Distinction between Manifestations of Diabetic Retinopathy and Dust Artifacts Using Three-Dimensional HSV Color Space

Authors: Naoto Suzuki

Abstract:

Many ophthalmologists find it difficult to distinguish between small retinal hemorrhages and dust artifacts when using fundus photography for the diagnosis of diabetic retinopathy. Six patients with diabetic retinopathy underwent fundus photography, which revealed dust artifacts in the photographs of some patients. We constructed an experimental device similar to the optical system of the fundus camera and colored the fundi of the artificial eyes with khaki, sunset, rose and sunflower colors. Using the experimental device, we photographed dust artifacts using each artificial eyes. We used Scilab 5.4.0 and SIVP 0.5.3 softwares to convert the red, green, and blue (RGB) color space to the hue, saturation, and value (HSV) color space. We calculated the differences between the areas of manifestations and perimanifestations and the areas of dust artifacts and periartifacts using average HSVs. The V values in HSV for the manifestations were as follows: hemorrhages, 0.06 ± 0.03; hard exudates, −0.12 ± 0.06; and photocoagulation marks, 0.07 ± 0.02. For dust artifacts, visualized in the human and artificial eyes, the V values were as follows: human eye, 0.19 ± 0.03; khaki, 0.41 ± 0.02; sunset, 0.43 ± 0.04; rose, 0.47 ± 0.11; and sunflower, 0.59 ± 0.07. For the human and artificial eyes, we calculated two sensitivity values of dust artifacts compared to manifestation areas. V values of the HSV color space enabled the differentiation of small hemorrhages, hard exudates, and photocoagulation marks from dust artifacts.

Keywords: Diabetic retinopathy, HSV color space, small hemorrhages, hard exudates, photocoagulation marks.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1126874

References:

[1] T. Tsuchiya, "Measure Against Lifestyle Related Disease," JMAJ, Vol.49 No.3, 2006, pp.132-134.
[2] Z.T. Bloomgarden, "American Diabetes Association Annual Meeting, 1999, Diabetes and obesity," Diabetes Care, Vol.23, No.1, 2000, pp.118-124.
[3] S.S. Savant, H.B. Chandalia, "Diabetic retinopathy," Int J Diabetes Dev Ctries, Vol.10, 1999, pp.9-25.
[4] American Diabetes Association, "Diabetic retinopathy," Clinical Diabetes, Vol.19 No.1, 2001, pp.29-32.
[5] J.B. Brown, K.L. Pedula, K.H. Summers, "Diabetic retinopathy," Diabetes Care, Vol.26 No.9, 2003, pp.2637-2642.
[6] S. Garg, R.M. Davis, "Diabetic retinopathy screening update," Clinical diabetes 2009, Vol.27 No.4, 2009, pp.140-145.
[7] M.S. Figueroa, I. Contreras, S. Noval, "Anti-angiogetic drugs as an adjunctive therapy in the surgical treatment of diabetic retinopathy," Curr Diabetes Rev, Vol.5 No.1, 2009, pp.52-56.
[8] E. Fernández-Caldas, W.L. Trudeau, D.K. Ledford, "Environmental control of indoor biologic agents," J Allergy Clin Immunol, Vol.2 No.2, 1994, pp.404-412.
[9] A.G. Oomen, J.P.C.M. Janssen, A. Dusseldorp, et al., "Exposure to chemicals via house dust," RIVM Report 609021064, 2008, pp.11-18.
[10] M. Born, E. Wolf, "Principles of Optics 7th expanded edition, Electromagnetic Theory of Propagation, Interference and Diffraction of Light," Cambridge Univ Press, 1999.
[11] R.G. Willson, M.W. Maimone, A.E. Johnson, et al., "An Optical Model for Image Artifacts Produced by Dust Particles on Lenses," Proceedings of ISAIRAS 2005 Conference, 2005.
[12] A.V. Shukla, "Clinical Optics Primer for Ophthalmic Medical Personnel, A Guide to Laws, Formulae, Calculations, and Clinical Applications," SLACK Inc, 2009.
[13] D.D. David, R. Prescott, S. Kennedy, "Simultaneous stereoscopic fundus camera incorporating a single optical axis," Invest Ophthalmol Vis Sci March, 1980, pp.289-297.
[14] R. Zeimer, S. Zou, T. Meeder, et al., "A fundus camera dedicated to the screening of diabetic retinopathy in the primary-care physician’s office," Invest Ophthalmol Vis Sci May, Vol. 43 No.5, 2002, pp.1581-1587.
[15] R.F. Lyon, "Prism-Based Color Separation for Professional Digital Photography," Proceedings of IS&T’s PICS 2000 Conference: Image Processing, Image Quality, Image Capture Systems Conference, 2000, Oregon, USA, 2000.
[16] A.E. Dirik, H.T. Sencar, N. Memon, "Source Camera Identification Based on Sensor dust Characteristics," The proceedings of Signal Processing Applications for Public Security and Forensics 2007, SAFE’07, IEEE Workshop, 2007.
[17] A. Zamfir, A. Drimbarean, M. Zamfir, et al., "An Optic Model of the Appearance of Blemishes in Digital Photographs," Proceedings of SPIE 2007, Vol. 6502, Digital Photography 3, 2007.
[18] R. Bergman, R. Maurer, H. Nachlieli, et al., "Comprehensive Solutions for Removal of Dust and Scratches from Images," Journal of Electronic Imaging, Vol.17 No.1, 2008, pp.1-25.
[19] A.E. Dirik, H.T. Sencar, N. Memon, "Digital Single Lens Reflex Camera Identification From Traces of Sensor Dust," IEEE Trans Info For and Sec 2008, Vol.3 No.3, 2008, pp.539-552.
[20] N. Suzuki, "Basic Research for Distinguishing Small Retinal Hemorrhages from Dust Artifact by using Hue, Lightness, and Saturation Color Space," International Journal of Medical, Health, Biomedical, Bioengineering and Pharmaceutical Engineering, Vol.6, No.5, 2012, pp151-159.
[21] C.C. Thomas, "OPTICS", Springfield, 1968, pp.156-7.