AI System for Anatomic Recognition & Lesion Detection in Nasopharyngolaryngoscopy: A Prospective Study

Development and Validation of an Artificial Intelligence System for Anatomic Site Recognition and Lesion Detection Based on Electronic Nasopharyngolaryngoscopic Images: A Prospective Multicenter Study

An artificial intelligence-assisted system is trained and validated by collecting nasopharyngolaryngoscopy images from patients.

Study Overview

• Status: Recruiting
• Conditions: Nasopharyngeal Neoplasms; Laryngeal Disease
• Intervention / Treatment: Other: Diagnostic; Other: Diagnostic

Detailed Description

To address the clinical pain points of traditional nasopharyngolaryngoscopy, such as incomplete visualization, inaccurate identification, and unclear imaging, this study will retrospectively collect nasopharyngolaryngoscopy images and baseline information (including gender and age) of patients who underwent nasopharyngolaryngoscopy at participating centers for model training and validation. Deep learning algorithms will be applied to construct the model. The final clinical performance evaluation of the model will be conducted using an independent, prospectively collected test cohort.

• Study Type: Observational
• Enrollment (Estimated): 500

Contacts and Locations

• Study Contact: Name: Bin Ye, MD PhD; Phone Number: +8615216616895; Email: aydyebin@126.com

Study Locations

• China
  • Shanghai, China
    • Recruiting
    • Ruijin Hospital, Shanghai Jiao Tong University School of Medicine
    • Contact: Bin Ye, MD PhD; Phone Number: +8615216616895; Email: aydyebin@126.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study Population

Image data of patients who underwent nasopharyngolaryngoscopy and met the research requirements were collected from various sub-centers nationwide.

Description

Inclusion Criteria:

• Age ≥ 18 years;
• Underwent standard electronic nasopharyngolaryngoscopy;
• Patients who underwent biopsy sampling have a clear pathological diagnosis;
• Signed a written informed consent form.

Exclusion Criteria:

• Image quality is substandard with severe motion artifacts;
• Lesion images are unclear and incomplete.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Model training and validation cohorts; A deep learning model is trained using the training dataset and validated with the internal validation set.	Other: Diagnostic; The deep learning model is trained using the training dataset and tested with the internal validation set.; Other: Diagnostic; The prospective dataset is used for the comparative testing of the model and physicians.
Prospective test cohort; Patients are prospectively enrolled, nasopharyngolaryngoscopy examination videos are collected, and the video data are processed to form a prospective test dataset, which is then used for testing.	Other: Diagnostic; The deep learning model is trained using the training dataset and tested with the internal validation set.; Other: Diagnostic; The prospective dataset is used for the comparative testing of the model and physicians.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
performance of lesion detection	The area under the receiver operating characteristic curve (ROC-AUC) of the model for abnormal lesion detection	Within 3 months after the completion of prospective data collection
performance of anatomic site recognition	The average precision (AP) of the model for recognizing nasopharyngeal and laryngeal anatomic sites	Within 3 months after the completion of prospective data collection

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Comparison of diagnostic performance between the model and physicians	Differences in sensitivity, specificity, and overall accuracy between the AI model and endoscopists with different years of experience	Within 3 months after the completion of prospective data collection

Collaborators and Investigators

• Sponsor: Ruijin Hospital

Study record dates

Study Major Dates

• Study Start (Actual): December 12, 2025
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): March 31, 2027

Study Registration Dates

• First Submitted: December 26, 2025
• First Submitted That Met QC Criteria: December 26, 2025
• First Posted (Actual): January 8, 2026

Study Record Updates

• Last Update Posted (Actual): January 8, 2026
• Last Update Submitted That Met QC Criteria: December 26, 2025
• Last Verified: December 1, 2025

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Stomatognathic Diseases; Neoplasms by Site; Neoplasms; Respiratory Tract Diseases; Head and Neck Neoplasms; Otorhinolaryngologic Diseases; Pharyngeal Neoplasms; Otorhinolaryngologic Neoplasms; Nasopharyngeal Diseases; Pharyngeal Diseases; Nasopharyngeal Neoplasms; Laryngeal Diseases
• Other Study ID Numbers: 2025-811

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No