Resumen
Introducción: la diabetes es una enfermedad metabólica altamente prevalente en nuestro país que genera complicaciones incapacitantes tales como la retinopatía diabética y el edema macular. Al ser un problema socioeconómico de alto impacto es importante buscar un método de diagnóstico temprano que además nos permita implementar un servicio de telemedicina para población con poco acceso a servicios de salud especializados.
Objetivo: describir el rendimiento en discriminación de edema macular de un algoritmo de detección de características aplicado sobre fotografías de fondo de ojo de pacientes diabéticos.
Material y métodos: se tomó una base de datos de 266 fotografías de fondo de ojo de pacientes diabéticos y se clasificaron en edema macular o sin edema macular mediante la valoración de oftalmólogos, y se probó si el algoritmo fue capaz de determinar la presencia o no de edema macular.
Resultados: se realizaron tres pruebas en las cuales los niveles de sensibilidad, especificidad y eficiencia del algoritmo fueron incrementando conforme la cantidad de fotografías en la fase de entrenamiento aumentó, llegando a valores de especificidad de 100%, sensibilidad 84% y eficiencia 91.30%.
Conclusiones: nuestro estudio sienta las bases de un método confiable de tamizaje por su alto valor de especificidad y permite que más adelante no solo se genere una respuesta binaria en la presencia o no de edema macular si no que permita la clasificación clínica y topográfica facilitando el inicio de tratamiento.
Abstract
Background: Diabetes is a metabolic disease highly prevalent in our country that ends in disabling complications such as diabetic retinopathy and macular edema. As a high-impact socioeconomic issue, it is important to look for an early diagnostic test that also allows us to introduce a telemedicine service for the population with little access to specialized health services.
Objective: To describe the performance in discrimination of macular edema of a feature detection algorithm on retinal fundus images from diabetic patients.
Material and methods: We use a database of 266 retinal fundus images of diabetic patients and were classified in Macular Edema or Without Macular Edema by ophthalmologists’ assessment and we test if the algorithm was capable of establish the presence or not of macular edema.
Results: We made 3 tests in which the standards of sensitivity, specificity and efficiency of the algorithm were increasing according to the amount of retinal fundus images in the training phase, reaching specificity values of 100%, sensitivity 84% and efficiency 91.30%.
Conclusions: Our study lays the foundation of a reliable screening method due to its high specificity value and allows not only a binary reply in the presence or not of macular edema but the clinical and topographic classification favoring the onset of treatment.
Sun H, Saeedi P, Karuranga S, et al. IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045. Diabetes Research and Clinical Practice. 2022;183:109-119. doi: 10.1016/j.diabres.2021.109119
Pérez-Lozano DL, Camarillo-Nava VM, Juárez-Zepeda TE, et al. Costo-efectividad del tratamiento de la diabetes mellitus tipo 2 en México. Rev Med Inst Mex Seguro Soc. 2023;61(2):172-80.
Tatulashvili S, Fagherazzi G, Dow C, et al. Socioeconomic inequalities and type 2 diabetes complications: A systematic review. Diabetes Metab. 2020;46(2):89-99. doi: 10.1016/j.diabet.2019.11.001
Ahsan KZ, Iqbal A, Jamil K, et al. Socioeconomic disparities in diabetes prevalence and management among the adult population in Bangladesh. PLoS One [Internet]. 2022;17(12):1-19. doi: 10.1371/journal.pone.0279228
Browning D, Stewart M, Lee C. Diabetic macular edema: Evidence-based management. Indian J Ophthalmol. 2018;66(12):1736-1750. doi: 10.4103/ijo.IJO_1240_18
Im JHB, Jin YP, Chow R, et al. Prevalence of diabetic macular edema based on optical coherence tomography in people with diabetes: A systematic review and meta-analysis. Surv Ophthalmol. 2022;67(4):1244-1251. doi: 10.1016/j.survophthal.2022.01.009.
Gurreri A, Pazzaglia A. Diabetic Macular Edema: State of Art and Intraocular Pharmacological Approaches. Adv Exp Med Biol. 2021;1307:375-389. doi: 10.1007/5584_2020_535
Shukla UV, Tripathy K. Diabetic Retinopathy. Stat Pearls. Treasure Island (FL): StatPearls Publishing; 2023.
Nicholson L, Talks SJ, Amoaku W, et al. Retinal vein occlusion (RVO) guideline: executive summary. Eye 2022 May;36(5):909-912. doi: 10.1038/s41433-022-02007-4.
Agarwal A, Pichi F, Invernizzi A, et al. Disease of the Year: Differential Diagnosis of Uveitic Macular Edema. Ocul Immunol Inflamm. 2019;27(1):72-88. doi: 10.1080/09273948.2018.1523437.
Daruich A, Matet A, Moulin A, et al. Mechanisms of macular edema: Beyond the surface. Prog Retin Eye Res. 2018;63:20-68. doi: 10.1016/j.preteyeres.2017.10.006
Bischoff P. Makulaödem: Vom Symptom zur Diagnose [Macular edema: from symptom to diagnosis]. Klin Monbl Augenheilkd. 1999;214(5):311-316. doi: 10.1055/s-2008-1034802
Suciu CI, Suciu VI, Nicoara SD. Optical Coherence Tomography (Angiography) Biomarkers in the Assessment and Monitoring of Diabetic Macular Edema. J Diabetes Res. 2020;2020:6655021. doi: 10.1155/2020/6655021.
Nozaki M, Kato A, Yasukawa T, et al. Indocyanine green angiography-guided focal navigated laser photocoagulation for diabetic macular edema. Jpn J Ophthalmol. 2019;63(3):243-254. doi: 10.1007/s10384-019-00662-x.
Kwan CC, Fawzi AA. Imaging and Biomarkers in Diabetic Macular Edema and Diabetic Retinopathy. Curr Diab Rep. 2019;19(10):95. doi: 10.1007/s11892-019-1226-2
Jemshi KM, Gopi VP, Issac Niwas S. Development of an efficient algorithm for the detection of macular edema from optical coherence tomography images. Int J Comput Assist Radiol Surg. 2018;13(9):1369-1377. doi: 10.1007/s11548-018-1795-6.
Mintz Y, Brodie R. Introduction to artificial intelligence in medicine. Minim Invasive Ther Allied Technol. 2019;28(2):73-81. doi: 10.1080/13645706.2019.1575882.
Keskinbora K, Güven F. Artificial Intelligence and Ophthalmology. Turk J Ophthalmol. 2020;50(1):37-43. doi: 10.4274/tjo.galenos.2020.78989.
Hessen SH, Abdul-Kader HM, Khedr AE, et al. Developing Multiagent E-Learning System-Based Machine Learning and Feature Selection Techniques. Comput Intell Neurosci. 2022;2022:2941840. doi: 10.1155/2022/2941840.
Gil-Rios MA, Chalopin C, Cruz-Aceves I, et al. Automatic Classification of Coronary Stenosis Using Feature Selection and a Hybrid Evolutionary Algorithm. Axioms. 2023;12(5):462. doi: 10.3390/axioms12050462
Tessmann M, Vega-Higuera F, Fritz D, et al. Multi-scale feature extraction for learning-based classification of coronary artery stenosis. Proceedings of the Medical Imaging 2009: Computer-Aided Diagnosis; International Society for Optics and Photonics, SPIE: Orlando, FL, USA, 2009; (7260):726002. Disponible en: https://doi.org/10.1117/12.811639
Tsiknakis N, Theodoropoulos D, Manikis G, et al. Deep learning for diabetic retinopathy detection and classification based on fundus images: A review. Comput. Biol. Med. 2021;135:104599. doi: 10.1016/j.compbiomed.2021.104599
Moraru A, Costin D, Moraru R, et al. Artificial intelligence and deep learning in ophthalmology - present and future (Review). Experimental and Therapeutic Medicine. 2020;20(4):3469-3473. doi: 10.3892/etm.2020.9118
Shahriari MH, Sabbaghi H, Asadi F, et al. Artificial intelligence in screening, diagnosis, and classification of diabetic macular edema: A systematic review. Surv Ophthalmol. 2023;68(1):42-53. doi: 10.1016/j.survophthal.2022.08.004
Gulshan V, Peng L, Coram M, et al. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA. 2016;316(22):2402-2410. doi: 10.1001/jama.2016.17216
Voets M, Møllersen K, Bongo LA. Reproduction study using public data of: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. PLoS ONE 2019;14(6):e0217541. Disponible en: https://doi.org/10.1371/journal.pone.0217541
Perdomo O, Otalora S, Rodríguez F, et al. A novel machine learning model based on exudate localization to detect diabetic macular edema. Ophthalmic Medical Image Analysis International Workshop 3. 2016:137-44. Disponible en: https://doi.org/10.17077/omia.1057
Manikandan S, Raman R, Rajalakshmi R, et al. Deep learning-based detection of diabetic macular edema using optical coherence tomography and fundus images: A meta-analysis. Indian J Ophthalmol. 2023;71(5):1783-1796. doi: 10.4103/IJO.IJO_2614_22
Hwang DK, Hsu CC, Chang KJ, et al. Artificial intelligence-based decision-making for age-related macular degeneration. Theranostics. 2019;9:232-245. doi: 10.7150/thno.28447.
Prahs P, Radeck V, Mayer C, et al. OCT-based deep learning algorithm for the evaluation of treatment indication with anti-vascular endothelial growth factor medications. Graefes Arch Clin Exp Ophthalmol. 2018;256:91-98. doi: 10.1007/s00417-017-3839-y
Treder M, Lauermann JL, Eter N. Automated detection of exudative age-related macular degeneration inspectre domain optical coherence tomography using deep learning. Graefes Arch Clin Exp Ophthalmol. 2018;256:259-265. doi: 10.1007/s00417-017-3850-3
Haralick RM, Shanmugam K, Dinstein I. "Textural Features for Image Classification," in IEEE Transactions on Systems, Man, and Cybernetics, 1973;3(6):610-621. doi: 10.1109/TSMC.1973.4309314.