Keywords
Redes neurales
Edema macular
Retinopatía diabética
Técnica de diagnóstico oftalmológico
Procesamiento de imagen asistida por computador Artificial intelligence
Macular edema
Neural networks
Diabetic retinopathy
Diagnostic techniques
Ophthalmological
Image processing
Computer-assisted
How to Cite
Abstract
Introduction: Diabetic Macular Edema is one of the main causes of legal blindness worldwide. The use of Artificial Networks may be helpful in the identification of Diabetic Macular Edema, particularly in developing countries, where there are huge limitations to access specialized care. Objectives: To establish the sensitivity and specificity of a diagnostic test based on an Artificial Neuronal Network for the automatic detection of Diabetic Macular Edema based on images of the posterior pole of the eye. Methodology: Cross section study of a diagnostic test based on an Artificial Neuronal Network evaluating the sensitivity and specificity of the diagnosis of the Diabetic Macular Edema in images of the posterior pole of the eye. Results: The network showed a precision of 73.5% in detecting and classifying the type of Edema, during the treatment stage. In the final stage, when comparing the network against the gold standard, the former resulted in a 61% and 69% sensitivity and specificity, respectively (positive predictive value of 63% and negative predictive value of 67%) for the detection of edema. The sensitivity was 70% and the specificity was 61% for the correct classification of the edema (positive predictive value of 64% and negative predictive value of 68%). Conclusion: The Artificial Neuronal Network showed a good performance in the detection and classification of Diabetic Macular Edema. This research is the first step towards the development of telemedicine tools to provide support and coverage for the detection of eye pathologies using eye fundus images.
References
Yau JWY, Rogers SL, Kawasaki R, Lamoureux EL, Kowalski JW, Bek T, et al. Global prevalence and major risk factors of diabetic retinopathy. Diabetes Care. 2012 Mar;35(3):556-64.
Shaw JE, Sicree RA, Zimmet PZ. Global estimates of the prevalence of diabetes for 2010 and 2030. Diabetes Res Clin Pract. 2010;87(1):4-14. https://doi.org/10.1016/j.diabres.2009.10.007
Lobo C, Pires I, Cunha-Vaz J. Diabetic Macular Edema. Opt Coherence Tomogr. 2012;32(2):1-21. https://doi.org/10.1007/978-3-642-27410-7_1
Saaddine JB, Honeycutt a a, Narayan K, Zhang X, Klein R, Boyle JP. Projection of diabetic retinopathy and other major eye diseases among people with diabetes mellitus: United states, 2005-2050. Arch Ophthalmol. 2008;126(12):1740-7. https://doi.org/10.1001/archopht.126.12.1740
Bursell SE, Cavallerano JD, Cavallerano AA, Clermont AC, Birkmire-Peters D, Aiello LP, et al. Stereo nonmydriatic digital-video color retinal imaging compared with Early Treatment Diabetic Retinopathy Study seven standard field 35-mm stereo color photos for determining level of diabetic retinopathy. Ophthalmology. 2001 Mar;108(3):572-85.
Wilkinson CP, Ferris FL, Klein RE, Lee PP, Agardh CD, Davis M, et al. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales. Ophthalmology. 2003 Sep;110(9):1677-82. https://doi.org/10.1016/S0161-6420(03)00475-5
National Library of Medicine (US). Neural Networks. MeSH Term: PubMed; 1992. p. acceso 28 de junio de 2016.
Aguirre AH. Introducción a las Redes Neuronales Artificiales. Rev Mex Ing Biomed. 2001;22(1):4-11.
Decencière et al. the Messidor database. Image Analysis & Stereology [Internet]. Feedback on a publicly distributed database. 2014. p. 231-4. https://doi.org/10.5566/ias.1155 Available from: http://www.ias-iss.org/ojs/IAS/article/view/1155
MathWorks Inc. MatLab [Internet]. 1994-2016. [cited 2015 Jun 1]. Available from: http://www.mathworks.com/academia/student_version/?s_ tid=main_sv_ML_tb
Krizhevsky A, Sutskever I, Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks. Toronto: Neural Information Processing Systems (NIPS); 2012: 1097-1105.
Paulus YM, Gariano RF. Diabetic retinopathy: a growing concern in an aging population. Geriatrics. 2009 Feb;64(2):16-20.
Acharya UR, Mookiah MRK, Koh JEW, Tan JH, Bhandary S V, Rao AK, et al. Automated screening system for retinal health using bi-dimensional empirical mode decomposition and integrated index. Comput Biol Med. 2016;(75):54-62. https://doi.org/10.1016/j.compbiomed.2016.04.015
ADCIS. Methods to evaluate segmentation and indexing techniques in the field of retinal ophthalmology (MESSIDOR) [Internet]. [cited 2015 May 20]. Available from: http://www.adcis.net/en/Contact-Us/Contact-ADCIS.html
Valverde C, Garcia M, Hornero R, Lopez-Galvez M. Automated detection of diabetic retinopathy in retinal images. Indian J Ophthalmol. 2016;64(1):26. https://doi.org/10.4103/0301-4738.178140