Automated grading system for evaluation of ocular redness associated with dry eye

Abstract

BackgroundWe have observed that dry eye redness is characterized by a prominence of fine horizontal conjunctival vessels in the exposed ocular surface of the interpalpebral fissure, and have incorporated this feature into the grading of redness in clinical studies of dry eye.AimTo develop an automated method of grading dry eye-associated ocular redness in order to expand on the clinical grading system currently used.MethodsNinety nine images from 26 dry eye subjects were evaluated by five graders using a 0–4 (in 0.5 increments) dry eye redness (Ora Calibra™ Dry Eye Redness Scale [OCDER]) scale. For the automated method, the Opencv computer vision library was used to develop software for calculating redness and horizontal conjunctival vessels (noted as “horizontality”). From original photograph, the region of interest (ROI) was selected manually using the open source ImageJ software. Total average redness intensity (Com-Red) was calculated as a single channel 8-bit image as R – 0.83G – 0.17B, where R, G and B were the respective intensities of the red, green and blue channels. The location of vessels was detected by normalizing the blue channel and selecting pixels with an intensity of less than 97% of the mean. The horizontal component (Com-Hor) was calculated by the first order Sobel derivative in the vertical direction and the score was calculated as the average blue channel image intensity of this vertical derivative. Pearson correlation coefficients, accuracy and concordance correlation coefficients (CCC) were calculated after regression and standardized regression of the dataset.ResultsThe agreement (both Pearson’s and CCC) among investigators using the OCDER scale was 0.67, while the agreement of investigator to computer was 0.76. A multiple regression using both redness and horizontality improved the agreement CCC from 0.66 and 0.69 to 0.76, demonstrating the contribution of vessel geometry to the overall grade. Computer analysis of a given image has 100% repeatability and zero variability from session to session.ConclusionThis objective means of grading ocular redness in a unified fashion has potential significance as a new clinical endpoint. In comparisons between computer and investigator, computer grading proved to be more reliable than another investigator using the OCDER scale. The best fitting model based on the present sample, and usable for future studies, was C4=−12.24+2.12C2HOR+0.88C2RED:C4 is the predicted investigator grade, and C2HOR and C2RED are logarithmic transformations of the computer calculated parameters COM-Hor and COM-Red. Considering the superior repeatability, computer automated grading might be preferable to investigator grading in multicentered dry eye studies in which the subtle differences in redness incurred by treatment have been historically difficult to define.

Measurement variability of the bulbar conjunctival microvasculature in healthy subjects using functional slit lamp biomicroscopy (FSLB)

“…The microvasculature of the bulbar conjunctiva has been the in vivo real-time study site for both ocular and systemic microvascular function in physiological and pathological conditions, such as dry eye (Rodriguez et al, 2013), contact lens wear, (Jiang et al, 2014; Cheung et al, 2012) diabetes (To et al, 2011; Cheung et al, 2009) and sickle cell disease (Wanek et al, 2013; Cheung et al, 2001). Distinct vasculopathies on the bulbar conjunctiva have been identified in these conditions (Jung et al, 2013; Wolf et al, 1990; Jung et al, 1983; Cheung et al, 2012; Wanek et al, 2013; Jiang et al, 2014; Rodriguez et al, 2013; To et al, 2011; Cheung et al, 2009; Cheung et al, 2001).…”

“…The microvasculature of the bulbar conjunctiva has been the in vivo real-time study site for both ocular and systemic microvascular function in physiological and pathological conditions, such as dry eye (Rodriguez et al, 2013), contact lens wear, (Jiang et al, 2014; Cheung et al, 2012) diabetes (To et al, 2011; Cheung et al, 2009) and sickle cell disease (Wanek et al, 2013; Cheung et al, 2001). Distinct vasculopathies on the bulbar conjunctiva have been identified in these conditions (Jung et al, 2013; Wolf et al, 1990; Jung et al, 1983; Cheung et al, 2012; Wanek et al, 2013; Jiang et al, 2014; Rodriguez et al, 2013; To et al, 2011; Cheung et al, 2009; Cheung et al, 2001). Several techniques have been developed to examine the conjunctival blood flow in vivo , including modified scanning laser Ophthalmoscopy (Duench et al, 2007), adapted slit-lamp biomicroscopy digital imaging (Wanek et al, 2013; Shahidi et al, 2010a; Koutsiaris et al, 2010a), slit-lamp stereomicrocope (Jung et al, 1983) and computer-assisted intravital microscopy (CAIM) (To et al, 2011; Cheung et al, 2009; Cheung et al, 2001; Cheung et al, 2012).…”

A Pilot Study Investigating Clinical Responses and Biological Pathways of Azelastine/Fluticasone in Nonallergic Vasomotor Rhinitis before and after Cold Dry Air Provocation

“…1). Bilateral ocular conjunctival redness was also assessed by trained staff before challenge based on a validated descriptive and photographic scale ranging from 0 to 4 in increments of 0.5 [23]. Subjects then entered the EEC and underwent CDA provocation (14 ± 5°C, <15% relative humidity, ×1 h) as described by Bernstein et al [24].…”

Quantifying Ocular Surface Inflammation and Correlating It With Inflammatory Cell Infiltration In Vivo: A Novel Method

“…9 In order to overcome the limits of qualitative measurements, several (semi-) automated techniques have been described. Most of them are based on a combination of color quantification, [10][11][12][13] edge detection, 11 and fractal analysis.…”

“…Many studies, including ours, have tried to minimize variability in image acquisition by setting fixed slitlamp parameters. 10,11,13 In addition, Amparo et al 10 proposed an elegant white-balance correction algorithm to balance differences in lightening conditions. With regard to conjunctival ROIs selection, small interoperator differences should be unimportant given the large amount of total conjunctiva and the fact that the indices do not depend on the number of pixels.…”