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

FIGURE 7.A.1

Primary monitor — image display.

The concept of “zone” adopted from the Modified ARIC grid is used in IVAN; it is composed of three concentric circles that demarcate an average optic disc with Zone A defined as the region from the disc margin to 12 disc diameter from the disc, and Zone B defined as the region from 12 disc diameter to 1 disc diameter from the disc. All retinal vessels are measured in Zone B.

7.A.1 Grading an image

Upon opening IVAN, the software automatically places the overlying grid on the brightest point of the image (usually the optic disc), detects vessels, and traces their width. The color blue denotes venules and the color red denotes arterioles. The vessels are automatically assigned as arteriole or venule; in the case of uncertainty, the vessel is assigned as an arteriole. The data table on the control window locates each vessel by its clockwise angle in degrees and displays the mean width and standard deviation (sigma) for each measured vessel (Figure 7.A.2).

The grader is responsible for visual evaluation of the automated display and making any necessary modifications. This includes the option to override any of the initial automated decisions or measurements such as adjusting the placement of the grid, changing the vessel type, deleting vessels, remeasuring vessels, and adding significant vessels missed in the initial automation.

Retinal Vascular Changes as Biomarkers of Systemic Cardiovascular Diseases 203

A

B

C

FIGURE 7.A.2

Secondary monitor — control panel (in arteriole view). The labels are: (A) angle of vessel in degrees, (B) mean width, and (C) standard deviation (sigma). (See color insert following page 174.)

The grader determines the validity of a measurement by the visual display and the width and standard deviation values. More significance should be given to the visual display.

An acceptable measurement is required to have the following:

•The visual vessel trace should have no obvious outliers from the visible edges of the vessel and must have a sigma value 8:00.

•The length of the measured segment should be as long as possible through Zone B for each particular vessel. A reasonable length will depend on the branching of the vessel and the photographic quality of the digital image.

All measurements must be taken proximal to all visible branching regardless of the length of the trunk or the length of the measured segment. If the trunk length in Zone B is short, it may be difficult to get a reliable measurement. In this case, a comment should be added to the saved data indicating the location of the possibly suspect vessel width. If the trunk is ungradeable, then both branches should be measured instead of the trunk.

Retinal Vascular Changes as Biomarkers of Systemic Cardiovascular Diseases 205

V2

A8

V7

A7

V3

FIGURE 7.A.4

Completed grading with grader interaction. (See color insert.)

7.A.3 Obtaining results

When the grader is satisfied that the biggest six arterioles and venules have been traced correctly and are within the acceptable standard deviation, they choose to calculate the image (Figure 7.A.5, label A) to obtain the required results (Figure 7.A.5, label B).

Following Knudtson’s revised formula [60] to calculate the Central Retinal Artery Equivalent (CRAE) and the Central Retinal Vein Equivalent (CRVE), only the width data from the six largest venules and six largest arterioles are required. Artery-to- Vein ratio (A/V ratio) is simply calculated as CRAE divided by CRVE.

The algorithm is thus:

ˆ

where W is the estimate of parent trunk arteriole or venule, and w1 and w2 are the widths of the narrower branch and the wider branch, respectively.

C

D

E

A

B

FIGURE 7.A.5

Control panel view after calculation. The labels are: (A) Calculate button, (B) Results panel, (C) APPROVE, (D) APPROVE W/COMMENT, and (E) REJECT. (See color insert.)

7.A.4 Saving data

At the completion of grading, there are three options for saving the data:

1.APPROVE (Figure 7.A.5, label C)

2.APPROVE W/COMMENT (Figure 7.A.5, label D)

3.REJECT (Figure 7.A.5, label E)

The APPROVE option is used for images that are gradeable and no comment is necessary. The APPROVE W/COMMENT option is used for images that are gradeable but had grading discrepancies that may affect the consistency of the data. These comments will be evaluated by the statisticians. The REJECT option is used for images that are ungradeable and no comment is necessary. Images that are ungradeable very often will have no acceptable automated vessels on the initial display and the grader will have difficulty discerning any vessels. Eyes that have fewer than four acceptable measurements of either vessel type will be considered ungradeable. Output data will automatically be sent to the specified comma separated values (.csv) file upon select-

Retinal Vascular Changes as Biomarkers of Systemic Cardiovascular Diseases 207

ing one of the three saving options and the grader will be prompted to open the next image for grading.

References

[1]van den Hoogen, P.C., Feskens, E.J., Nagelkerke, N.J., et al., The relation between blood pressure and mortality due to coronary heart disease among men in different parts of the world. Seven Countries Study Research Group, N Engl J Med, 342, 1, 2000.

[2]MacMahon, S., Blood pressure and the risk of cardiovascular disease, N Engl J Med, 342, 50, 2000.

[3]Stamler, J., Dyer, A.R., Shekelle, R.B., et al., Relationship of baseline major risk factors to coronary and all-cause mortality, and to longevity: findings from long-term follow-up of Chicago cohorts, Cardiology, 82, 191, 1993.

[4]Wolf, P.A., D’Agostino, R.B., Kannel, W.B., et al., Cigarette smoking as a risk factor for stroke. the Framingham study, JAMA, 259, 1025, 1988.

[5]Langer, R.D., Ganiats, T.G., and Barrett-Connor, E., Paradoxical survival of elderly men with high blood pressure, BMJ, 298, 1356, 1989.

[6]Pekkanen, J., Tervahauta, M., Nissinen, A., et al., Does the predictive value of baseline coronary risk factors change over a 30-year follow-up? Cardiology, 82, 181, 1993.

[7]Prospective studies collaboration, Cholesterol, diastolic blood pressure, and stroke: 13,000 strokes in 450,000 people in 45 prospective cohorts, Lancet, 346, 1647, 1995.

[8]Harjai, K.J., Potential new cardiovascular risk factors: left ventricular hypertrophy, homocysteine, lipoprotein(a), triglycerides, oxidative stress, and fibrinogen, Ann Intern Med, 131, 376, 1999.

[9]Oparil, S. and Oberman, A., Nontraditional cardiovascular risk factors, Am J Med Sci, 317, 193, 1999.

[10]Pahor, M., Elam, M.B., Garrison, R.J., et al., Emerging noninvasive biochemical measures to predict cardiovascular risk, Arch Intern Med, 159, 237, 1999.

[11]Goto, I., Katsuki, S., Ikui, H., et al., Pathological studies on the intracerebral and retinal arteries in cerebrovascular and noncerebrovascular diseases, Stroke, 6, 263, 1975.

[12]Tso, M.O. and Jampol, L.M., Pathophysiology of hypertensive retinopathy, Ophthalmology, 89, 1132, 1982.

[13]Wendland, J.P., Retinal arteriolosclerosis in age, essential hypertension, and diabetes mellitus, Trans Am Ophthalmol Soc, 64, 735, 1966.

[14]Wells, R.E., Herman, M., and Gorlin, R., Microvascular changes in coronary artery disease, Circulation, 237, 33, 1966.

[15]Ashton, N. and Harry, J., The pathology of cotton wool spots and cytoid bodies in hypertensive retinopathy and other diseases, Trans Ophthalmol Soc UK, 83, 91, 1963.

[16]Ashton, N., Peltier, S., and Garner, A., Experimental hypertensive retinopathy in the monkey, Trans Ophthalmol Soc UK, 88, 167, 1969.

[17]Ashton, N., The eye in malignant hypertension, Trans Am Acad Ophthalmol Otolaryngol, 76, 17, 1972.

[18]Garner, A., Ashton, N., Tripathi, R., et al., Pathogenesis of hypertensive retinopathy. an experimental study in the monkey, Br J Ophthalmol, 59, 3, 1975.

[19]Garner, A. and Ashton, N., Pathogenesis of hypertensive retinopathy: a review, J R Soc Med, 72, 362, 1979.

[20]Gunn, R.M., Ophthalmoscopic evidence of (1) arterial changes associated with chronic renal diseases and (2) of increased arterial tension, Trans Ophthalmol Soc UK, 12, 124, 1892.

[21]Gunn, R.M., On ophthalmoscopic evidence of general arterial disease, Trans Ophthalmol Soc UK, 18, 356, 1898.

[22]O’Hare, J.P. and Walker, W.G., Arteriosclerosis and hypertension, Arch Intern Med, 33, 343, 1924.

[23]Friedenwald, H., The Doyne Memorial Lecture: Pathological changes in the retinal blood-vessels in arteriosclerosis and hypertension, Trans Ophthalmol Soc UK, 50, 452, 1930.

[24]Keith, N.M., Wagener, H.P., and Barker, N.W., Some different types of essential hypertension: their course and prognosis, Am J Med Sci, 197, 332, 1939.

[25]Breslin, D.J., Gifford, Jr., R.W., Fairbairn, 2nd, J.F., et al., Prognostic importance of ophthalmoscopic findings in essential hypertension, JAMA, 195, 335, 1966.

[26]Breslin, D.J., Gifford, Jr., R.W., and Fairbairn, 2nd, J.F., Essential hypertension. A twenty-year follow-up study, Circulation, 33, 87, 1966.

[27]Scheie, H.G., Evaluation of ophthalmoscopic changes of hypertension and arteriolar sclerosis, AMA Arch Ophthalmol, 49, 117, 1953.

[28]Salus, R., A contribution to the diagnosis of arteriosclerosis and hypertension,

Retinal Vascular Changes as Biomarkers of Systemic Cardiovascular Diseases 209

Am J Ophthalmol, 45, 81, 1958.

[29]Leishman, R., The eye in general vascular disease: hypertension and arteriosclerosis, Br J Ophthalmol, 41, 641, 1957.

[30]Evelyn, K.A., Nicholis, J.V., and Turnbull, W., A method of grading and recording: the retinal changes in essential hypertension, Am J Ophthalmol, 45, 165, 1958.

[31]Frant, R. and Groen, J., Prognosis of vascular hypertension; a 9 year follow-up study of 418 cases, Arch Med Interna, 85, 727, 1950.

[32]Cohen, M., Lesions of the fundus in essential hypertension and in arterial and renal diseases, Arch Ophthalmol, 17, 99401007, 1937.

[33]Gillum, R.F., Retinal arteriolar findings and coronary heart disease, Am Heart J, 122, 262, 1991.

[34]Nakayama, T., Date, C., Yokoyama, T., et al., A 15.5-year follow-up study of stroke in a Japanese provincial city. The Shibata Study, Stroke, 28, 45, 1997.

[35]Ralph, R.A., Prediction of cardiovascular status from arteriovenous crossing phenomena, Ann Ophthalmol, 6, 323, 1974.

[36]Kagan, A., Aureli, E., and Dobree, J., A note on signs in the fundus oculi and arterial hypertension: conventional assessment and significance, Bull World Health Organ, 34, 955, 1966.

[37]Dimmitt, S.B., West, J.N., Eames, S.M., et al., Usefulness of ophthalmoscopy in mild to moderate hypertension, Lancet, 1, 1103, 1989.

[38]Aoki, N., Horibe, H., Ohno, Y., et al., Epidemiological evaluation of funduscopic findings in cerebrovascular diseases. III. Observer variability and reproducibility for funduscopic findings, Jpn Circ J, 41, 11, 1977.

[39]Klein, R., Klein, B.E., Moss, S.E., et al., Blood pressure, hypertension and retinopathy in a population, Trans Am Ophthalmol Soc, 91, 207, 1993, discussion 222-6.

[40]Klein, R., Klein, B.E., Moss, S.E., et al., Hypertension and retinopathy, arteriolar narrowing, and arteriovenous nicking in a population, Arch Ophthalmol, 112, 92, 1994.

[41]Klein, R., Klein, B.E., and Moss, S.E., The relation of systemic hypertension to changes in the retinal vasculature: the Beaver Dam Eye Study, Trans Am Ophthalmol Soc, 95, 329, 1997, discussion 348-50.

[42]Klein, R., Retinopathy in a population-based study, Trans Am Ophthalmol Soc, 90, 561, 1992.

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

[44]Wong, T.Y. and Mitchell, P., Hypertensive retinopathy, N Engl J Med, 351, 2310, 2004.

[45]Walsh, J.B., Hypertensive retinopathy. description, classification, and prognosis, Ophthalmology, 89, 1127, 1982.

[46]Schubert, H.D., Ocular manifestations of systemic hypertension, Curr Opin Ophthalmol, 9, 69, 1998.

[47]Dodson, P.M., Lip, G.Y., Eames, S.M., et al., Hypertensive retinopathy: a review of existing classification systems and a suggestion for a simplified grading system, J Hum Hypertens, 10, 93, 1996.

[48]Patton, N., Aslam, T.M., MacGillivray, T., et al., Retinal image analysis: concepts, applications and potential, Prog Retin Eye Res, 25, 99, 2006.

[49]Hubbard, L.D., Brothers, R.J., King, W.N., et al., Methods for evaluation of retinal microvascular abnormalities associated with hypertension/sclerosis in the Atherosclerosis Risk in Communities Study, Ophthalmology, 106, 2269, 1999.

[50]Couper, D.J., Klein, R., Hubbard, L.D., et al., Reliability of retinal photography in the assessment of retinal microvascular characteristics: the Atherosclerosis Risk in Communities Study, Am J Ophthalmol, 133, 78, 2002.

[51]Sherry, L.M., Wang, J.J., Rochtchina, E., et al., Reliability of computerassisted retinal vessel measurementin a population, Clin Experiment Ophthalmol, 30, 179, 2002.

[52]Li, H., Hsu, W., Lee, M.L., et al., Automatic grading of retinal vessel caliber,

IEEE Trans Biomed Eng, 52, 1352, 2005.

[53]Wong, T.Y., Knudtson, M.D., Klein, R., et al., Computer-assisted measurement of retinal vessel diameters in the Beaver Dam Eye Study: methodology, correlation between eyes, and effect of refractive errors, Ophthalmology, 111, 1183, 2004.

[54]Parr, J.C. and Spears, G.F., General caliber of the retinal arteries expressed as the equivalent width of the central retinal artery, Am J Ophthalmol, 77, 472, 1974.

[55]Parr, J.C. and Spears, G.F., Mathematic relationships between the width of a retinal artery and the widths of its branches, Am J Ophthalmol, 77, 478, 1974.

[56]Wong, T.Y., Islam, F.M., Klein, R., et al., Retinal vascular caliber, cardiovascular risk factors, and inflammation: the multi-ethnic study of atherosclerosis (MESA), Invest Ophthalmol Vis Sci, 47, 2341, 2006.

[57]Wong, T.Y., Klein, R., Sharrett, A.R., et al., The prevalence and risk factors of retinal microvascular abnormalities in older persons: the Cardiovascular Health Study, Ophthalmology, 110, 658, 2003.

Retinal Vascular Changes as Biomarkers of Systemic Cardiovascular Diseases 211

[58]van Leiden, H.A., Dekker, J.M., Moll, A.C., et al., Risk factors for incident retinopathy in a diabetic and nondiabetic population: the Hoorn study, Arch Ophthalmol, 121, 245, 2003.

[59]Lowell, J., Hunter, A., Steel, D., et al., Measurement of retinal vessel widths from fundus images based on 2-D modeling, IEEE Trans Med Imaging, 23, 1196, 2004.

[60]Knudtson, M.D., Lee, K.E., Hubbard, L.D., et al., Revised formulas for summarizing retinal vessel diameters, Curr Eye Res, 27, 143, 2003.

[61]Patton, N., Aslam, T., Macgillivray, T., et al., Asymmetry of retinal arteriolar branch widths at junctions affects ability of formulae to predict trunk arteriolar widths, Invest Ophthalmol Vis Sci, 47, 1329, 2006.

[62]Wong, T.Y., Wang, J.J., Rochtchina, E., et al., Does refractive error influence the association of blood pressure and retinal vessel diameters? The Blue Mountains Eye Study, Am J Ophthalmol, 137, 1050, 2004.

[63]Rudnicka, A.R., Burk, R.O., Edgar, D.F., et al., Magnification characteristics of fundus imaging systems, Ophthalmology, 105, 2186, 1998.

[64]Liew, G., Mitchell, P., Wang, J.J., et al., Effect of axial length on retinal vascular network geometry, Am J Ophthalmol, 141, 597, 2006, author reply 597-8.

[65]Cheung, N. and Wong, T.Y., The retinal arteriole to venule ratio: informative or deceptive? Graefe’s Clinical and Experimental Ophthalmology, 2007, forthcoming.

[66]Liew, G., Sharrett, A.R., Kronmal, R., et al., Measurements of retinal vascular caliber: issues and alternatives to using the arteriole to venule ratio, Invest Ophthalmol Vis Sci, 48, 52, 2007.

[67]Liew, G., Wong, T.Y., Mitchell, P., et al., Are narrower or wider retinal venules associated with incident hypertension? Hypertension, 48, e10, 2006, author reply e11.

[68]Ikram, M.K., de Jong, F.J., Vingerling, J.R., et al., Are retinal arteriolar or venular diameters associated with markers for cardiovascular disorders? The Rotterdam Study, Invest Ophthalmol Vis Sci, 45, 2129, 2004.

[69]Ikram, M.K., Witteman, J.C., Vingerling, J.R., et al., Response to are narrower or wider retinal venules associated with incident hypertension? Hypertension, 2006.

[70]Cheung, N., Islam, F.M., Saw, S.M., et al., Distribution and associations of retinal vascular caliber with ethnicity, gender and birth parameters in young children, Invest Ophthalmol Vis Sci, 48, 1018, 2007.

[71]Sharrett, A.R., Hubbard, L.D., Cooper, L.S., et al., Retinal arteriolar diameters and elevated blood pressure: the Atherosclerosis Risk in Communities Study,