Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features

Michael D. Abràmoff, Wallace L M Alward, Emily C. Greenlee, Lesya Shuba, Chan Y. Kim, John H. Fingert, Young H. Kwon

Research output: Contribution to journalArticle

171 Citations (Scopus)

Abstract

PURPOSE. To evaluate a novel automated segmentation algorithm for cup-to-disc segmentation from stereo color photographs of patients with glaucoma for the measurement of glaucoma progression. METHODS. Stereo color photographs of the optic disc were obtained by using a fixed stereo-base fundus camera in 58 eyes of 58 patients with suspected or open-angle glaucoma. Manual planimetry was performed by three glaucoma faculty members to delineate a reference standard rim and cup segmentation of all stereo pairs and by three glaucoma fellows as well. Pixel feature classification was evaluated on the stereo pairs and corresponding reference standard, by using feature computation based on simulation of photoreceptor color opponency and visual cortex simple and complex cells. An optimal subset of 12 features was used to segment all pixels in all stereo pairs, and the percentage of pixels assigned the correct class and linear cup-to-disc ratio (LCDR) estimates of the glaucoma fellows and the algorithm were compared to the reference standard. RESULTS. The algorithm was able to assign cup, rim, and background correctly to 88% of all pixels. Correlations of the LCDR estimates of glaucoma fellows with those of the reference standard were 0.73 (95% CI, 0.58-0.83), 0.81 (95% CI, 0.70-0.89), and 0.86 (95% CI, 0.78-0.91), respectively, whereas the correlation of the algorithm with the reference standard was 0.93 (95% CI, 0.89-0.96; n = 58). CONCLUSIONS. The pixel feature classification algorithm allows objective segmentation of the optic disc from conventional color stereo photographs automatically without human input. The performance of the disc segmentation and LCDR calculation of the algorithm was comparable to that of glaucoma fellows in training and is promising for objective evaluation of optic disc cupping.

Original languageEnglish
Pages (from-to)1665-1673
Number of pages9
JournalInvestigative Ophthalmology and Visual Science
Volume48
Issue number4
DOIs
Publication statusPublished - 2007 Apr 1

Fingerprint

Optic Disk
Glaucoma
Color
Open Angle Glaucoma
Visual Cortex

All Science Journal Classification (ASJC) codes

  • Ophthalmology

Cite this

Abràmoff, Michael D. ; Alward, Wallace L M ; Greenlee, Emily C. ; Shuba, Lesya ; Kim, Chan Y. ; Fingert, John H. ; Kwon, Young H. / Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features. In: Investigative Ophthalmology and Visual Science. 2007 ; Vol. 48, No. 4. pp. 1665-1673.
@article{a65bae612733453d930fdee120b6fb67,
title = "Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features",
abstract = "PURPOSE. To evaluate a novel automated segmentation algorithm for cup-to-disc segmentation from stereo color photographs of patients with glaucoma for the measurement of glaucoma progression. METHODS. Stereo color photographs of the optic disc were obtained by using a fixed stereo-base fundus camera in 58 eyes of 58 patients with suspected or open-angle glaucoma. Manual planimetry was performed by three glaucoma faculty members to delineate a reference standard rim and cup segmentation of all stereo pairs and by three glaucoma fellows as well. Pixel feature classification was evaluated on the stereo pairs and corresponding reference standard, by using feature computation based on simulation of photoreceptor color opponency and visual cortex simple and complex cells. An optimal subset of 12 features was used to segment all pixels in all stereo pairs, and the percentage of pixels assigned the correct class and linear cup-to-disc ratio (LCDR) estimates of the glaucoma fellows and the algorithm were compared to the reference standard. RESULTS. The algorithm was able to assign cup, rim, and background correctly to 88{\%} of all pixels. Correlations of the LCDR estimates of glaucoma fellows with those of the reference standard were 0.73 (95{\%} CI, 0.58-0.83), 0.81 (95{\%} CI, 0.70-0.89), and 0.86 (95{\%} CI, 0.78-0.91), respectively, whereas the correlation of the algorithm with the reference standard was 0.93 (95{\%} CI, 0.89-0.96; n = 58). CONCLUSIONS. The pixel feature classification algorithm allows objective segmentation of the optic disc from conventional color stereo photographs automatically without human input. The performance of the disc segmentation and LCDR calculation of the algorithm was comparable to that of glaucoma fellows in training and is promising for objective evaluation of optic disc cupping.",
author = "Abr{\`a}moff, {Michael D.} and Alward, {Wallace L M} and Greenlee, {Emily C.} and Lesya Shuba and Kim, {Chan Y.} and Fingert, {John H.} and Kwon, {Young H.}",
year = "2007",
month = "4",
day = "1",
doi = "10.1167/iovs.06-1081",
language = "English",
volume = "48",
pages = "1665--1673",
journal = "Investigative Ophthalmology and Visual Science",
issn = "0146-0404",
publisher = "Association for Research in Vision and Ophthalmology Inc.",
number = "4",

}

Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features. / Abràmoff, Michael D.; Alward, Wallace L M; Greenlee, Emily C.; Shuba, Lesya; Kim, Chan Y.; Fingert, John H.; Kwon, Young H.

In: Investigative Ophthalmology and Visual Science, Vol. 48, No. 4, 01.04.2007, p. 1665-1673.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features

AU - Abràmoff, Michael D.

AU - Alward, Wallace L M

AU - Greenlee, Emily C.

AU - Shuba, Lesya

AU - Kim, Chan Y.

AU - Fingert, John H.

AU - Kwon, Young H.

PY - 2007/4/1

Y1 - 2007/4/1

N2 - PURPOSE. To evaluate a novel automated segmentation algorithm for cup-to-disc segmentation from stereo color photographs of patients with glaucoma for the measurement of glaucoma progression. METHODS. Stereo color photographs of the optic disc were obtained by using a fixed stereo-base fundus camera in 58 eyes of 58 patients with suspected or open-angle glaucoma. Manual planimetry was performed by three glaucoma faculty members to delineate a reference standard rim and cup segmentation of all stereo pairs and by three glaucoma fellows as well. Pixel feature classification was evaluated on the stereo pairs and corresponding reference standard, by using feature computation based on simulation of photoreceptor color opponency and visual cortex simple and complex cells. An optimal subset of 12 features was used to segment all pixels in all stereo pairs, and the percentage of pixels assigned the correct class and linear cup-to-disc ratio (LCDR) estimates of the glaucoma fellows and the algorithm were compared to the reference standard. RESULTS. The algorithm was able to assign cup, rim, and background correctly to 88% of all pixels. Correlations of the LCDR estimates of glaucoma fellows with those of the reference standard were 0.73 (95% CI, 0.58-0.83), 0.81 (95% CI, 0.70-0.89), and 0.86 (95% CI, 0.78-0.91), respectively, whereas the correlation of the algorithm with the reference standard was 0.93 (95% CI, 0.89-0.96; n = 58). CONCLUSIONS. The pixel feature classification algorithm allows objective segmentation of the optic disc from conventional color stereo photographs automatically without human input. The performance of the disc segmentation and LCDR calculation of the algorithm was comparable to that of glaucoma fellows in training and is promising for objective evaluation of optic disc cupping.

AB - PURPOSE. To evaluate a novel automated segmentation algorithm for cup-to-disc segmentation from stereo color photographs of patients with glaucoma for the measurement of glaucoma progression. METHODS. Stereo color photographs of the optic disc were obtained by using a fixed stereo-base fundus camera in 58 eyes of 58 patients with suspected or open-angle glaucoma. Manual planimetry was performed by three glaucoma faculty members to delineate a reference standard rim and cup segmentation of all stereo pairs and by three glaucoma fellows as well. Pixel feature classification was evaluated on the stereo pairs and corresponding reference standard, by using feature computation based on simulation of photoreceptor color opponency and visual cortex simple and complex cells. An optimal subset of 12 features was used to segment all pixels in all stereo pairs, and the percentage of pixels assigned the correct class and linear cup-to-disc ratio (LCDR) estimates of the glaucoma fellows and the algorithm were compared to the reference standard. RESULTS. The algorithm was able to assign cup, rim, and background correctly to 88% of all pixels. Correlations of the LCDR estimates of glaucoma fellows with those of the reference standard were 0.73 (95% CI, 0.58-0.83), 0.81 (95% CI, 0.70-0.89), and 0.86 (95% CI, 0.78-0.91), respectively, whereas the correlation of the algorithm with the reference standard was 0.93 (95% CI, 0.89-0.96; n = 58). CONCLUSIONS. The pixel feature classification algorithm allows objective segmentation of the optic disc from conventional color stereo photographs automatically without human input. The performance of the disc segmentation and LCDR calculation of the algorithm was comparable to that of glaucoma fellows in training and is promising for objective evaluation of optic disc cupping.

UR - http://www.scopus.com/inward/record.url?scp=34248355562&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34248355562&partnerID=8YFLogxK

U2 - 10.1167/iovs.06-1081

DO - 10.1167/iovs.06-1081

M3 - Article

C2 - 17389498

AN - SCOPUS:34248355562

VL - 48

SP - 1665

EP - 1673

JO - Investigative Ophthalmology and Visual Science

JF - Investigative Ophthalmology and Visual Science

SN - 0146-0404

IS - 4

ER -