A computer algorithm to quantitatively assess quality of digital optic disc images

Michele Moscaritolo, Henry D Jampel, Ingrid E Zimmer Galler, Frederick Knezevich, Ran Zeimer

Research output: Contribution to journalArticle

Abstract

Optic disc photography is used in the management and study of glaucoma. Quality assessment is needed at the time of acquisition and during review. A computerized algorithm for objective quality assessment was developed to mimic the procedure used by human observers. It was tested on film-based images obtained with mydriasis (40 normal and 46 glaucomatous eyes) and non-mydriatic digital images (30 normal and 38 glaucomatous eyes). The image sharpness was graded by six masked readers into four categories. The area under the receiver operating characteristic curve for identifying unreadable images was 1.0 for the digital and film-based images and 0.91 and 1.0 for differentiating between unreadable and mediocre images for digital and film-based images, respectively. This pilot study demonstrates that the algorithm can identify all unreadable images. Further studies are necessary to test whether it can be applied to images obtained in other locations on the fundus and with additional cameras.

Original languageEnglish (US)
Pages (from-to)279-284
Number of pages6
JournalOphthalmic Surgery Lasers and Imaging
Volume41
Issue number2
DOIs
StatePublished - Mar 2010

Fingerprint

Optic Disk
Mydriasis
Photography
ROC Curve
Glaucoma

ASJC Scopus subject areas

  • Ophthalmology
  • Surgery

Cite this

A computer algorithm to quantitatively assess quality of digital optic disc images. / Moscaritolo, Michele; Jampel, Henry D; Zimmer Galler, Ingrid E; Knezevich, Frederick; Zeimer, Ran.

In: Ophthalmic Surgery Lasers and Imaging, Vol. 41, No. 2, 03.2010, p. 279-284.

Research output: Contribution to journalArticle

@article{ae05e338df2941b7bb2802b77579f6ab,
title = "A computer algorithm to quantitatively assess quality of digital optic disc images",
abstract = "Optic disc photography is used in the management and study of glaucoma. Quality assessment is needed at the time of acquisition and during review. A computerized algorithm for objective quality assessment was developed to mimic the procedure used by human observers. It was tested on film-based images obtained with mydriasis (40 normal and 46 glaucomatous eyes) and non-mydriatic digital images (30 normal and 38 glaucomatous eyes). The image sharpness was graded by six masked readers into four categories. The area under the receiver operating characteristic curve for identifying unreadable images was 1.0 for the digital and film-based images and 0.91 and 1.0 for differentiating between unreadable and mediocre images for digital and film-based images, respectively. This pilot study demonstrates that the algorithm can identify all unreadable images. Further studies are necessary to test whether it can be applied to images obtained in other locations on the fundus and with additional cameras.",
author = "Michele Moscaritolo and Jampel, {Henry D} and {Zimmer Galler}, {Ingrid E} and Frederick Knezevich and Ran Zeimer",
year = "2010",
month = "3",
doi = "10.3928/15428877-20100303-21",
language = "English (US)",
volume = "41",
pages = "279--284",
journal = "Ophthalmic Surgery Lasers and Imaging Retina",
issn = "2325-8160",
publisher = "Slack Incorporated",
number = "2",

}

TY - JOUR

T1 - A computer algorithm to quantitatively assess quality of digital optic disc images

AU - Moscaritolo, Michele

AU - Jampel, Henry D

AU - Zimmer Galler, Ingrid E

AU - Knezevich, Frederick

AU - Zeimer, Ran

PY - 2010/3

Y1 - 2010/3

N2 - Optic disc photography is used in the management and study of glaucoma. Quality assessment is needed at the time of acquisition and during review. A computerized algorithm for objective quality assessment was developed to mimic the procedure used by human observers. It was tested on film-based images obtained with mydriasis (40 normal and 46 glaucomatous eyes) and non-mydriatic digital images (30 normal and 38 glaucomatous eyes). The image sharpness was graded by six masked readers into four categories. The area under the receiver operating characteristic curve for identifying unreadable images was 1.0 for the digital and film-based images and 0.91 and 1.0 for differentiating between unreadable and mediocre images for digital and film-based images, respectively. This pilot study demonstrates that the algorithm can identify all unreadable images. Further studies are necessary to test whether it can be applied to images obtained in other locations on the fundus and with additional cameras.

AB - Optic disc photography is used in the management and study of glaucoma. Quality assessment is needed at the time of acquisition and during review. A computerized algorithm for objective quality assessment was developed to mimic the procedure used by human observers. It was tested on film-based images obtained with mydriasis (40 normal and 46 glaucomatous eyes) and non-mydriatic digital images (30 normal and 38 glaucomatous eyes). The image sharpness was graded by six masked readers into four categories. The area under the receiver operating characteristic curve for identifying unreadable images was 1.0 for the digital and film-based images and 0.91 and 1.0 for differentiating between unreadable and mediocre images for digital and film-based images, respectively. This pilot study demonstrates that the algorithm can identify all unreadable images. Further studies are necessary to test whether it can be applied to images obtained in other locations on the fundus and with additional cameras.

UR - http://www.scopus.com/inward/record.url?scp=77950415892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950415892&partnerID=8YFLogxK

U2 - 10.3928/15428877-20100303-21

DO - 10.3928/15428877-20100303-21

M3 - Article

C2 - 20307051

AN - SCOPUS:77950415892

VL - 41

SP - 279

EP - 284

JO - Ophthalmic Surgery Lasers and Imaging Retina

JF - Ophthalmic Surgery Lasers and Imaging Retina

SN - 2325-8160

IS - 2

ER -