Premium
Topographic analysis of eyelid position using digital image processing software
Author(s) -
Chun Yeoun Sook,
Park Hong Hyun,
Park In Ki,
Moon Nam Ju,
Park Sang Joon,
Lee Jeong Kyu
Publication year - 2017
Publication title -
acta ophthalmologica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.534
H-Index - 87
eISSN - 1755-3768
pISSN - 1755-375X
DOI - 10.1111/aos.13437
Subject(s) - perimeter , repeatability , reproducibility , computer science , margin (machine learning) , correlation coefficient , palpebral fissure , software , roundness (object) , mathematics , normalization (sociology) , artificial intelligence , orthodontics , pattern recognition (psychology) , statistics , medicine , surgery , geometry , machine learning , sociology , anthropology , programming language
Purpose To propose a novel analysis technique for objective quantification of topographic eyelid position with an algorithmatically calculated scheme and to determine its feasibility. Methods One hundred normal eyelids from 100 patients were segmented using a graph cut algorithm, and 11 shape features of eyelids were semi‐automatically quantified using in‐house software. To evaluate the intra‐ and inter‐examiner reliability of this software, intra‐class correlation coefficients ( ICC s) were used. To evaluate the diagnostic value of this scheme, the correlations between semi‐automatic and manual measurements of margin reflex distance 1 ( MRD 1) and margin reflex distance 2 ( MRD 2) were analysed using a Bland–Altman analysis. To determine the degree of agreement according to manual MRD length, the relationship between the variance of semi‐automatic measurements and the manual measurements was evaluated using linear regression. Results Intra‐ and inter‐examiner reliability were excellent, with ICC s ranging from 0.913 to 0.980 in 11 shape features including MRD 1, MRD 2, palpebral fissure, lid perimeter, upper and lower lid lengths, roundness, total area, and medial, central, and lateral areas. The correlations between semi‐automatic and manual MRD s were also excellent, with better correlation in MRD 1 than in MRD 2 ( R = 0.893 and 0.823, respectively). In addition, significant positive relationships were observed between the variance and the length of MRD 1 and 2; the longer the MRD length, the more the variance. Conclusion The proposed novel optimized integrative scheme, which is shown to have high repeatability and reproducibility, is useful for topographic analysis of eyelid position.