Detecting Eye Diseases Via Hybrid Deep Learning Algorithms From Fundus Images

January 19, 2024 updated by: URAL Telekomunikasyon San. Trade Inc.

Screening And Detecting Eye Diseases With Hybrid Deep Learning Algorithms From Fundus Images And Validation Of Automated Artificial Intelligence Algorithm

Eye health is of great importance for quality of life. Some eye diseases can progress and cause permanent damage up to vision loss if they are not treated early. Therefore, it is of great importance to have regular eye examinations and to detect possible eye diseases before they progress. Healthy people should also undergo eye screening once a year, and those with any complaints regarding eye health should be examined.

With the advancing technology, Artificial Intelligence (AI) has begun to play a significant role in the healthcare sector. Retinal diseases, serious health problems resulting from damage to the back part of the eye's retina, include conditions such as retinopathy, macular degeneration, and glaucoma. Artificial intelligence, with its visual recognition and analysis capabilities, holds great potential in the early diagnosis of retinal diseases.

AI-based diagnosis of retinal diseases typically involves the use of specialized algorithms that analyze retinal images. These algorithms identify abnormal features in the eye, providing doctors with a quick and accurate diagnosis.

EyeCheckup v2.0 will diagnose glaucoma suspicion, severe glaucoma suspicion, age-related macular degeneration diagnosis, RVO diagnosis, diabetic retinopathy diagnosis and stage, presence/absence of DME suspicion and other retinal diseases from fundus images. This study is designed to assess the safety and efficacy of EyeCheckup v2.0.

The study is a single center study to determine the sensitivity and specificity of EyeCheckup to retinal and optic disc diseases. EyeCheckup v2.0 is an automated software device that is designed to analyze ocular fundus digital color photographs taken in frontline primary care settings in order to quickly screen.

Study Overview

Status

Recruiting

Conditions

Intervention / Treatment

Detailed Description

According to the World Health Organization's worldwide report published in 2020, at least 2.2 billion people worldwide currently have visual impairment, and at least 1 billion of them have a visual impairment that can be prevented or has not yet been addressed. The world faces significant eye health challenges, including inequalities in the coverage and quality of eye care prevention, treatment, and rehabilitation services, a lack of trained eye care providers, and poor integration of eye care services into health systems, among others.

It is known that more than 80% of all visual disorders can be prevented or treated. An eye fundus examination must be performed by a retina specialist to make a correct diagnosis, but people only consult an ophthalmologist when they feel any discomfort. While typically symptoms progress so much that once a disease occurs, resulting in expensive treatments and surgeries, often the damage is irreversible, resulting in visual impairment or even permanent vision loss.

Artificial intelligence is used to study and develop theories and methods that can help simulate and extend human intelligence, which have been used in many fields of research such as automatic diagnosis and medicine. In recent years, the intersection of artificial intelligence (AI) technology and modern medicine has made effective and rapid disease screening possible. EyeCheckup is an automated software device designed to analyze digital color photographs of the ocular fundus to quickly screen for retinal and optic disc diseases.

The main aim of the research is to evaluate the performance of the automatic screening algorithm to detect steerable retinal and optic disc diseases based on color fundus images and to determine its sensitivity and specificity towards possible diseases. For the clinical validation of the system, the images will be evaluated by ophthalmologists and the results will be compared with the artificial intelligence algorithm.

After exclusions, this study will enroll up to 1528 subjects that meet the eligibility criteria. Participants who meet the eligibility criteria will be recruited after obtaining written informed consent from primary health care providers. Subjects will undergo fundus photography per, Food and Drug Administration (FDA) cleared, ophthalmic cameras. Images will be taken according to a specific EyeCheckup imaging protocol provided to the ophthalmic camera operator and then analyzed by the EyeCheckup v2.0 device.

Methods and tools to be used in the research:

I. Fundus photo capturing with non-mydriatic cameras: Optic disc-centered and fovea-centered fundus images will be taken with Canon CR-2 AF, Topcon TRC-NW400 and Optomed Aurora Non-mydriatic fundus cameras. For volunteers whose non-mydriatic images cannot be obtained, pupil dilation will be achieved by instilling tropicamide drops, and then images will be taken. Canon CR-2 AF, Topcon TRC-NW400 and Optomed Aurora Non-mydriatic fundus cameras, from which retina images will be taken, are CE marked and FDA approved.

Tests to be done:

I. Fundus images obtained with three different cameras from each volunteer included in the study will be analyzed separately for both the right eye and the left eye by the EyeCheckup artificial intelligence algorithm on a camera-based basis.

ii. Evaluation of Canon CR-2 AF images by retina and glaucoma specialists for clinical validation of the system and comparison of the results,

Study Type

Observational

Enrollment (Estimated)

1528

Contacts and Locations

This section provides the contact details for those conducting the study, and information on where this study is being conducted.

Study Contact

Study Locations

  • Turkey
      • Antalya, Turkey, 07070
        • Recruiting
        • Akdeniz University Hospital
        • Contact:
        • Principal Investigator:
          • Mustafa ÜNAL, Prof. Dr.
        • Sub-Investigator:
          • Mehmet Erkan DOĞAN, Lecturer
        • Sub-Investigator:
          • Mehmet BULUT, Assoc. Dr.
        • Sub-Investigator:
          • Aslı ÇETİNKAYA YAPRAK, Lecturer
        • Sub-Investigator:
          • Esra AYHAN TUZCU, Assoc. Dr.

Participation Criteria

Researchers look for people who fit a certain description, called eligibility criteria. Some examples of these criteria are a person's general health condition or prior treatments.

Eligibility Criteria

Ages Eligible for Study

  • Adult
  • Older Adult

Accepts Healthy Volunteers

Yes

Sampling Method

Non-Probability Sample

Study Population

Primary care clinic invitation to volunteer, Eighteen years of age or older Have been referred to an ophthalmologist for eye examination to screen for eye disease

Description

Inclusion Criteria:

Must understand the study and sign informed consent. No history of retinal vascular disease, cataracts or any other disease that may affect the appearance of the retina or optic disc (refractive error and ocular surface disease are allowed).

No history of intraocular surgery or ocular laser treatment for any retinal disease, other than cataract surgery.

18 years and over

Exclusion Criteria:

Not understand the study or informed consent, Media opacity or other defect that would prevent taking a fundus photograph with the feature to be evaluated (which could not be taken with a non-mydriatic fundus camera in 6 attempts or was rejected 6 times by the EyeCheckup quality algorithm due to quality), Has intraocular surgery other than cataracts or has had laser treatment on the retina, Contraindicated for imaging with the fundus imaging systems used in the study, Under 18 years

Study Plan

This section provides details of the study plan, including how the study is designed and what the study is measuring.

How is the study designed?

Design Details

What is the study measuring?

Primary Outcome Measures

Outcome Measure
Measure Description
Time Frame
To determine the accuracy of diagnosis with artificial intelligence algorithm
Time Frame: through study completion, an average of 1 year
Comparison of the compatibility of the diagnosis of the artificial intelligence algorithm with the diagnoses of retina and glaucoma specialists
through study completion, an average of 1 year

Secondary Outcome Measures

Outcome Measure
Measure Description
Time Frame
To determine the sensitivity and specificity of EyeCheckup v2.0 to detect retinal and optic disc diseases
Time Frame: through study completion, an average of 1 year
  1. To determine the sensitivity of EyeCheckup v2.0 to detect Glaucoma, RVO, diabetic retinopathy, suspected DME, ARMD, other retinal disease (True positive rate of the algorithm)
  2. To determine the specificity of EyeCheckup v2.0 to detect Glaucoma, RVO, diabetic retinopathy, suspected DME, ARMD, other retinal disease (True negative rate of the algorithm)
  3. To determine the specificity of EyeCheckup v2.0 to detect Refere/Nonrefere (True negative rate of the algorithm)
  4. To determine the sensitivity of EyeCheckup v2.0 to detect Refere/Nonrefere (True positive rate of the algorithm)
through study completion, an average of 1 year

Collaborators and Investigators

This is where you will find people and organizations involved with this study.

Sponsor

URAL Telekomunikasyon San. Trade Inc.

Study record dates

These dates track the progress of study record and summary results submissions to ClinicalTrials.gov. Study records and reported results are reviewed by the National Library of Medicine (NLM) to make sure they meet specific quality control standards before being posted on the public website.

Study Major Dates

Study Start (Actual)

March 1, 2023

Primary Completion (Estimated)

March 1, 2024

Study Completion (Estimated)

March 1, 2024

Study Registration Dates

First Submitted

January 9, 2024

First Submitted That Met QC Criteria

January 9, 2024

First Posted (Actual)

January 19, 2024

Study Record Updates

Last Update Posted (Actual)

January 22, 2024

Last Update Submitted That Met QC Criteria

January 19, 2024

Last Verified

January 1, 2024

More Information

Terms related to this study

Keywords

Additional Relevant MeSH Terms

Other Study ID Numbers

  • EC-2023-TR

Drug and device information, study documents

Studies a U.S. FDA-regulated drug product

No

Studies a U.S. FDA-regulated device product

No

This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.

Clinical Trials on Glaucoma

Clinical Trials on Mydriatic Agent

Search Similar Trials

Sponsors and Collaborators

Medical Conditions

Drug Interventions

CROs by country

CROs in Luxembourg

Conditions

Rare Diseases

Drug Interventions

Dietary Supplements

Sponsor/Collaborators

Locations

3
Subscribe