Page 242 - Computational Retinal Image Analysis

References 239

stages and initiate treatments before the development of substantial sight-threatening
retinopathy. Currently, lesion detection and segmentation are manually performed by
ophthalmologists and retinopathy graders and screeners upon visual inspection of the
ocular fundus by means of digital fundus photography. Like in other domains, manual
annotations are prone to human ingenuous errors. This makes it desirable to be at
disposal automated systems deployable in clinical scenarios. Compared to traditional
hand-engineered systems, modern deep learning-based architectures are capable
of taking advantage of the vast amount of data available and achieving excellent
performance, comparable to humans [20]. Moreover, the long-term complications
of diabetes might affect different vascular systems of the body. An assessment of
the presence and severity of retinal microvascular abnormalities may provide a
deeper understanding of other concurrent systemic vascular disease associated with
diabetes. The retinal pathological changes may have valuable future use as a marker
of various other cerebrovascular and systemic disorders.

References
[1] R.P. Crick, P.T. Khaw, A Textbook of Clinical Ophthalmology: A Practical Guide to
Disorders of the Eyes and Their Management, World Scientific, Singapore, 2003.
[2] R.N. Frank, On the pathogenesis of diabetic retinopathy: a 1990 update, Ophthalmology
98 (5) (1991) 586–593.
[2a] R.P. Murphy, Management of diabetic retinopathy, Am. Fam. Physician 51 (4) (1995)
785–796.
[3] T.E. Rohan, C.D. Frost, N.J. Wald, Prevention of blindness by screening for diabetic
retinopathy: a quantitative assessment, Bmj 299 (6709) (1989) 1198–1201.
[4] M.O. Bachmann, S.J. Nelson, Impact of diabetic retinopathy screening on a British
district population: case detection and blindness prevention in an evidence-based model,
J. Epidemiol. Community Health 52 (1) (1998) 45–52.
[5] J.C. Javitt, L.P. Aiello, Cost-effectiveness of detecting and treating diabetic retinopathy,
Ann. Intern. Med. 124 (1 Pt 2) (1996) 164–169.
[6] E. Stefánsson, T. Bek, M. Porta, N. Larsen, J.K. Kristinsson, E. Agardh, Screening and
prevention of diabetic blindness, Acta Ophthalmol. Scand. 78 (4) (2000) 374–385.
[7] K. Facey, E. Cummins, K. Macpherson, A. Morris, L. Reay, J. Slattery, Health Technology
Assessment Report 1: Organisations of Services for Diabetic Retinopathy Screening,
Health Technology Board for Scotland, Glasgow, Scotland, 2002.
[8] B.S. Sutton, A Cost‐Effectiveness and Probabilistic Sensitivity Analysis of Opportunistic
Screening Versus Systematic Screening for Sight‐Threatening Diabetic Eye Disease
(Thesis). Saint Louis University, USA, 2003.
[9] P. Jeppesen, T. Bek, The occurrence and causes of registered blindness in diabetes
patients in Århus County, Denmark, Acta Ophthalmol. Scand. 82 (5) (2004) 526–530.
[10] E. Olafsdottir, E. Stefansson, Biennial eye screening in patients with diabetes without
retinopathy: 10-year experience, Br. J. Ophthalmol. 91 (12) (2007) 1599–1601.
[11] S.J. Aldington, E.M. Kohner, S. Meuer, R. Klein, A.K. Sjølie, Methodology for
retinal photography and assessment of diabetic retinopathy: the EURODIAB IDDM
complications study, Diabetologia 38 (4) (1995) 437–444.
[12] Early Treatment Diabetic Retinopathy Study Research Group, Grading diabetic