Ординатура / Офтальмология / Английские материалы / Automated Image Detection of Retinal Pathology_Jelinek, Cree_2009

(a)

(b)

(c)

FIGURE 2.4

Optical Coherence Tomography (OCT). (a) Normal macula of a diabetic with no DR. (b) A patient with 6/6 acuity and microaneurysms close to the fovea. OCT shows intraretinal thickening and cystic spaces of intraretinal edema. Edema just involves the fovea. (c) The same patient six months later. Visual acuity has fallen to 6/12. There is increased intraretinal edema with foveal involvement. (See color insert.)

The minimum image field is an equivalent view to a 45° horizontal and 40° vertical image centered on the macula that includes the optic disc. More extensive coverage, that is, two or more views, provides more data and may allow for classification of retinopathy. As the optic disc is a simple landmark for the photographer to find, three 45° views with the optic disc placed at the left edge, the center, and the right edge are a simple set to obtain that cover a wide area of retina and include a view of the macula. An automated system could determine this by identifying the optic disc. It can be recognized by its approximate size, color, and the emergence of the retinal vasculature; tracking the vascular tree back to its source is an alternative. There are situations where there is difficulty in accurately identifiying the optic disc. The optic disc can be locally obscured in diabetic retinopathy either by preretinal hemorrhage, fibrovascular tissue, or retinal detachment, all advanced states of disease. Large accumulations of hard exudate could appear as an optic disc size white lesion. Uncommonly there could be other abnormalities that superficially resemble the optic disc, for example, chorioretinal scars may be white and may be associated with vessels.

Due to imperfections in centering some retinal photographs have a peripheral segment obscured while the remainder is of good quality. Poor quality areas could be enhanced or removed and analysis could also determine if there is then still sufficient area of quality image. A composite retinal image could be constructed from a set of retinal images taken widely around the retina by mapping the retinal vascular tree.

To classify retinopathy there must be an analysis of each of the four quadrants centered on the optic disc (quandants are centered on the optic disc rather than on center of the macula). To distinguish early from moderate and severe NPDR, specific lesions (intraretinal hemorrhages, venous beading, and IRMAs) must be identified and counted in each quadrant. The presence (or absence) of new vessels must be determined to identify PDR (or by their absence NPDR). Normal retinal vessels follow a particular set of parameters. They are a continuously connected tree-like structure, arising from the optic disc, have small curvatures, the vessel caliber changes gradually, and the intensity profile across a vessel is approximated by a Gaussian curve. Arterioles do not cross arterioles and veins do not cross veins. New vessels do not follow these “rules” and in particular may cross a normal vessel or themselves.

To detect DME the macula needs to be accurately identified. The macula may be identified by several strategies; for a right eye image it lies to the left of the optic disc and to the right on a left eye image, the macula is surrounded by a wreath of vasculature with branches pointing toward but not reaching the avascular center, the center has a concentration of pigment, and in a healthy eye has an optical reflex, the foveal reflex. Of these the first feature is universal, the second usually true (there are exceptions, the vascular pattern can be unreliable in a few normal eyes, and in some disease states, for example, heterotopia macula (dragged macula)), the last two features may be obscured in macular disease including diabetic retinopathy itself. With the macula identified the presence, number of, and proximity to the center of the various diabetic retinopathy lesions can be determined. This process for reading retinal images is summarized in Table 2.7.

Table 2.7: Steps in Reading a Retinal Image

1.Identify eye as right or left.

2.Identify quality view of macula as minimum image.

3.Identify lesions of retinopathy:

microaneurysms, hemorrhages, hard exudate, (cotton wool spot,) venous beading, new vessels, fibrosis, vitreous hemorrhage.

4.Lesions’ proximity to macula center as indicator for DME.

5.Grading by identification and quantification of lesions in four quadrants.

2.10.2Frequency of screening

The optimal frequency for diabetic retinopathy screening is unknown. Without empirical data to show otherwise, annual screening is recommended [139]. Less frequent re-screening may be needed for those with no apparent retinopathy or mild NPDR with no apparent DME. For these patients, the annual incidence of progression to either PDR or DME is low and therefore a longer interval between examinations may be appropriate [140]. Based on cost effectiveness there is a clear argument for only screening those with no retinopathy every two or three years. Effectiveness is virtually unchanged for very significant screening cost savings. The need for annual screening for some type 2 diabetics has been questioned [141].

2.10.3Cost effectiveness of screening

The cost and benefits of screening will vary depending on the perspective taken. An accepted measure of utility is the Cost per Sight Year Saved. This shows diabetic retinopathy screening to be highly effective [142; 143].

2.10.4Access to care and screening

The size of the diabetes epidemic, socioeconomic, cultural and geographic issues, lack of patient education, limited funding with scarce health resources, incomplete communication between health care providers with broken continuity of care and incomplete patient registers all contribute to many patients missing out on adequate eye care. With effective treatment readily available, there is unnecessary loss of vision and blindness.

Access to health care is also likely to be a determinant of duration of diabetes before diagnosis, metabolic control after diagnosis, retinal screening penetration and access to early treatment. At least in Australia, there appears to be no major difference in prevalence of retinopathy between rural and urban areas although other rural-urban differences in eye disease exist [144].

As a complex, largely asymptomatic, chronic disease, there are many reasons for access to health care to be patchy. Barriers to diabetes care can be placed in five domains: psychological (i.e., behavioral), psychosocial (i.e., the way the individual and those around interact with each other such as family), internal physical (i.e., physical conditions that prevent self care), external physical (i.e., barriers relating to the health system in its widest context) and educational [145].

2.11Conclusion

Digital photographic screening of the diabetic population is an essential health care measure for detection of early diabetic retinopathy. Automated retinal image analysis promises to provide consistently accurate and detailed screening information, an effective solution to managing the huge volume of images generated by screening the large and ever increasing diabetic population and “instant” image analysis at the time of screening.

References

[1]Fong, D.S., Aiello, L.P., and Gardner, Retinopathy in diabetes, Diabetes Care, 27(suppl 1), S84, 2004.

[2]Zimmet, P., Alberti, K.G., and Shaw, J., Global and societal implications of the diabetes epidemic, Nature, 414, 782, 2001.

[3]New Zealand Herald, World faces diabetes catastrophe, experts say, New Zealand Herald, August 26, 2003.

[4]Stumvoll, M., Goldstein, B.J., and van Haeften, T.W., Type 2 diabetes: Principles of pathogensis and therapy, Lancet, 365, 1333, 2005.

[5]Knowler, W.C., Barrett-Connor, E., Fowler, S.E., et al., Reduction in the incidence of type 2 diabetes with lifestyle intervention or metformin, N Engl J Med., 346, 393, 2002.

[6]Tuomilehto, J., Lindstrom, J., Eriksson, J.G., et al., Prevention of type 2 diabetes mellitus by changes in lifestyle among subjects with impaired glucose tolerance, N Engl J Med., 344, 1343, 2001.

[7]Ramachandran, A., Snehalatha, C., Mary, S., et al., The Indian Diabetes Prevention Programme shows that lifestyle modification and metformin prevent type 2 diabetes in Asian Indian subjects with impaired glucose tolerance (IDPP-1), Diabetologia, 49, 289, 2006.

[8]Daneman, D., Type 1 diabetes, Lancet, 367, 847, 2006.

[9]Permutt, M.A., Wasson, J., and N., C., Genetic epidemiology of diabetes, J Clin Invest, 115, 1431, 2005.

[10]Fagot-Campagna, A., Pettitt, D.J., Engelgau, M.M., et al., Type 2 diabetes among North American children and adolescents: An epidemiologic review and a public health perspective, J. Pediatr., 136, 664, 2000.

[11]Rosenbloom, A., Joe, J.R., Young, R.S., et al., Emerging epidemic of type 2 diabetes in youth, Diabetes Care, 22, 345, 1999.

[12]McElduff, A., Ross, G.P., Lagstrom,¨ J.A., et al., Pregestational diabetes and pregnancy: An Australian experience, Diabetes Care, 28, 1260, 2005.

[13]Pettitt, D.J., Bennett, P.H., Knowler, W.C., et al., Gestational diabetes mellitus and impaired glucose tolerance during pregnancy: Long terms effects on obesity and glucose tolerance in the offspring, Diabetes, 34(supp 2), 119, 1985.

[14]Amos, A.F., McCarty, D.J., and Zimmet, P., The rising global burden of diabetes and its complications: Estimates and projections to the year 2010, Diab Med, 14(supp 5), S1, 1997.

[15]International Diabetes Federation, ed., Diabetes Atlas, International Diabetes Federation, 2nd ed., 2003.

[16]Dorf, A. and et al., Retinopathy in Pima Indians: Relationship to glucose level, duration of diabetes and age at examination in a population with a high prevalence of diabetes, Diabetes, 25, 554, 1976.

[17]Harris, M., Klein, R., Welborn, T., et al., Onset of NIDDM occurs at least 4–7 years before clinical diagnosis, Diabetes Care, 15, 815, 1992.

[18]Tapp, R.J., Shaw, J.E., Harper, C.A., et al., The prevalence of and factors associated with diabetic retinopathy in the Australian population, Diabetes Care, 26, 1731, 2003.

[19]Yu, T., Mitchell, P., Berry, G., et al., Retinopathy in older persons without diabetes and its relationship to hypertension, Arch Ophthalmol, 116, 83, 1998.

[20]Aiello, L.P., Cahill, M.T., and Wong, J.S., Systemic considerations in the management of diabetic retinopathy, Am J Ophthalmol, 132, 760, 2001.

[21]Klein, R., Klein, B.E., Moss, S.E., et al., The Wisconsin Epidemiologic Study of Diabetic Retinopathy. IV. Diabetic macular edema, Ophthalmology, 91, 1464, 1985.

[22]Williams, R., Airey, M., Baxter, H., et al., Epidemiology of diabetic retinopathy and macular oedema: A systematic review, Eye, 18, 963, 2004.

[23]Simmons, D., Clover, G., and Hope, C., Ethnic differences in diabetic

retinopathy, Diabet Med, 24, 1093, 2007.

[24]Frank, R.N., Diabetic retinopathy, N Engl J Med, 350, 48, 2004.

[25]Early Treatment Diabetic Retinopathy Study Research Group, Grading diabetic retinopathy from stereoscopic color fundus photographs–an extension of the modified Airlie House classification. ETDRS report number 10., Ophthalmology, 98, 786, 1991.

[26]Klein, R., Barriers to prevention of vision loss caused by diabetic retinopathy, Arch Ophthalmol, 115, 1073, 1997.

[27]American Academy of Ophthalmology, Diabetic retinopathy disease severity scale 2002, 2002, http://www.aao.org/education/library/recommendations/ international dr.cfm.

[28]Klein, R., Klein, B.E., Moss, S.E., et al., The Wisconsin Epidemiologic Study of Diabetic Retinopathy: XVII. The 14-year incidence and progression of diabetic retinopathy and associated risk factors in type 1 diabetes, Ophthalmology, 105, 1801, 1998.

[29]Klein, R., Klein, B.E., and Moss, S.E., How many steps of progression of diabetic retinopathy are meaningful? The Wisconsin Epidemiologic Study of Diabetic Retinopathy, Arch Ophthalmol, 119, 547, 2001.

[30]Klein, R., Klein, B.E., Moss, S.E., et al., The Wisconsin Epidemiologic Study of Diabetic Retinopathy. III. Prevalence and risk of diabetic retinopathy when age at diagnosis is 30 or more years, Arch Ophthalmol, 102, 527, 1984.

[31]Yanko, L., Goldbourt, U., Michaelson, I.C., et al., Prevalence and 15-year incidence of retinopathy and associated characteristics in middle-aged and elderly diabetic men, Br J Ophthalmol, 67, 759, 1984.

[32]Diabetic Retinopathy Vitrectomy Study, Early vitrectomy for severe vitreous hemorrhage in diabetic retinopathy. Four-year results of a randomized trial: Diabetic Retinopathy Vitrectomy Study Report 5, Arch Ophthalmol, 108, 958, 1990.

[33]The Diabetes Control and Complications Trial Research Group, The effect of intensive treatment of diabetes on the development and progression of longterm complications in insulin-dependent diabetes mellitus, N Engl J Med, 329, 977, 1993.

[34]Diabetes Control and Complications Trial Research Group, Progression of retinopathy with intensive versus conventional treatment in the Diabetes Control and Complications Trial, Ophthalmology, 102, 647, 1995.

[35]UK Prospective Diabetes Study (UKPDS) Group, Intensive blood-glucose control with sulphonylureas or insulin compared with conventional treatment and risk of complications in patients with type 2 diabetes (UKPDS 33), Lancet, 352, 837, 1998.

[36]Klein, R., Klein, B.E., Lee, K.E., et al., The incidence of hypertension in insulin-dependent diabetes, Arch Intern Med, 156, 622, 1996.

[37]Klein, R., Klein, B.E., Moss, S.E., et al., Blood pressure and hypertension in diabetes, Am J Epidemiol, 122, 75, 1985.

[38]UK Prospective Diabetes Study (UKPDS) Group, Tight blood pressure control and risk of macrovascular and microvascular complications in type 2 diabetes: UKPDS 38, BMJ, 317, 703, 1998.

[39]Park, J.Y., Kim, H.K., Chung, Y.E., et al., Incidence and determinants of microalbuminuria in Koreans with type 2 diabetes, Diabetes Care, 21, 530, 1998.

[40]Hasslacher, C., Bostedt-Kiesel, A., Kempe, H.P., et al., Effect of metabolic factors and blood pressure on kidney function in proteinuric type 2 (non- insulin-dependent) diabetic patients, Diabetologia, 36, 1051, 1993.

[41]Klein, R., Moss, S.E., and Klein, B.E., Is gross proteinuria a risk factor for the incidence of proliferative diabetic retinopathy? Ophthalmology, 100, 1140, 1993.

[42]Klein, R., Klein, B.E., Moss, S.E., et al., The 10-year incidence of renal insufficiency in people with type 1 diabetes, Diabetes Care, 22, 743, 1999.

[43]Lloyd, G., The importance of accuracy in blood pressure recording, Br J Clin Pract, 49, 284, 1996.

[44]UK Prospective Diabetes Study Group (UKPDS), X. Urinary albumin excretion over 3 years in diet-treated type 2, (non-insulin-dependent) diabetic patients, and association with hypertension, hyperglycaemia and hypertriglyceridaemia, Diabetologia, 36, 1021, 1993.

[45]Moloney, J.B. and Drury, M.I., The effect of pregnancy on the natural course of diabetic retinopathy, Am J Ophthalmol, 93, 745, 1982.

[46]Klein, B.E., Moss, S.E., and Klein, R., Effect of pregnancy on progression of diabetic retinopathy, Diabetes Care, 13, 34, 1990.

[47]Diabetes Control and Complications Trial (DCCT) Research Group, Effect of pregnancy on microvascular complications in the Diabetes Control and Complications Trial, Diabetes Care, 23, 1084, 2000.

[48]Sone, H., Okuda, Y., Kawakami, Y., et al., Progesterone induces vascular endothelial growth factor on retinal pigment epithelial cells in culture, Life Sci, 59, 21, 1996.

[49]Chen, H.C., Newsom, R.S., Patel, V., et al., Retinal blood flow changes during pregnancy in women with diabetes, Invest Ophthalmol Vis Sci, 35, 3199, 1994.

[50]Schocket, L.S., Grunwald, J.E., Tsang, A.F., et al., The effect of pregnancy on

retinal hemodynamics in diabetic versus nondiabetic mothers, Am J Ophthalmol, 128, 477, 1999.

[51]Muhlhauser, I., Cigarette smoking and diabetes: An update, Diabet Med, 11, 336, 1994.

[52]Sawicki, P.T., Muhlhauser, I., Bender, R., et al., Effects of smoking on blood pressure and proteinuria in patients with diabetic nephropathy, J Intern Med, 239, 345, 1996.

[53]Mohr, S.E. and Boswell, R.E., Genetic analysis of Drosophila melanogaster polytene chromosome region 44D–45F: Loci required for viability and fertility, Genetics, 160, 1503, 2002.

[54]Barber, A.J., Lieth, E., Khin, S.A., et al., Neural apoptosis in the retina during experimental and human diabetes. Early onset and effect of insulin, J Clin Invest, 102, 783, 1998.

[55]Ciulla, T.A., Harris, A., Latkany, P., et al., Ocular perfusion abnormalities in diabetes, Acta Ophthalmol Scand, 80, 468, 2002.

[56]Otani, T., Kishi, S., and Maruyama, Y., Patterns of diabetic macular edema with optical coherence tomography, Am J Ophthalmol, 127, 688, 1999.

[57]Gabbay, K.H., Hyperglycemia, polyol metabolism, and complications of diabetes mellitus, Annu Rev Med, 26, 521, 1975.

[58]Sato, S., Secchi, E.F., Lizak, M.J., et al., Polyol formation and NADPHdependent reductases in dog retinal capillary pericytes and endothelial cells,

Invest Ophthalmol Vis Sci, 40, 697, 1999.

[59]Brownlee, M., Vlassara, H., and Cerami, A., Nonenzymatic glycosylation and the pathogenesis of diabetic complications, Ann Intern Med, 101, 527, 1984.

[60]Friedman, E.A., Advanced glycosylated end products and hyperglycemia in the pathogenesis of diabetic complications, Diabetes Care, 22 Suppl 2, B65, 1999.

[61]Schmidt, A.M., Yan, S.D., Wautier, J.L., et al., Activation of receptor for advanced glycation end products: A mechanism for chronic vascular dysfunction in diabetic vasculopathy and atherosclerosis, Circ Res, 84, 489, 1999.

[62]Singh, R., Barden, A., Mori, T., et al., Advanced glycation end-products: A review, Diabetologia, 44, 129, 2001.

[63]Inoguchi, T., Battan, R., Handler, E., et al., Preferential elevation of protein kinase C isoform beta II and diacylglycerol levels in the aorta and heart of diabetic rats: Differential reversibility to glycemic control by islet cell transplantation, Proc Natl Acad Sci USA, 89, 11059, 1992.

[64]Xia, P., Inoguchi, T., Kern, T.S., et al., Characterization of the mechanism for the chronic activation of diacylglycerol-protein kinase C pathway in diabetes

and hypergalactosemia, Diabetes, 43, 1122, 1994.

[65]Nishikawa, T., Edelstein, D., and Brownlee, M., The missing link: A single unifying mechanism for diabetic complications, Kidney Int Suppl, 77, S26, 2001.

[66]Taher, M.M., Garcia, J.G., and Natarajan, V., Hydroperoxide-induced diacylglycerol formation and protein kinase C activation in vascular endothelial cells, Arch Biochem Biophys, 303, 260, 1993.

[67]Nagpala, P.G., Malik, A.B., Vuong, P.T., et al., Protein kinase C beta 1 overexpression augments phorbol ester-induced increase in endothelial permeability, J Cell Physiol, 166, 249, 1996.

[68]Xia, P., Aiello, L.P., Ishii, H., et al., Characterization of vascular endothelial growth factor’s effect on the activation of protein kinase C, its isoforms, and endothelial cell growth, J Clin Invest, 98, 2018, 1997.

[69]Giugliano, D., Ceriello, A., and Paolisso, G., Oxidative stress and diabetic vascular complications, Diabetes Care, 19, 257, 1996.

[70]Sakata, K., Funatsu, H., Harino, S., et al., Relationship between macular microcirculation and progression of diabetic macular edema, Ophthalmology, 113, 1385, 2006.

[71]McMillan, D.E., Plasma protein changes, blood viscosity, and diabetic microangiopathy, Diabetes, 25, 858, 1976.

[72]McMillan, D.E., Utterback, N.G., and La Puma, J., Reduced erythrocyte deformability in diabetes, Diabetes, 27, 895, 1978.

[73]Schmid-Schonbein, H. and Volger, E., Red-cell aggregation and red-cell deformability in diabetes, Diabetes, 25, 897, 1976.

[74]Sagel, J., Colwell, J.A., Crook, L., et al., Increased platelet aggregation in early diabetus mellitus, Ann Intern Med, 82, 733, 1975.

[75]Miyamoto, K. and Ogura, Y., Pathogenetic potential of leukocytes in diabetic retinopathy, Semin Ophthalmol, 14, 233, 2000.

[76]Grant, M.B., Afzal, A., Spoerri, P., et al., The role of growth factors in the pathogenesis of diabetic retinopathy, Expert Opin Investig Drugs, 13, 1275, 2004.

[77]Joussen, A.M., Poulaki, V., Qin, W., et al., Retinal vascular endothelial growth factor induces intercellular adhesion molecule-1 and endothelial nitric oxide synthase expression and initiates early diabetic retinal leukocyte adhesion in vivo, Am J Pathol, 160, 501, 2002.

[78]Miller, J.W., Adamis, A.P., and Aiello, L.P., Vascular endothelial growth factor in ocular neovascularization and proliferative diabetic retinopathy, Diabetes Metab Rev, 13, 37, 1997.

[79]Aiello, L.P., Avery, R.L., Arrigg, P.G., et al., Vascular endothelial growth factor in ocular fluid of patients with diabetic retinopathy and other retinal disorders, N Engl J Med, 331, 1480, 1994.

[80]Cunha-Vaz, J., Faria de Abreu, J.R., and Campos, A.J., Early breakdown of the blood-retinal barrier in diabetes, Br J Ophthalmol, 59, 649, 1975.

[81]Diabetes Control and Complications Trial (DCCT), Early worsening of diabetic retinopathy in the Diabetes Control and Complications Trial, Arch Ophthalmol, 116, 874, 1998.

[82]Diabetic Retinopathy Study Research Group, Preliminary report on effects of photocoagulation therapy, Am J Ophthalmol, 81, 383, 1976.

[83]Sjolie, A.K. and Moller, F., Medical management of diabetic retinopathy, Diabet Med, 21, 666, 2004.

[84]Diabetic Retinopathy Study Research Group, Photocoagulation treatment of proliferative diabetic retinopathy. Clinical application of Diabetic Retinopathy Study (DRS) findings, DRS report number 8, Ophthalmol, 88, 583, 1981.

[85]Diabetic Retinopathy Study Research Group, Four risk factors for severe visual loss in diabetic retinopathy. the third report from the Diabetic Retinopathy Study, Arch Ophthalmol, 97, 654, 1979.

[86]Aiello, L.M., Perspectives on diabetic retinopathy, Am J Ophthalmol, 136, 122, 2003.

[87]Fong, D.S., Strauber, S.F., Aiello, L.P., et al., Comparison of the modified early treatment diabetic retinopathy study and mild macular grid laser photocoagulation strategies for diabetic macular edema, Arch Ophthalmol, 125, 469, 2007.

[88]Early Treatment Diabetic Retinopathy Study (ETDRS) Research Group , Photocoagulation for diabetic macular edema. Early Treatment Diabetic Retinopathy Study Report Number 1, Arch Ophthalmol, 103, 1796, 1985.

[89]Early Treatment Diabetic Retinopathy Study (ETDRS) Research Group, Early photocoagulation for diabetic retinopathy. ETDRS Report Number 9, Ophthalmol, 98(5 Suppl), 766, 1991.

[90]Luttrull, J.K., Musch, D.C., and Spink, C.A., Subthreshold diode micropulse panretinal photocoagulation for proliferative diabetic retinopathy, Eye, 22, 607, 2008.

[91]Luttrull, J.K., Musch, D.C., and Mainster, M.A., Subthreshold diode micropulse photocoagulation for the treatment of clinically significant diabetic macular oedema, Br J Ophthalmol, 89, 74, 2004.

[92]The Diabetic Retinopathy Vitrectomy Study Research Group, Early vitrectomy for severe vitreous hemorrhage in diabetic retinopathy. Two-year results