Abstract
Fluorescein angiograms from diabetics were digitised for analysis using digital image-processing techniques. Computer algorithms were written to detect and count microaneurysms present in the images. The accuracy, speed and reproducibility of the technique were assessed and compared with those of manual counts made by clinicians from both digitised and analogue images. Free-response ROC (receiver operating characteristic) curves were used to assess the performance of both the clinicians and the computer by comparing the results with “gold standards” compiled from prints of the original fluorescein angiograms. The computer performed as well as the clinicians when the latter were analysing the digitised images (512 × 512 pixel resolution), but only when one image was acquired at 4 times this resolution did the computer's performance match that of the clinicians analysing the analogue image. The automated technique was more reproducible than the manual method.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Algazi VR, Keltner JL, Johnson CA (1985) Computer analysis of the optic cup in glaucoma. Invest Ophthalmol Vis Sci 26:1759–1770
Baudoin CE, Maneschi F, Quentel G, Soubrane G, Hayes T, Jones G, Coscas G, Kohner EM (1983) Quantitative evaluation of fluorescein angiograms: microaneurysm counts. Diabetes 32 [Suppl 2]:8–13
Baudoin CE, Lay BJ, Klein JC (1984) Automatic detection of microaneurysms in diabetic fluorescein angiography. Rev Epidemiol Sante Publique 32:254–261
Bunch PC, Hamilton JF, Sanderson GK, Simmons AH (1977) A free response approach to the measurement and characterisation of radiographic observers' performance. S.P.I.E. Optical Instrumentation in Medicine VI, 127:124–135
Chaudhuri S, Chatterjee S, Katz N, Nelson M, Goldbaum M (1989) Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE Trans Med Imag 8:263–269
Friberg TR, Lace J, Rosenstock J, Raskin P (1987) Retinal microaneurysm counts in diabetic retinopathy: colour photography versus fluorescein angiography. Can J Ophthalmol 22:226–229
Friberg TR, Rehkopf PG, Warnicki JW, Eller AW (1987) Use of directly acquired digital fundus and fluorescein images in the diagnosis of retinal disease. Retina 7:246–251
Goldbaum MH, Chatterjee S, Chaudhuri S, Katz N (1990) Digital image processing for ophthalmology. In: Masters BR (ed) Noninvasive diagnostic techniques in ophthalmology. Springer, New York Berlin Heidelberg, pp 548–568
Goldberg RE, Varma R, Spaeth GL, Magargal LE, Callen D (1989) Quantification of progressive diabetic macular nonperfusion. Ophthalmic Surg 20:42–45
Jagoe JR, Blauth CI, Smith PL, Arnold JV, Taylor KM, Wootton R (1989) Quantification of retinal damage during cardiopulmonary bypass. Proceedings, 3rd International Conference on Image Processing and its Applications, Warwick, UK. (IEE conference publication 307) IEE, London, pp 319–321
Jagoe JR, Blauth CI, Smith PL, Arnold JV, Taylor KM, Wootton R (1990) automatic geometrical registration of retinal angiograms. Comput Biomed Res 20:403–409
Klein R, Meuer SM, Moss SE, Klein BEK (1989) The relationship of retinal microaneurysm counts to the four-year progression of diabetic retinopathy. Arch Ophthalmol 107:1780–1785
Kohner EM, Sleightholm M, KROC Collaborative Study Group (1986) Does microaneurysm count reflect severity of early diabetic retinopathy? Ophthalmology 93:586–589
Metz CE (1986) ROC methodology in radiologic imaging. Invest Radiol 21:720–733
Peli E (1989) Electro-optic fundus imaging. Surv Ophthalmol 34:113–122
Phillips RP, Ross PGB, Tyszka M, Sharp PF, Forrester JV (1991) Detection and quantification of hyperfluorescent leakage by computer analysis of fundus fluorescein angiograms. Graefe's Arch Clin Exp Ophthalmol (in press)
Rehkopf PG, Warnicki JW (1990) Ophthalmic image processing. In: Masters BR (ed) Noninvasive diagnostic techniques in ophthalmology. Springer, New York Berlin Heidelberg, pp 1–16
Rosenfeld A, Kak AC (1982) Digital picture processing, vol 2, 2nd edn. Academic Press, London, pp 205–266
Ward NP, Tomlinson S, Taylor CJ (1989) Image analysis of fundus photographs: the detection and measurement of exudates associated with diabetic retinopathy. Ophthalmology 96:80–86
Author information
Authors and Affiliations
Additional information
A summary of this work was presented at the 31st Meeting of the Association for Eye Research, Bad Hónnef, Germany, 14–18 October, 1990. This study was supported by the Scottish Home and Health Department and the Scottish Hospitals Endowment Research Trust. The first author (T. S.) is the recipient of a Medical Research Council studentship
Offprint requests to: T. Spencer
Rights and permissions
About this article
Cite this article
Spencer, T., Phillips, R.P., Sharp, P.F. et al. Automated detection and quantification of microaneurysms in fluorescein angiograms. Graefe's Arch Clin Exp Ophthalmol 230, 36–41 (1992). https://doi.org/10.1007/BF00166760
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00166760