International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-8, Issue-9S3, July 2019 1560 Retrieval Number: I33260789S319/2019©BEIESP DOI: 10.35940/ijitee.I3326.0789S319 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Abstract: Fractal dimension (Df) has been identified as indirect measure in quantifying the complexity of retinal vessel network which is useful for early detection of vascular changes. Reliability studies of Df measurement on retinal vasculature, has been conducted on retinal images processed by using semi-automated software which only permits image with 45ᵒ field of view (FOV). Smartphone-assisted fundus camera retinal image has a maximum 30ᵒ FOV which warrant manual processing in measuring the Df. Retinal blood vessels need to be manually segmented to produce binary images for retinal vasculatures Df measurement. Therefore, this study was conducted to determine the intragrader and intergrader reliability of manual segmentation of the retinal vasculature Df measurement from retinal images taken using a smartphone-assisted fundus camera Forty-five retinal images were captured using the Portable Eye Examination Kit Retina (Peek Retina™, Peek Vision Ltd, UK). Suitable image for Df analysis were selected based on gradable retinal image criteria which included; i) good image focus, ii) centered position of optic nerve head (ONH) and iii) significant blood vessel visibility. The images were cropped 0.5 disc diameters away from disc margin and resized to 500x500 pixels using GNU Image Manipulation Program Version 2.8.18 (GIMP, The GIMP Team, United States). Retinal vessels were manually traced by using layering capabilities for blood vessel segmentation. Df values of segmented blood vessels were measured by using Image J (National Institutes of Health, USA) and its plugin software, FracLac Version 2.5. Intragrader and intergrader reliability was determined by comparing the Df values between; two readings measured one week apart by a grader and readings from two different graders, respectively, using intraclass correlation coefficient (ICC) and Bland-Altman graphical plots. Intragrader agreement for retinal Df showed good reliability with ICC of 0.899 (95% CI: 0.814–0.945). Bland Altman analysis indicated good agreement between Df values at different grading time (mean difference 0.0050; 95% CI:-0.0001–0.0101). Intergrader reliability for retinal Df was high with ICC of 0.814 (95% CI: 0.459–0.919). Bland Altman plot revealed good intergrader agreement for retinal Df between two graders with a bias value of 0.0158 (95% CI: 0.0092–0.0223). In conclusion, manual segmentation of retinal image captured by smartphone-assisted fundus camera has good reliability (0.75 < ICC < 0.9) for Df analysis to study the morphology of retinal vasculatures. Keywords: fractal dimension, retinal vascular, smartphone-assisted fundus camera, Peek retina, reliability I. INTRODUCTION Fractal dimension (Df) has been identified as an indirect measure of retinal vascular complexity. ___________________________________ Revised Manuscript Received on July 22, 2019. Nur Raihan Esa Siti Noor Hakimah Saidi Mohd Zulfaezal Che Azemin Nor Azwani Mohd Shukri Norsham Ahmad Firdaus Yusof @ Alias A few studies on retinal Df analysis found that Df functions is a sensitive biomarker in detecting vascular structural changes [1–3]. The availability of automatic fundus camera in providing digital retinal images allows the retinal vascular complexity to be quantified. Quality of retinal image plays an important role in yielding accurate Df values [4]. Complexity analysis requires good quality retinal photographs for vascular segmentation process in producing binary images (black and white) of self-similar vessels branching patterns. Low retinal image resolution used for vascular segmentation was reported to produce an imprecise measurement of Df [4]. Segmentation of blood vessels involving manual or computer-assisted procedures has been applied in many studies. A study reported that different techniques of segmentation used to skeletonize the vascular network resulted in large variability of Df values [5]. The crucial issues in computing Df measurements are the reliability of the segmentation technique and image resolution used. Reliability analysis is important to assess the consistency of a particular method or parameter (between two measurements) to determine its applicability for the future studies [6]. In the past decades, studies on reliability of manual vascular segmentation yielded mixed results. A reliability study on the manual vascular segmentation in evaluating retinal Df demonstrated good agreement [7]. They reported that retinal Df values derived by manual segmentation techniques between two different graders showed minimal mean differences (0.004) with coefficient of repeatability of ±0.050. On the other hand, the Df values were shown to be less reliable between two observers of a diabetic retinopathy retinal images dataset in another study [8]. The manual segmentation might have led to under- or over segmentation of small retinal vascular structures which resulted in the inconsistent retinal Df values in the study. However, a more recent study found manual segmentation method was validated to quantify retinal Df values among hypertension and diabetic patients [9]. A few studies have been conducted to assess the intragrader and intergrader reliability of semi-automated computer programs in generating self-similar pattern of blood vessels networks for retinal vasculature Df measurements. demonstrated high reliability estimates in evaluating retinal complexity with ICC ranging from 0.93 to 0.95 [10,11]. The findings were supported by Bland-Altman analysis which revealed good intergrader agreement for retinal Df with very minimal average differences between graders. Most of the studies in Reliability of Manual Vascular Segmentation for Retinal Fractal Dimension using Peek Retina tm Nur Raihan Esa, Siti Noor Hakimah Saidi, Mohd Zulfaezal Che Azemin, Nor Azwani Mohd Shukri, Norsham Ahmad, Firdaus Yusof @ Alias