Development and Validation of a Deep Learning System for Multiple Ocular Fundus Diseases Using Retinal Images

Overview

Retinal images can reflect both fundus and systemic conditions (diabetes and cardiovascular disease) and firstly to be used for medical artificial intelligence (AI) algorithm training due to its advantages of clinical significance and easy to obtain. Here, the investigators developed a single network model that can mine the characteristics among multiple fundus diseases, which was trained by plenty of fundus images with one or several disease labels (if they have) in each of them. The model performance was compared with those of both native and international ophthalmologists. The model was further tested by datasets with different camera types and validated by three external datasets prospectively collected from the clinical sites where the model would be applied.

Full Title of Study: “Development and Validation of a Deep Learning System for Multiple Ocular Fundus Diseases Using Retinal Images: a Multi-center Prospective Study”

Study Type

  • Study Type: Observational
  • Study Design
    • Time Perspective: Other
  • Study Primary Completion Date: February 2020

Interventions

  • Other: diagnostic
    • Training dataset was used to train the deep learning model, which was validated and tested by other two datasets.

Arms, Groups and Cohorts

  • Training dataset
    • Retinal images collected from hospitals and multiple screening sites all over China
  • Validation dataset
    • Retinal images separated from training dataset
  • Testing dataset
    • Retinal images prospectively collected from the hospitals and ocular disease screening sites totally different from training dataset

Clinical Trial Outcome Measures

Primary Measures

  • Area under the receiver operating characteristic curve of the deep learning system
    • Time Frame: baseline
    • The investigators will calculate the area under the receiver operating characteristic curve of deep learning system and compare this index between deep learning system and human doctors.

Secondary Measures

  • Sensitivity of the deep learning system
    • Time Frame: baseline
    • The investigators will calculate the sensitivity of deep learning system and compare this index between deep learning system and human doctors.
  • Specificity of the deep learning system
    • Time Frame: baseline
    • The investigators will calculate the specificity of deep learning system and compare this index between deep learning system and human doctors.

Participating in This Clinical Trial

Inclusion Criteria

  • The quality of fundus images should clinical acceptable. More than 80% of the fundus image area including four main regions (optic disk, macular, upper and lower retinal vessel archs) are easy to read and discriminate. Exclusion Criteria:

  • Images with light leakage (>30% of area), spots from lens flares or stains, and overexposure were excluded from further analysis.

Gender Eligibility: All

Minimum Age: N/A

Maximum Age: N/A

Are Healthy Volunteers Accepted: Accepts Healthy Volunteers

Investigator Details

  • Lead Sponsor
    • Sun Yat-sen University
  • Provider of Information About this Clinical Study
    • Principal Investigator: Haotian Lin, Prof. – Sun Yat-sen University
  • Overall Contact(s)
    • Haotian Lin, PhD, 13802793086, gddlht@aliyun.com

Clinical trials entries are delivered from the US National Institutes of Health and are not reviewed separately by this site. Please see the identifier information above for retrieving further details from the government database.

At TrialBulletin.com, we keep tabs on over 200,000 clinical trials in the US and abroad, using medical data supplied directly by the US National Institutes of Health. Please see the About and Contact page for details.