Premium
Geometric Morphometric Comparison of Retinal Veins between Healthy Individuals and Individuals Diagnosed with Glaucoma and Diabetic Retinopathy
Author(s) -
Koons Aaron W,
Zdilla Matthew J
Publication year - 2017
Publication title -
the faseb journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.709
H-Index - 277
eISSN - 1530-6860
pISSN - 0892-6638
DOI - 10.1096/fasebj.31.1_supplement.585.11
Subject(s) - fundus (uterus) , diabetic retinopathy , ophthalmology , retinal , glaucoma , medicine , optic disc , retina , retinal vein , optic cup (embryology) , optometry , diabetes mellitus , biology , neuroscience , biochemistry , phenotype , gene , eye development , endocrinology
Segmentation algorithms have been investigated for the identification of ophthalmic diseases via fundus images; however, patterns of vasculature in the retina have not been assessed via geometric morphometric techniques to differentiate normal and pathologic fundus images. This study utilized the High‐Resolution Fundus Image Database to compare 15 images of healthy patients, 15 images of patients with diabetic retinopathy, and 15 images of glaucomatous patients. Retinal veins were selected for pattern analysis due to the ease of identification. Segments from the most prominent inferior and superior retinal veins traveling from the edge of the optic disk to a vertical line drawn through center of the fovea were selected for analysis. Canonical variate analysis revealed statistically significant differences between the shapes of retinal vein patterns in healthy eyes, eyes with glaucoma, and eyes with diabetic retinopathy. Geometric morphometric analysis may be a useful tool in the identification of diseases from anatomical differences of blood vessels identified in fundus images. Support or Funding Information WV Research Challenge Fund [HEPC.dsr.14.13]