This artificial intelligence approach can assist doctors in making better clinical decisions for vocal cord lesions.
Area of Science:
- Otolaryngology
- Medical Imaging Analysis
- Artificial Intelligence in Medicine
Background:
- Laryngoscopy is a standard diagnostic tool for vocal cord lesions but has limitations.
- Deep learning (DL) shows promise in medical image analysis.
- This study evaluates DL's diagnostic utility in laryngoscopy.
Purpose of the Study:
- To systematically review and meta-analyze the diagnostic performance of deep learning algorithms in laryngoscopy for laryngeal cancer detection.
Main Methods:
- Systematic review and meta-analysis following PRISMA guidelines.
- Searched PubMed, Scopus, Embase, and Web of Science databases.
- Included studies applying DL to laryngoscopy images; extracted diagnostic metrics using a random-effects model.
Main Results:
- Analyzed 9 studies with 106,175 images.
- Pooled sensitivity for laryngeal cancer: 0.95 (95% CI: 0.85-0.98).
- Pooled specificity for laryngeal cancer: 0.96 (95% CI: 0.91-0.98).
- Area Under the Curve (AUC) for DL: 0.99 (95% CI: 0.97-0.99).
Conclusions:
- Deep learning exhibits excellent diagnostic efficacy for laryngeal cancer via laryngoscopy.
- DL has the potential to support endoscopists in diagnosing laryngeal cancer.
- AI-powered tools can aid clinical decision-making in laryngology.
