Deep Learning Assisted Epithelial Basement Membrane Dystrophy Detection

Automated Deep Learning for Detection of Epithelial Basement Membrane Dystrophy Using Optical Coherence Tomography and Longitudinal Reproducibility of Disease Characteristics

Epithelial basement membrane dystrophy, also known as Map-Dot fingerprint dystrophy or Cogan microcystic dystrophy, is a common bilateral dystrophy of the anterior human cornea. According to one study, it affects approximately 2% of the human population. A more recent study even reported basement membrane changes in 25% of the general population. However, due to its clinical and morphological appearance, the disease is probably often overlooked.

Although epithelial basement membrane dystrophy is asymptomatic in many affected patients, there are some important clinical consequences of the disease to consider: Dystrophy is estimated to be the second most common cause of recurrent corneal erosion syndrome and is also an important differential diagnosis of dry eye disease. Therefore, it can cause severe pain in affected patients. In addition, epithelial basement membrane dystrophy plays an important role in the context of cataract surgery, one of the most commonly performed surgeries worldwide: besides the importance of appropriate disease management before surgery to prevent postoperative exacerbation of ocular surface symptoms, epithelial basement membrane dystrophy is also a risk factor for inaccurate preoperative biometry.

In recent years, specific features of epithelial basement membrane dystrophy have been introduced in examination methods other than slit-lamp biomicroscopy, such as epithelial thickness mapping or optical coherence tomography. Due to the recent introduction of a variety of deep learning systems, the application of machine learning could significantly increase the detection rate for epithelial basement membrane dystrophy. Furthermore, to the best of our knowledge, the change in disease characteristics over time is currently unknown.

Therefore, the first part of this study will investigate the ability of an automated deep learning system using optical coherence tomography scans to distinguish between normal human corneas and corneas affected by epithelial basement membrane dystrophy. For this purpose, 100 eyes of 50 patients will be included in both study groups. In an optional 2nd part of the study, a second visit will be planned in patients with epithelial basement membrane dystrophy to investigate the reproducibility of disease characteristics as a secondary outcome.

Study Overview

• Status: Recruiting
• Conditions: Map Dot Fingerprint Dystrophy
• Intervention / Treatment: Diagnostic test: anterior segment optical coherence tomography

Detailed Description

This study aims to investigate the capability of an automated deep learning system using anterior segment optical coherence tomography scans to distinguish between normal human corneas and corneas affected by epithelial basement membrane dystrophy. In an optional substudy, a second visit will be scheduled to investigate the reproducibility of disease characteristics as a secondary outcome.

One-hundred eyes of 50 patients with epithelial basement membrane dystrophy and 100 eyes of 50 healthy subjects will be included in this study. After successful screening, all study participants will undergo one single study visit. During this visit, two questionnaires (Ocular Surface Disease Index, Quality of Vision), two different anterior segment optical coherence tomography devices (MS-39, Anterion), a slit lamp examination including slit lamp photography will be performed.

In an optional substudy, patients with epithelial basement membrane dystrophy will have a second visit, to compare the variability of disease characteristics, including number of maps, dots, fingerprint lines and cysts between the two visits.

• Study Type: Observational
• Enrollment (Anticipated): 100

Contacts and Locations

• Study Contact: Name: Oliver Findl, MD, MBA, FEBO; Phone Number: +43 1 91021- 57564; Email: office@viros.at

Study Locations

• Austria
  • Vienna, Austria, 1140
    • Recruiting
    • Vienna Institute for Research in Ocular Surgery (VIROS)
    • Contact: Andreas Schlatter, MD; Phone Number: +43 1 91021- 57564; Email: a.schlatter@viros.at

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• Sampling Method: Probability Sample

Study Population

Community sample

Description

Inclusion Criteria (Group 1):

• Age 18 or older
• Written informed consent
• Presence of epithelial basement membrane dystrophy

Inclusion Criteria (Group 2):

• Age 18 or older
• Written informed consent
• No corneal pathology in both eyes

Exclusion Criteria:

• Other corneal conditions (such as corneal scarring, fuchs endothelial corneal dystrophy, etc.)
• Pregnancy (pregnancy test will be taken in women of reproductive age), nursing women

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Epithelial Basement Membrane Dystrophy; Patients with epithelial basement membrane dystrophy	Diagnostic test: anterior segment optical coherence tomography; Two different optical systems (MS-39, Costruzione Strumenti Oftalmici Italy; Anterion optical coherence tomographer, Heidelberg Engineering) will be used for acquisition of cross-sectional scans. Radial scan patterns will be used for acquisition.
Healthy; Patients/Subjects without corneal pathologies	Diagnostic test: anterior segment optical coherence tomography; Two different optical systems (MS-39, Costruzione Strumenti Oftalmici Italy; Anterion optical coherence tomographer, Heidelberg Engineering) will be used for acquisition of cross-sectional scans. Radial scan patterns will be used for acquisition.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
Sensitivity of the deep learning system to detect optical coherence tomography scans with epithelial basement membrane dystrophy on the final test data set	1 day
Specificity of the deep learning system to detect optical coherence tomography scans with epithelial basement membrane dystrophy on the final test data set	1 day
Area under the curve of the deep learning algorithm on the final test data set	1 day

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Interobserver variability regarding disease diagnosis (normal cornea vs. epithelial basement membrane dystrophy) according to slit lamp photographies		1 day
Interobserver variability regarding number of maps according to slit lamp photographies		1 day
Interobserver variability regarding number of dots according to slit lamp photographies		1 day
Interobserver variability regarding number of fingerprints according to slit lamp photographies		1 day
Interobserver variability regarding number of cysts according to slit lamp photographies		1 day
Difference in epithelial thickness mapping between healthy corneas and corneas affected by epithelial basement membrane dystrophy		1 day
Difference in Ocular Surface Disease Index between healthy subjects and patients affected by epithelial basement membrane dystrophy	minimum: 0, maximum: 100, higher scores are associated with increased symptoms regarding ocular surface disease	1 day
Difference in Quality of Vision questionnaire score between healthy subjects and patients affected by epithelial basement membrane dystrophy	0- to 100-unit linear scale, higher scores indicating poorer quality of vision	1 day
Sub-study only: Reproducibility of number of maps between visit 1 and visit 2 according to slit lamp photographies and optical coherence tomography images	number of corneal maps will be assessed by a clinical investigator at both visits	3 months
Sub-study only: Reproducibility of number of dots between visit 1 and visit 2 according to slit lamp photographies and optical coherence tomography images	number of corneal dots will be assessed by a clinical investigator at both visits	3 months
Sub-study only: Reproducibility of number of fingerprints between visit 1 and visit 2 according to slit lamp photographies and optical coherence tomography images	number of corneal fingerprint lines will be assessed by a clinical investigator at both visits	3 months
Sub-study only: Reproducibility of number of cysts between visit 1 and visit 2 according to slit lamp photographies and optical coherence tomography images	number of corneal cysts will be assessed by a clinical investigator at both visits	3 months

Collaborators and Investigators

• Sponsor: Vienna Institute for Research in Ocular Surgery

Study record dates

Study Major Dates

• Study Start (Actual): February 27, 2023
• Primary Completion (Anticipated): February 27, 2024
• Study Completion (Anticipated): February 27, 2024

Study Registration Dates

• First Submitted: February 27, 2023
• First Submitted That Met QC Criteria: March 13, 2023
• First Posted (Actual): March 15, 2023

Study Record Updates

• Last Update Posted (Actual): March 15, 2023
• Last Update Submitted That Met QC Criteria: March 13, 2023
• Last Verified: March 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Cardiovascular Diseases; Vascular Diseases; Nervous System Diseases; Eye Diseases; Vasculitis; Cranial Nerve Diseases; Vestibulocochlear Nerve Diseases; Cogan Syndrome
• Other Study ID Numbers: DL_EBMD

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No