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

doi:10.1167/iovs.06-1081

Back

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

Journal article

Open access

Peer reviewed

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 and Young H Kwon

Investigative ophthalmology & visual science, Vol.48(4), pp.1665-1673

04/2007

DOI: 10.1167/iovs.06-1081

PMCID: PMC2739577

PMID: 17389498

Files and links (1)

url

https://doi.org/10.1167/iovs.06-1081View

Published (Version of record) Open Access

Abstract

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. 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. 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). 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.

Algorithms

Humans

Image Interpretation, Computer-Assisted - methods

Middle Aged

Optic Nerve Diseases - diagnosis

Glaucoma, Open-Angle - diagnosis

Ocular Hypertension - diagnosis

Female

Male

Disease Progression

Optic Disk - pathology

Photography - methods

Details

Title: Subtitle: Automated segmentation of the optic disc from stereo color photographs using physiologically plausible features
Creators: Michael D Abràmoff - Department of Ophthalmology and Visual Sciences, University of Iowa Hospitals and Clinics, 200 Hawkins Drive, Iowa City, IA 52242, USA. michael-abramoff@uiowa.edu
Wallace L M Alward
Emily C Greenlee
Lesya Shuba
Chan Y Kim
John H Fingert
Young H Kwon
Resource Type: Journal article
Publication Details: Investigative ophthalmology & visual science, Vol.48(4), pp.1665-1673
DOI: 10.1167/iovs.06-1081
PMID: 17389498
PMCID: PMC2739577
NLM abbreviation: Invest Ophthalmol Vis Sci
ISSN: 0146-0404
eISSN: 1552-5783
Publisher: United States
Grant note: R01 EY 017066 / NEI NIH HHS R01 EY017066 / NEI NIH HHS R01 EY017066-02 / NEI NIH HHS R01 EY017066-01 / NEI NIH HHS
Language: English
Date published: 04/2007
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Ophthalmology and Visual Sciences
Record Identifier: 9983806391302771

Metrics

29 Record Views

189 Times Cited - Web of Science