AI tool to recognize anatomy and find lesions during nasopharyngolaryngoscopy
Official title: Development and Validation of an Artificial Intelligence System for Anatomic Site Recognition and Lesion Detection Based on Electronic Nasopharyngolaryngoscopic Images: A Prospective Multicenter Study
Run by Ruijin Hospital · NCT07326358 · Data updated 2026-11-12
This project will try an AI system that reads nasopharyngolaryngoscopy images to help doctors spot anatomy and lesions in adults having these exams.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 500 (estimated) |
| Sponsor | Ruijin Hospital Academic / other |
| Locations | 1 site (Shanghai) |
| Status | Recruiting |
| Started | December 12, 2025 |
| Main results expected | December 31, 2026 |
| Study ends | March 31, 2027 |
| Registry record updated | January 8, 2026 |
| Trial ID | NCT07326358 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Ideal candidates are adults (age 18 or older) who underwent standard electronic nasopharyngolaryngoscopy at the enrolling site and can provide informed consent, with clear images available for use.
✕Probably not a fit
Patients whose images are of poor quality, have severe motion artifacts, or contain incomplete lesion views are unlikely to benefit from the AI model.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
The study will collect standard electronic nasopharyngolaryngoscopy images and basic patient information from adult patients at participating centers to train and validate a deep learning model. Retrospective image and metadata collection, including biopsy-confirmed pathology when available, will be used for model development. After training and internal validation, the model's clinical performance will be tested on an independent, prospectively collected cohort. The aim is to improve anatomic recognition and lesion detection during nasopharyngolaryngoscopy.
Why it matters
Potential benefit: If successful, the AI could reduce missed or misidentified areas on examination and help clinicians detect lesions earlier, potentially improving diagnosis and treatment planning.
How similar studies have gone: Deep learning approaches have shown promise in other endoscopic and laryngoscopic image-detection tasks, but AI specifically applied to nasopharyngolaryngoscopy remains relatively novel.
Who can join: the full rules
Show full inclusion / exclusion criteria
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.
Where it's running
-
Ruijin Hospital, Shanghai Jiao Tong University School of Medicine
Shanghai, China Recruiting
Study contacts
- Study coordinator: Bin Ye, MD PhD
- Email: aydyebin@126.com
- Phone: +8615216616895
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Measuring tongue and throat forces during direct laryngoscopy
We will test whether measuring and then showing surgeons real-time forces on the tongue and throat during laryngeal surgery helps reduce postoperative pain, numbness, and taste changes in adults having direct laryngoscopy.
-
Comparing two and three cycles of chemotherapy with immunotherapy for advanced nasopharyngeal cancer
This study is testing whether two cycles of chemotherapy combined with immunotherapy can help people with advanced nasopharyngeal cancer just as much as three cycles, but with fewer side effects.
-
Injecting steroids to treat chronic cough
This study is testing if steroid injections can help people with a long-lasting cough that doesn't have a clear cause feel better compared to a placebo.
-
Using music therapy via an app to reduce anxiety before ENT surgery
This study is testing whether listening to music through an app can help reduce anxiety for people getting ready for ENT surgery.
-
Collection of biological samples for research on head and neck disorders
This study is collecting biological samples from people with head and neck disorders to see how these conditions develop and find better ways to diagnose and treat them.
-
Using Nivolumab with chemotherapy for nasopharyngeal carcinoma in children and adults
This study tests if adding the drug Nivolumab to regular chemotherapy can help children and adults with nasopharyngeal carcinoma respond better to treatment.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.