Skip to content

A novel deep learning-based three-dimensional retinal vascular analysis for progression risk stratification in glaucoma patients

A novel deep learning-based three-dimensional retinal vascular analysis for progression risk stratification in glaucoma patients

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500104716
Enrollment
Unknown
Registered
2025-06-23
Start date
2025-07-01
Completion date
Unknown
Last updated
2025-06-30

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

Conditions

Glaucoma

Interventions

Gold Standard:Glaucoma is defined when at least one eye had the presence of the structural and functional evidence of glaucoma, including glaucomatous optic disc cupping, RNFL damage, or neuroretinal
Index test:A novel deep learning-based three-dimensional retinal vascular analysis

Sponsors

The Chinese University of Hong Kong
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 80 Years

Inclusion criteria

Inclusion criteria: 1. Older than 18 years 2. Best corrected visual acuity (BCVA) no less than 20/40. 3. No severe systemic disorders (i.e., those without clinical retinal involvement). 4. Glaucoma is defined when at least one eye had the presence of the structural and functional evidence of glaucoma, including glaucomatous optic disc cupping, RNFL damage, or neuroretinal rim loss, and minimal criteria for glaucomatous VF defect as per published standard (38): glaucoma hemifield test result outside normal limits, pattern standard deviation (PSD) with P < 0.05 or a cluster of 3 or more points in the pattern deviation plot in a single hemifield with P < 0.05, one of which must have P < 0.01. Any one of the preceding criteria, if repeatable, was considered sufficient evidence for the glaucomatous visual field (VF) defect.

Exclusion criteria

Exclusion criteria: 1. Other ocular diseases that may cause retinal vascular change, such as diabetic retinopathy, hypertension retinopathy; or AMD. 2. Extremely myopia (i.e., axial length > 27.0 mm). 3. OCTA images with insufficient image quality.

Design outcomes

Primary

MeasureTime frame
The accuracy of deep learning system for feature extraction, progression detection, and risk stratification for glaucoma progression;Sensitivity;Specificity;

Countries

China

Contacts

Public ContactRuyue Shen

The Chinese University of Hong Kong

ruyueshen@cuhk.edu.hk+852 3943 0786

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026