An Automated Grading and Diagnosis System for Evaluation of Dry Eye Syndrome

Ayşe Bağbaba, Baha Şen, Dursun Delen, Betül Seher Uysal

Research output: Contribution to journalArticle

Abstract

This article describes methods used to determine the severity of Dry Eye Syndrome (DES) based on Oxford Grading Schema (OGS) automatically by developing and applying a decider model. The number of dry punctate dots occurred on corneal surface after corneal fluorescein staining can be used as a diagnostic indicator of DES severity according to OGS; however, grading of DES severity exactly by carefully assessing these dots is a rather difficult task for humans. Taking into account that current methods are also subjectively dependent on the perception of the ophtalmologists coupled with the time and resource intensive requirements, enhanced diagnosis techniques would greatly contribute to clinical assessment of DES. Automated grading system proposed in this study utilizes image processing methods in order to provide more objective and reliable diagnostic results for DES. A total of 70 fluorescein-stained cornea images from 20 patients with mild, moderate, or severe DES (labeled by an ophthalmologist in the Keratoconus Center of Yildirim Beyazit University Ataturk Training and Research Hospital) used as the participants for the study. Correlations between the number of dry punctate dots and DES severity levels were determined. When automatically created scores and clinical scores were compared, the following measures were observed: Pearson’s correlation value between the two was 0.981; Lin’s Concordance Correlation Coefficients (CCC) was 0.980; and 95% confidence interval limites were 0.963 and 0.989. The automated DES grade was estimated from the regression fit and accordingly the unknown grade is calculated with the following formula: Gpred = 1.3244 log(Ndots) - 0.0612. The study has shown the viability and the utility of a highly successful automated DES diagnostic system based on OGS, which can be developed by working on the fluorescein-stained cornea images. Proper implemention of a computationally savvy and highly accurate classification system, can assist investigators to perform more objective and faster DES diagnoses in real-world scenerios.

Original languageEnglish
Article number227
JournalJournal of Medical Systems
Volume42
Issue number11
DOIs
StatePublished - 1 Nov 2018

Fingerprint

Dry Eye Syndromes
Fluorescein
Cornea
Image processing
Keratoconus

Keywords

  • Corneal images
  • Dry eye
  • Fluorescein staining
  • Image processing
  • Oxford grading scale

Cite this

Bağbaba, Ayşe ; Şen, Baha ; Delen, Dursun ; Uysal, Betül Seher. / An Automated Grading and Diagnosis System for Evaluation of Dry Eye Syndrome. In: Journal of Medical Systems. 2018 ; Vol. 42, No. 11.
@article{e1473d83f235494cabf5851d10299dce,
title = "An Automated Grading and Diagnosis System for Evaluation of Dry Eye Syndrome",
abstract = "This article describes methods used to determine the severity of Dry Eye Syndrome (DES) based on Oxford Grading Schema (OGS) automatically by developing and applying a decider model. The number of dry punctate dots occurred on corneal surface after corneal fluorescein staining can be used as a diagnostic indicator of DES severity according to OGS; however, grading of DES severity exactly by carefully assessing these dots is a rather difficult task for humans. Taking into account that current methods are also subjectively dependent on the perception of the ophtalmologists coupled with the time and resource intensive requirements, enhanced diagnosis techniques would greatly contribute to clinical assessment of DES. Automated grading system proposed in this study utilizes image processing methods in order to provide more objective and reliable diagnostic results for DES. A total of 70 fluorescein-stained cornea images from 20 patients with mild, moderate, or severe DES (labeled by an ophthalmologist in the Keratoconus Center of Yildirim Beyazit University Ataturk Training and Research Hospital) used as the participants for the study. Correlations between the number of dry punctate dots and DES severity levels were determined. When automatically created scores and clinical scores were compared, the following measures were observed: Pearson’s correlation value between the two was 0.981; Lin’s Concordance Correlation Coefficients (CCC) was 0.980; and 95{\%} confidence interval limites were 0.963 and 0.989. The automated DES grade was estimated from the regression fit and accordingly the unknown grade is calculated with the following formula: Gpred = 1.3244 log(Ndots) - 0.0612. The study has shown the viability and the utility of a highly successful automated DES diagnostic system based on OGS, which can be developed by working on the fluorescein-stained cornea images. Proper implemention of a computationally savvy and highly accurate classification system, can assist investigators to perform more objective and faster DES diagnoses in real-world scenerios.",
keywords = "Corneal images, Dry eye, Fluorescein staining, Image processing, Oxford grading scale",
author = "Ayşe Bağbaba and Baha Şen and Dursun Delen and Uysal, {Bet{\"u}l Seher}",
year = "2018",
month = "11",
day = "1",
doi = "10.1007/s10916-018-1086-3",
language = "English",
volume = "42",
journal = "Journal of Medical Systems",
issn = "0148-5598",
publisher = "Springer New York",
number = "11",

}

An Automated Grading and Diagnosis System for Evaluation of Dry Eye Syndrome. / Bağbaba, Ayşe; Şen, Baha; Delen, Dursun; Uysal, Betül Seher.

In: Journal of Medical Systems, Vol. 42, No. 11, 227, 01.11.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An Automated Grading and Diagnosis System for Evaluation of Dry Eye Syndrome

AU - Bağbaba, Ayşe

AU - Şen, Baha

AU - Delen, Dursun

AU - Uysal, Betül Seher

PY - 2018/11/1

Y1 - 2018/11/1

N2 - This article describes methods used to determine the severity of Dry Eye Syndrome (DES) based on Oxford Grading Schema (OGS) automatically by developing and applying a decider model. The number of dry punctate dots occurred on corneal surface after corneal fluorescein staining can be used as a diagnostic indicator of DES severity according to OGS; however, grading of DES severity exactly by carefully assessing these dots is a rather difficult task for humans. Taking into account that current methods are also subjectively dependent on the perception of the ophtalmologists coupled with the time and resource intensive requirements, enhanced diagnosis techniques would greatly contribute to clinical assessment of DES. Automated grading system proposed in this study utilizes image processing methods in order to provide more objective and reliable diagnostic results for DES. A total of 70 fluorescein-stained cornea images from 20 patients with mild, moderate, or severe DES (labeled by an ophthalmologist in the Keratoconus Center of Yildirim Beyazit University Ataturk Training and Research Hospital) used as the participants for the study. Correlations between the number of dry punctate dots and DES severity levels were determined. When automatically created scores and clinical scores were compared, the following measures were observed: Pearson’s correlation value between the two was 0.981; Lin’s Concordance Correlation Coefficients (CCC) was 0.980; and 95% confidence interval limites were 0.963 and 0.989. The automated DES grade was estimated from the regression fit and accordingly the unknown grade is calculated with the following formula: Gpred = 1.3244 log(Ndots) - 0.0612. The study has shown the viability and the utility of a highly successful automated DES diagnostic system based on OGS, which can be developed by working on the fluorescein-stained cornea images. Proper implemention of a computationally savvy and highly accurate classification system, can assist investigators to perform more objective and faster DES diagnoses in real-world scenerios.

AB - This article describes methods used to determine the severity of Dry Eye Syndrome (DES) based on Oxford Grading Schema (OGS) automatically by developing and applying a decider model. The number of dry punctate dots occurred on corneal surface after corneal fluorescein staining can be used as a diagnostic indicator of DES severity according to OGS; however, grading of DES severity exactly by carefully assessing these dots is a rather difficult task for humans. Taking into account that current methods are also subjectively dependent on the perception of the ophtalmologists coupled with the time and resource intensive requirements, enhanced diagnosis techniques would greatly contribute to clinical assessment of DES. Automated grading system proposed in this study utilizes image processing methods in order to provide more objective and reliable diagnostic results for DES. A total of 70 fluorescein-stained cornea images from 20 patients with mild, moderate, or severe DES (labeled by an ophthalmologist in the Keratoconus Center of Yildirim Beyazit University Ataturk Training and Research Hospital) used as the participants for the study. Correlations between the number of dry punctate dots and DES severity levels were determined. When automatically created scores and clinical scores were compared, the following measures were observed: Pearson’s correlation value between the two was 0.981; Lin’s Concordance Correlation Coefficients (CCC) was 0.980; and 95% confidence interval limites were 0.963 and 0.989. The automated DES grade was estimated from the regression fit and accordingly the unknown grade is calculated with the following formula: Gpred = 1.3244 log(Ndots) - 0.0612. The study has shown the viability and the utility of a highly successful automated DES diagnostic system based on OGS, which can be developed by working on the fluorescein-stained cornea images. Proper implemention of a computationally savvy and highly accurate classification system, can assist investigators to perform more objective and faster DES diagnoses in real-world scenerios.

KW - Corneal images

KW - Dry eye

KW - Fluorescein staining

KW - Image processing

KW - Oxford grading scale

UR - http://www.scopus.com/inward/record.url?scp=85054592081&partnerID=8YFLogxK

U2 - 10.1007/s10916-018-1086-3

DO - 10.1007/s10916-018-1086-3

M3 - Article

C2 - 30298212

AN - SCOPUS:85054592081

VL - 42

JO - Journal of Medical Systems

JF - Journal of Medical Systems

SN - 0148-5598

IS - 11

M1 - 227

ER -