Real-time Artificial Intelligence System for Detecting Multiple Ocular Fundus Lesions by Ultra-widefield Fundus Imaging

Real-time Artificial Intelligence System for Detecting Multiple Ocular Fundus Lesions by Ultra-widefield Fundus Imaging: A Prospective Multicenter Study

Status

UNKNOWN

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT04859634

Enrollment

2000

Registered

2021-04-26

Start date

2020-11-01

Completion date

2022-12-25

Last updated

2021-04-26

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Abnormality of the Fundus, Artificial Intelligence, Diagnostic Imaging, Diagnostic Screening Programs

Keywords

Artificial Intelligence, Deep learning, Ultra-widefield Fundus Imaging, Ocular Fundus Lesions, Diagnostic Screening Programs

Brief summary

This prospective multicenter study will evaluate the efficacy of a real-time artificial intelligence system for detecting multiple ocular fundus lesions by ultra-widefield fundus imaging in real-world settings.

Detailed description

The ocular fundus can show signs of both ocular diseases (e.g., lattice degeneration, retinal detachment and glaucoma) and systemic diseases (e.g., hypertension, diabetes and leukemia). The routine fundus examination is conducive for early detection of these diseases. However, manual conducting fundus examination needs an experienced retina ophthalmologist, and is time-consuming and labor-intensive, which is difficult for its routine implementation on large scale. This study will develop an artificial intelligence system integrating with ultra-widefield fundus imaging to automatically screen for multiple ocular fundus lesions in real time and evaluate its performance in different real-world settings. The efficacy of the system will compare to the final diagnoses of each participant made by experienced ophthalmologists.

Interventions

DEVICETaking an ultra-widefield fundus image

The participant only needs to take an ultra-widefield fundus image as usual.

Study design

Observational model

COHORT

Time perspective

PROSPECTIVE

Eligibility

Sex/Gender

ALL

Healthy volunteers

Yes

Inclusion criteria

All the participants who agree to take ultra-widefield fundus images.

Exclusion criteria

1. Patients who cannot cooperate with a photographer such as some paralytics, the patients with dementia and severe psychopaths. 2. Patients who do not agree to sign informed consent.

Design outcomes

Primary

Measure	Time frame	Description
Accuracy	8 months	Performance of artificial intelligence system for detecting multiple ocular fundus lesions based on ultra-widefield fundus imaging.

Secondary

Measure	Time frame	Description
Specificity	8 months	Performance of artificial intelligence system for detecting multiple ocular fundus lesions based on ultra-widefield fundus imaging.
Cohen's kappa coefficient	8 months	The comparison between the performacne of AI system and ophthalmologists of three degrees of expertise.
Sensitivity	8 months	Performance of artificial intelligence system for detecting multiple ocular fundus lesions based on ultra-widefield fundus imaging.
False-negative rate	8 months	Features of Misclassification
Data processing time of AI system	8 months	Data processing time of AI system.
False-positive rate	8 months	Features of Misclassification

Countries

China

Contacts

Primary ContactHaotian Lin, MD, PhD

haot.lin@hotmail.com8613802793086

Backup ContactZhongwen Li, MD

cuitx3@mail2.sysu.edu.cn8618138726682

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026