Automated Retroillumination Photography Analysis for Objective Assessment of Fuchs Corneal Dystrophy

Allen Eghrari, Aisha A. Mumtaz, Brian Garrett, Mahsa Rezaei, Mina S. Akhavan, Sheikh Amer Riazuddin, John D Gottsch

Research output: Contribution to journalArticle

Abstract

PURPOSE:: Retroillumination photography analysis is an objective tool for the assessment of the number and distribution of guttae in eyes affected with Fuchs corneal dystrophy (FCD). Current protocols include manual processing of images; here, we assess validity and interrater reliability of automated analysis across various levels of FCD severity. METHODS:: Retroillumination photographs of 97 FCD-affected corneas were acquired, and total counts of guttae were previously summated manually. For each cornea, a single image was loaded into ImageJ software. We reduced color variability and subtracted background noise. Reflection of light from each gutta was identified as a local area of maximum intensity and counted automatically. Noise tolerance level was titrated for each cornea by examining a small region of each image with automated overlay to ensure appropriate coverage of individual guttae. We tested interrater reliability of automated counts of guttae across a spectrum of clinical and educational experience. RESULTS:: A set of 97 retroillumination photographs was analyzed. Clinical severity as measured by a modified Krachmer scale ranged from a severity level of 1 to 5 in the set of analyzed corneas. Automated counts by an ophthalmologist correlated strongly with Krachmer grading (R = 0.79) and manual counts (R = 0.88). Intraclass correlation coefficients demonstrated strong correlation at 0.924 (95% CI, 0.870–0.958) among cases analyzed by 3 students, and 0.869 (95% CI, 0.797–0.918) among cases for which images were analyzed by an ophthalmologist and 2 students. CONCLUSIONS:: Automated retroillumination photography analysis allows for grading of FCD severity with high resolution across a spectrum of disease severity.

Original languageEnglish (US)
JournalCornea
DOIs
StateAccepted/In press - Nov 2 2016

Fingerprint

Fuchs' Endothelial Dystrophy
Photography
Cornea
Noise
Students
Reproducibility of Results
Software
Color
Light

ASJC Scopus subject areas

  • Ophthalmology

Cite this

Automated Retroillumination Photography Analysis for Objective Assessment of Fuchs Corneal Dystrophy. / Eghrari, Allen; Mumtaz, Aisha A.; Garrett, Brian; Rezaei, Mahsa; Akhavan, Mina S.; Riazuddin, Sheikh Amer; Gottsch, John D.

In: Cornea, 02.11.2016.

Research output: Contribution to journalArticle

@article{85bc0a3f8c374f30a77cbe4b21aa5203,
title = "Automated Retroillumination Photography Analysis for Objective Assessment of Fuchs Corneal Dystrophy",
abstract = "PURPOSE:: Retroillumination photography analysis is an objective tool for the assessment of the number and distribution of guttae in eyes affected with Fuchs corneal dystrophy (FCD). Current protocols include manual processing of images; here, we assess validity and interrater reliability of automated analysis across various levels of FCD severity. METHODS:: Retroillumination photographs of 97 FCD-affected corneas were acquired, and total counts of guttae were previously summated manually. For each cornea, a single image was loaded into ImageJ software. We reduced color variability and subtracted background noise. Reflection of light from each gutta was identified as a local area of maximum intensity and counted automatically. Noise tolerance level was titrated for each cornea by examining a small region of each image with automated overlay to ensure appropriate coverage of individual guttae. We tested interrater reliability of automated counts of guttae across a spectrum of clinical and educational experience. RESULTS:: A set of 97 retroillumination photographs was analyzed. Clinical severity as measured by a modified Krachmer scale ranged from a severity level of 1 to 5 in the set of analyzed corneas. Automated counts by an ophthalmologist correlated strongly with Krachmer grading (R = 0.79) and manual counts (R = 0.88). Intraclass correlation coefficients demonstrated strong correlation at 0.924 (95{\%} CI, 0.870–0.958) among cases analyzed by 3 students, and 0.869 (95{\%} CI, 0.797–0.918) among cases for which images were analyzed by an ophthalmologist and 2 students. CONCLUSIONS:: Automated retroillumination photography analysis allows for grading of FCD severity with high resolution across a spectrum of disease severity.",
author = "Allen Eghrari and Mumtaz, {Aisha A.} and Brian Garrett and Mahsa Rezaei and Akhavan, {Mina S.} and Riazuddin, {Sheikh Amer} and Gottsch, {John D}",
year = "2016",
month = "11",
day = "2",
doi = "10.1097/ICO.0000000000001056",
language = "English (US)",
journal = "Cornea",
issn = "0277-3740",
publisher = "Lippincott Williams and Wilkins",

}

TY - JOUR

T1 - Automated Retroillumination Photography Analysis for Objective Assessment of Fuchs Corneal Dystrophy

AU - Eghrari, Allen

AU - Mumtaz, Aisha A.

AU - Garrett, Brian

AU - Rezaei, Mahsa

AU - Akhavan, Mina S.

AU - Riazuddin, Sheikh Amer

AU - Gottsch, John D

PY - 2016/11/2

Y1 - 2016/11/2

N2 - PURPOSE:: Retroillumination photography analysis is an objective tool for the assessment of the number and distribution of guttae in eyes affected with Fuchs corneal dystrophy (FCD). Current protocols include manual processing of images; here, we assess validity and interrater reliability of automated analysis across various levels of FCD severity. METHODS:: Retroillumination photographs of 97 FCD-affected corneas were acquired, and total counts of guttae were previously summated manually. For each cornea, a single image was loaded into ImageJ software. We reduced color variability and subtracted background noise. Reflection of light from each gutta was identified as a local area of maximum intensity and counted automatically. Noise tolerance level was titrated for each cornea by examining a small region of each image with automated overlay to ensure appropriate coverage of individual guttae. We tested interrater reliability of automated counts of guttae across a spectrum of clinical and educational experience. RESULTS:: A set of 97 retroillumination photographs was analyzed. Clinical severity as measured by a modified Krachmer scale ranged from a severity level of 1 to 5 in the set of analyzed corneas. Automated counts by an ophthalmologist correlated strongly with Krachmer grading (R = 0.79) and manual counts (R = 0.88). Intraclass correlation coefficients demonstrated strong correlation at 0.924 (95% CI, 0.870–0.958) among cases analyzed by 3 students, and 0.869 (95% CI, 0.797–0.918) among cases for which images were analyzed by an ophthalmologist and 2 students. CONCLUSIONS:: Automated retroillumination photography analysis allows for grading of FCD severity with high resolution across a spectrum of disease severity.

AB - PURPOSE:: Retroillumination photography analysis is an objective tool for the assessment of the number and distribution of guttae in eyes affected with Fuchs corneal dystrophy (FCD). Current protocols include manual processing of images; here, we assess validity and interrater reliability of automated analysis across various levels of FCD severity. METHODS:: Retroillumination photographs of 97 FCD-affected corneas were acquired, and total counts of guttae were previously summated manually. For each cornea, a single image was loaded into ImageJ software. We reduced color variability and subtracted background noise. Reflection of light from each gutta was identified as a local area of maximum intensity and counted automatically. Noise tolerance level was titrated for each cornea by examining a small region of each image with automated overlay to ensure appropriate coverage of individual guttae. We tested interrater reliability of automated counts of guttae across a spectrum of clinical and educational experience. RESULTS:: A set of 97 retroillumination photographs was analyzed. Clinical severity as measured by a modified Krachmer scale ranged from a severity level of 1 to 5 in the set of analyzed corneas. Automated counts by an ophthalmologist correlated strongly with Krachmer grading (R = 0.79) and manual counts (R = 0.88). Intraclass correlation coefficients demonstrated strong correlation at 0.924 (95% CI, 0.870–0.958) among cases analyzed by 3 students, and 0.869 (95% CI, 0.797–0.918) among cases for which images were analyzed by an ophthalmologist and 2 students. CONCLUSIONS:: Automated retroillumination photography analysis allows for grading of FCD severity with high resolution across a spectrum of disease severity.

UR - http://www.scopus.com/inward/record.url?scp=84994259642&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994259642&partnerID=8YFLogxK

U2 - 10.1097/ICO.0000000000001056

DO - 10.1097/ICO.0000000000001056

M3 - Article

JO - Cornea

JF - Cornea

SN - 0277-3740

ER -