Automated detection of proliferative retinopathy in clinical practice

Timely intervention for diabetic retinopathy (DR) lessens the possibility of blindness and can save considerable costs to health systems. To ensure that interventions are timely and effective requires methods of screening and monitoring pathological changes, including assessing outcomes. Fractal analysis, one method that has been studied for assessing DR, is potentially relevant in today’s world of telemedicine because it provides objective indices from digital images of complex patterns such as are seen in retinal vasculature, which is affected in DR. We introduce here a protocol to distinguish between nonproliferative (NPDR) and proliferative (PDR) changes in retinal vasculature using a fractal analysis method known as local connected dimension (Dconn) analysis. The major finding is that compared to other fractal analysis methods, Dconn analysis better differentiates NPDR from PDR (p = 0.05). In addition, we are the first to show that fractal analysis can be used to differentiate between NPDR and PDR using automated vessel identification. Overall, our results suggest this protocol can complement existing methods by including an automated and objective measure obtainable at a lower level of expertise that experts can then use in screening for and monitoring DR.

[1]  M. Aria Vicsek,et al.  Aggregation Models of Fractal Growth , 1997 .

[2]  Jean-Pierre Antoine,et al.  Image analysis with two-dimensional continuous wavelet transform , 1993, Signal Process..

[3]  José Pedro De La Cruz,et al.  Pharmacological approach to diabetic retinopathy. , 2004, Diabetes/metabolism research and reviews.

[4]  B. Masters,et al.  Fractal pattern formation in human retinal vessels , 1989 .

[5]  A. Daxer,et al.  Fractals and retinal vessels , 1992, The Lancet.

[6]  Richard F. Voss,et al.  Multifractals and the Local Connected Fractal Dimension: Classification of Early Chinese Landscape Paintings , 1993 .

[7]  Ralf Metzler,et al.  Bi-asymptotic fractals: Fractals between lower and upper bounds , 1998 .

[8]  Frédéric Zana,et al.  Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation , 2001, IEEE Trans. Image Process..

[9]  Barry R. Masters,et al.  Fractal analysis of human retinal vessels , 1990, Other Conferences.

[10]  Herbert F. Jelinek,et al.  Segmentation of retinal fundus vasculature in nonmydriatic camera images using wavelets: Advanced Segmentation Techniques , 2003 .

[11]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

[12]  B. Masters,et al.  Fractal analysis of the vascular tree in the human retina. , 2004, Annual review of biomedical engineering.

[13]  William M. Wells,et al.  Medical Image Computing and Computer-Assisted Intervention — MICCAI’98 , 1998, Lecture Notes in Computer Science.

[14]  H. Taylor,et al.  World blindness: a 21st century perspective , 2001, The British journal of ophthalmology.

[15]  Yuki,et al.  Clinical Ophthalmology , 2000, The British journal of ophthalmology.

[16]  S. Cross,et al.  The Applications of Fractal Geometry in Pathology , 1995 .

[17]  A. Darkins,et al.  Framework for a national teleretinal imaging program to screen for diabetic retinopathy in Veterans Health Administration patients. , 2006, Journal of rehabilitation research and development.

[18]  T F Nonnenmacher,et al.  Self-similarity and fractal irregularity in pathologic tissues. , 1996, Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc.

[19]  A. Fassina,et al.  Fractal analysis of lumbar vertebral cancellous bone architecture , 2001, Clinical anatomy.

[20]  W. B. Marks,et al.  A fractal analysis of cell images , 1989, Journal of Neuroscience Methods.

[21]  Jeffrey M. Hausdorff,et al.  Fractal dynamics in physiology: Alterations with disease and aging , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[22]  W. Raub.  From the National Institutes of Health. , 1990, JAMA.

[23]  D. Yeshurun,et al.  Patterns of cardiovascular reactivity in disease diagnosis. , 2004, QJM : monthly journal of the Association of Physicians.

[24]  T. Gardner,et al.  Minocycline reduces proinflammatory cytokine expression, microglial activation, and caspase-3 activation in a rodent model of diabetic retinopathy. , 2005, Diabetes.

[25]  A. Cavallerano,et al.  Nonmydriatic teleretinal imaging improves adherence to annual eye examinations in patients with diabetes. , 2006, Journal of rehabilitation research and development.

[26]  H. Taylor,et al.  Costs of mobile screening for diabetic retinopathy: a practical framework for rural populations. , 2001, The Australian journal of rural health.

[27]  N. Osborne,et al.  Retinal ischemia: mechanisms of damage and potential therapeutic strategies , 2004, Progress in Retinal and Eye Research.

[28]  A. Daxer.  Characterisation of the neovascularisation process in diabetic retinopathy by means of fractal geometry: diagnostic implications , 1993, Graefe's Archive for Clinical and Experimental Ophthalmology.

[29]  Xiaoyi Jiang,et al.  Adaptive Local Thresholding by Verification-Based Multithreshold Probing with Application to Vessel Detection in Retinal Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Xiaohong W. Gao,et al.  Quantification and characterisation of arteries in retinal images , 2000, Comput. Methods Programs Biomed..

[31]  L S Liebovitch,et al.  Fractal analysis of a voltage-dependent potassium channel from cultured mouse hippocampal neurons. , 1987, Biophysical journal.

[32]  Huw Jones,et al.  Applications of Fractals and Chaos , 1993, Springer Berlin Heidelberg.

[33]  Anthony J. Yezzi,et al.  Vessel Segmentation Using a Shape Driven Flow , 2004, MICCAI.

[34]  F. Ferris,et al.  How effective are treatments for diabetic retinopathy? , 1993, JAMA.

[35]  A. Daxer,et al.  The fractal geometry of proliferative diabetic retinopathy: implications for the diagnosis and the process of retinal vasculogenesis. , 1993, Current eye research.

[36]  K. Khunti,et al.  Effectiveness of screening and monitoring tests for diabetic retinopathy – a systematic review , 2000, Diabetic medicine : a journal of the British Diabetic Association.

[37]  David Cornforth,et al.  Fractop: a tool for automated biological image clas sification , 2002 .

[38]  G. Giani,et al.  Blindness Due to Diabetes: Population‐based Age‐ and Sex‐specific Incidence Rates , 1997, Diabetic medicine : a journal of the British Diabetic Association.

[39]  Christoph Hirneiss,et al.  Tele-screening for diabetic retinopathy with the retinal thickness analyzer. , 2003, Diabetes care.

[40]  Losa Ga,et al.  Self-similarity and fractal irregularity in pathologic tissues. , 1996 .

[41]  E. Weibel,et al.  Fractals in Biology and Medicine , 1994 .

[42]  Martin A Mainster,et al.  The fractal properties of retinal vessels: Embryological and clinical implications , 1990, Eye.

[43]  A. Kwok,et al.  Update on the treatment of diabetic retinopathy. , 2007, Hong Kong medical journal = Xianggang yi xue za zhi.

[44]  Q. Wang,et al.  Barriers to compliance with screening guidelines for diabetic retinopathy. , 1999, Ophthalmic epidemiology.

[45]  J. Olson,et al.  Soluble leucocyte adhesion molecules in diabetic retinopathy stimulate retinal capillary endothelial cell migration , 1997, Diabetologia.

[46]  Ronald Klein,et al.  Noncompliance with vision care guidelines in Latinos with type 2 diabetes mellitus: the Los Angeles Latino Eye Study. , 2006, Ophthalmology.

[47]  A. Miller,et al.  Update on the Treatment of Diabetic Retinopathy , 2008, TheScientificWorldJournal.

[48]  G Landini,et al.  Fractal analysis of the normal human retinal fluorescein angiogram. , 1993, Current eye research.

[49]  John I. Clark,et al.  Fractal analysis of region-based vascular change in the normal and non-proliferative diabetic retina , 2002, Current eye research.

[50]  S Gaillard,et al.  Identification of living oligodendrocyte developmental stages by fractal analysis of cell morphology , 2001, Journal of neuroscience research.

[51]  Herbert F. Jelinek,et al.  Comparison of various methods to delineate blood vessels in retinal images , 2005 .

[52]  Roberto Marcondes Cesar Junior,et al.  Blood vessels segmentation in nonmydriatic images using wavelets and statistical classifiers , 2003, 16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003).

[53]  J. Gitter,et al.  Fractal analysis of the electromyographic interference pattern , 1995, Journal of Neuroscience Methods.

[54]  H. Hastings.  Fractal geometry in biological systems: An analytical approach , 1997 .

[55]  E. Agardh,et al.  Photocoagulation of diabetic macular oedema--complications and visual outcome. , 2000, Acta ophthalmologica Scandinavica.

[56]  Toke Bek,et al.  Visual prognosis after panretinal photocoagulation for proliferative diabetic retinopathy. , 2005, Acta ophthalmologica Scandinavica.

[57]  L F Richardson,et al.  The problem of contiguity : An appendix to statistics of deadly quarrels , 1961 .

[58]  David Maberley,et al.  Screening for diabetic retinopathy in James Bay, Ontario: a cost-effectiveness analysis. , 2003, CMAJ : Canadian Medical Association journal = journal de l'Association medicale canadienne.

[59]  Robert Harris,et al.  THE NATIONAL HEALTH AND MEDICAL RESEARCH COUNCIL , 1951, The Medical journal of Australia.

[60]  Cathy R. Taylor,et al.  Improving Diabetic Retinopathy Screening Ratios Using Telemedicine-Based Digital Retinal Imaging Technology , 2007, Diabetes Care.

[61]  P. Grassberger,et al.  Measuring the Strangeness of Strange Attractors , 1983 .

[62]  Benoit B. Mandelbrot,et al.  A Fractal’s Lacunarity, and how it can be Tuned and Measured , 1994 .

[63]  J. Kanski.  Clinical Ophthalmology: A Systematic Approach , 1989 .

[64]  H F Jelinek,et al.  Use of fractal theory in neuroscience: methods, advantages, and potential problems. , 2001, Methods.

[65]  G. Landini,et al.  Local connected fractal dimensions and lacunarity analyses of 60 degrees fluorescein angiograms. , 1995, Investigative ophthalmology & visual science.

[66]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

[67]  Lewis F. Richardson,et al.  Statistics Of Deadly Quarrels , 1960 .

[68]  B. Doft,et al.  Retinopathy risk factor regression after laser panretinal photocoagulation for proliferative diabetic retinopathy. , 1984, Ophthalmology.

[69]  Herbert F. Jelinek,et al.  Vessel segmentation and tracking using a two-dimensional model , 2005 .

[70]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[71]  Francis K. H. Quek,et al.  A review of vessel extraction techniques and algorithms , 2004, CSUR.

[72]  P. Basch.  Quality of health care delivered to adults in the United States. , 2003, New England Journal of Medicine.

[73]  Roberto Marcondes Cesar Junior,et al.  Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification , 2005, IEEE Transactions on Medical Imaging.

[74]  The role of automated grading of diabetic retinopathy in a primary care screening programme , 2005 .

[75]  M. Cree,et al.  A comparison of computer based classification methods applied to the detection of microaneurysms in ophthalmic fluorescein angiograms , 1998, Comput. Biol. Medicine.

[76]  Luciano da Fontoura Costa,et al.  Shape Analysis and Classification: Theory and Practice , 2000 .