To Develop and Validate a Nasoendoscopic Intelligent Diagnostic System for Nasopharyngeal Carcinoma

NCT04547673 | Recruiting DMC

• 1 other identifier: ZSYY2020
• Study Type: observational
• Target: 1,000
• Locations: 1 country
• Sites: 3

Brief Summary

Nasopharyngeal carcinoma (NPC) occurs at a high frequency in southern China, northern Africa, and Alaska, with a reported incidence of 30 cases per 100 000 in Guangdong Province. Endoscopic examination and biopsy are the main methods used for detection and diagnosis of NPC. Early NPC patients achieve favourable prognoses after concurrent radiotherapy and chemotherapy in compassion with advanced NPC patients. Here, the investigators focused on the utility of artificial intelligence to detect early NPC, which based on white light imaging (WLI) and Narrow-band imaging (NBI) nasoendoscopic examination. Having access to this unique population provides an unprecedented opportunity to investigate the effect of intelligent system on diverse nasopharyngeal lesions detection and develop a novel Computer-Aided Diagnosis System.

Conditions

Otolaryngological Disease; Artificial Intelligence

Keywords

Nasopharyngeal Carcinoma; Endoscopy; Narrow-Band Imaging; White-Light Imaging

Outcome Measures

Primary Outcomes (1)

• Pathological diagnosis

  All lesions, detected by either WLI or NBI, are biopsied. 2 experienced pathologists, who were blinded to the endoscopic and intelligent assessment, evaluate the pathological nature of the biopsied lesion independently, and 2 professors with over 10 years of experience in Otolaryngology and pathology department are consulted in cases of disagreement.

  baseline

Secondary Outcomes (1)

• Lesion range

  baseline

Study Arms (2)

NPC group

Patients pathologically diagnosed as NPC by agreement of 2 experienced pathologists who were blinded to the corresponding endoscopic assessment.

Diagnostic Test: rigid nasal endoscopes

Non-NPC group

Patients pathologically diagnosed as non-NPC (including inflammatory hyperplasia, Atypical hyperplasia, Papilloma etc.) by agreement of 2 experienced pathologists who were blinded to the corresponding endoscopic assessment.

Diagnostic Test: rigid nasal endoscopes

Interventions

rigid nasal endoscopes DIAGNOSTIC_TEST

The endoscope is introduced through the nasal passage to observe, in sequence, the posterior nostril, superior and posterior walls of the nasopharynx, torus tubarius, pharyngeal opening of the auditory tube, and Rosenmu¨ller recess. The imaging light mode is set to conventional WLI and subsequently switch to NBI during the procedure, and representative images are collected and preserve for further analysis. All lesions, detected by either WLI or NBI, are biopsied.

NPC group; Non-NPC group

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients at the outpatient department of otolaryngology at the First Affiliated Hospital of Sun Yat-sen University, Guangzhou, People's Republic of China, or patients at Sun Yat-Sen University Cancer Center and Kiang Wu Hospital, with risk factors including any of the following: Cantonese ethnicity, NPC family history, Epstein-Barr virus detection, any symptom of nasal obstruction, sense of peculiar smell, blood-stained nasal discharge, epistaxis, ear fullness, tinnitus, hearing loss, diplopia, headache, or cervical mass.

You may qualify if:

• Older than 18 years of age

You may not qualify if:

• Refuse to sign the informed consent statement
• Patients who have contraindications, e.g. coagulation dysfunction, drug allergy.

Sponsors & Collaborators

• First Affiliated Hospital, Sun Yat-Sen University: lead
• Sun Yat-sen University: collaborator

Study Sites (3)

First Affiliated Hospital of Sun Yat-sen University

Guangzhou, Guangdong, 501180, China

RECRUITING

Sun Yat-Sen University Cancer Center

Guangzhou, Guangdong, 510060, China

RECRUITING

Kiang Wu Hospital

Macao, Macao, 999078, China

RECRUITING

Related Publications (1)

• He R, Jie P, Hou W, Long Y, Zhou G, Wu S, Liu W, Lei W, Wen W, Wen Y. Real-time artificial intelligence-assisted detection and segmentation of nasopharyngeal carcinoma using multimodal endoscopic data: a multi-center, prospective study. EClinicalMedicine. 2025 Feb 15;81:103120. doi: 10.1016/j.eclinm.2025.103120. eCollection 2025 Mar.

  PMID: 40026832 DERIVED

MeSH Terms

Conditions

Otorhinolaryngologic Diseases; Nasopharyngeal Carcinoma

Condition Hierarchy (Ancestors)

Carcinoma; Neoplasms, Glandular and Epithelial; Neoplasms by Histologic Type; Neoplasms; Nasopharyngeal Neoplasms; Pharyngeal Neoplasms; Otorhinolaryngologic Neoplasms; Head and Neck Neoplasms; Neoplasms by Site; Nasopharyngeal Diseases; Pharyngeal Diseases; Stomatognathic Diseases

Study Officials

• Weiping Wen, Ph.D

  Otolaryngology Department, First Affiliated Hospital of Sun Yat-sen University

  STUDY DIRECTOR

Central Study Contacts

Yihui Wen, Ph.D

CONTACT

+86-13480200660; wenyihui@mail.sysu.edu.cn

Rui He, M.D.

CONTACT

13096385286; herui27@mail2.sysu.edu.cn

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Vice President of First Affiliated Hospital, Sun Yat-Sen University; President of sixth Affiliated Hospital, Sun Yat-Sen University

Study Record Dates

• First Submitted: September 4, 2020
• First Posted: September 14, 2020
• Study Start: June 20, 2020
• Primary Completion: October 31, 2024
• Study Completion (Estimated): December 31, 2026
• Last Updated: February 20, 2024

Record last verified: 2024-02

Data Sharing

• IPD Sharing: Will not share

Locations

CN (3)