Detection of Exudates and Microaneurysms in the Retina by Segmentation in Fundus Images

  • Eduardo Bernal Catalán Tecnológico Nacional de México / Instituto Tecnológico de Acapulco
  • Eduardo De la Cruz Gámez Tecnológico Nacional de México / Instituto Tecnológico de Acapulco
  • José Antonio Montero Valverde Tecnológico Nacional de México / Instituto Tecnológico de Acapulco
  • Rafael Hernández Reyna Tecnológico Nacional de México / Instituto Tecnológico de Acapulco
  • José Luis Hernández Hernández Tecnológico Nacional de México / Instituto Tecnológico de Chilpancingo
Keywords: Diabetic Retinopathy, Exudates, Microaneurysms, Image Processing, Segmentation

Abstract

This article proposes two methodologies for the detection of lesions in the retina, which may indicate the presence of diabetic retinopathy (DR). Through the use of digital image processing techniques, it is possible to isolate the pixels that correspond to a lesion of RD, to achieve segmenting microaneurysms, the edges of the objects contained in the image are highlighted in order to detect the contours of the objects to select by size those that meet an area of 15 to 25 pixels in the case of 512x512 images and identify the objects as possible microaneurysms, while for the detection of exudates the green channel is selected to contrast the luminous objects in the retinography and from the conversion to gray scale, a histogram is graphed to identify the ideal threshold for the segmentation of the pixels that belong to the exudates at the end of the optical disk previously identified by a specialist. A confusion matrix supervised by an ophthalmologist was created to quantify the results obtained by the two methodologies, obtaining a specificity of 0.94 and a sensitivity of 0.97, values that are outstanding to proceed with the classification stage.

References

Basto-Abreu A, Barrientos-Gutiérrez T, Rojas Martínez R, et al. Prevalencia de diabetes y descontrol glucémico en México: resultados de la Ensanut 2016. Salud Publica Mex [Internet]. 2020;62(1):50-59. Available from: https://doi.org/10.21149/10752

Martínez Rubio M, Moya Moya M, Bellot Bernabé A, et al. Cribado de retinopatía diabética y teleoftalmología. Arch Soc Esp Oftalmol [Internet]. 2012;87(12):392-395. Available from: http://dx.doi.org/10.1016/j.oftal.2012.04.004

Instituto Nacional de Salud Pública. Encuesta Nacional de Salud y Nutrición de Medio Camino 2016 [Internet]. Secretaria de Salud; 2016. Available from: https://ensanut.insp.mx/encuestas/ensanut2016/informes.php

Federación Mexicana de Diabetes A. C. Retinopatía diabética [Internet]. Federación Mexicana de Diabetes A. C; 2017. Available: http://fmdiabetes.org/retinopatia-diabetica-estadisticas/

Akram UM, Khan SA. Automated Detection of Dark and Bright Lesions in Retinal Images for Early Detection of Diabetic Retinopathy. J Med Syst [Internet]. 2012;36(5):3151–3162. Available from: https://doi.org/10.1007/s10916-011-9802-2

Harangi B, Hajdu A. Automatic exudate detection by fusing multiple active contours and regionwise classification. Comput Biol Med [Internet]. 2014;54(1):156–171. Available from: https://doi.org/10.1016/j.compbiomed.2014.09.001

Norma RH, Janet MP, Miguel MU, et al. Detección de microaneurismas en la retina. XXXVIII Congreso Nacional de Ingeniería Biomédica. Ingeniería Biomédica. Mazatlán: SOMIB; 2015;92-95.

Martinez-Perez ME, Highes AD, Stanton, AV, et al. Retinal vascular tree morphology: A Semi-Automatic Quantification. IEEE Trans Biomed Eng [Internet]. 2002;49(8):912-917. Available from: https://doi.org/10.1109/tbme.2002.800789

Gelman R, Martínez Pérez ME, Vanderveen DK, et al. Diagnosis of Plus Disease in Retinopathy of Prematurity Using Retinal Image multiScale Analysis. Investig Ophthalmol Vis Sci [Internet]. 2005;46(12):4734-4738. Available from: https://doi.org/10.1167/iovs.05-0646

Decencière E, Zhang X, Cazuguel G, et al. FEEDBACK ON A PUBLICLY DISTRIBUTED IMAGE DATABASE: THE MESSIDOR DATABASE. Image Anal Stereol [Internet]. 2014;33(3):231-234. Available from: https://doi.org/10.5566/ias.1155

Uribe Valencia LJ. Detección automática de exudados en imágenes a color del fondo del ojo para el pre-diagnóstico de la retinopatía diabética [master's thesis]. [Tonantzintla]: Instituto Nacional de Astrofísica, Óptica y Electrónica, 2014. 99p. Spanish.

Flores Mamani O. Sistema de diagnóstico de la retinopatía diabética mediante imágenes digitales [dissertation]. [Ciudad de la Paz]: Universidad Mayor de San Andrés, 2014. 108p. Spanish.

Vivanco LMQ, Sánchez FH, Marañón DCE. Optimización de los filtros mediana-gaussiano para una mejor convergencia del snake en la segmentación de imágenes médicas. In: XV Convención y Feria Internacional Informática 2013 – I Congreso Integracionista de las Ciencias y las Tecnologías Informáticas. La Habana: Ministerio de Informática y Comunicaciones; 2013. Spanish.

Rapantzikos K, Zervakis M, Balas, K. Detection and segmentation of drusen deposits on human retina: Potential in the diagnosis of age-related macular degeneration. Med Image Anal [Internet]. 2003;7(1):95–108. Available from: https://doi.org/10.1016/s1361-8415(02)00093-2

Flores Eraña JG. Síntesis digital de color utilizando tonos de gris [master's thesis]. [San Luis Potosí]: Universidad Autónoma de San Luis Potosí, 2009. 49p. Spanish.

Sepulveda Giraldo A. Procesamiento de imágenes por medio de filtros acusto-ópticos [master's thesis]. [Pereira]: Universidad Tecnológica de Pereira, 2007. 80p.

García M, Sánchez, CI, Poza J, et al. Detection of Hard Exudates in Retinal Images Using a Radial Basis Function Classifier. Ann Biomed Eng [Internet]. 2009;37(7):1448–1463. Available from: https://doi.org/10.1007/s10439-009-9707-0

La Serna Palomino S, Román Concha UN. Técnicas de segmentación en procesamiento digital de imágenes. RISI [Internet]. 2009;6(2):9-16. Available from: https://revistasinvestigacion.unmsm.edu.pe/index.php/sistem/article/view/3299

Schwarz MW, Cowan WB, Beatty JC. An experimental comparison of RGB, YIQ, LAB, HSV, and opponent color models. ACM Trans Graph [Internet]. 1987;6(2):123–158. Available from: https://doi.org/10.1145/31336.31338

Mokrzycki WS, Tatol M. Perceptual difference in Lab Colour space as the base for object colour identification. In: Burduk R, Kurzynski M, Wozniak M, Zolnierek A (eds). Computer Recognition Systems 4 [Internet]. Berlin: Springer-Verlag Berlin Heidelberg; 2009. Available from: https://doi.org/10.13140/2.1.3650.5927

Wisaeng K, Sa-Ngiamvibool W. Exudates Detection Using Morphology Mean Shift Algorithm in Retinal Images. IEEE Access [Internet]. 2019;7:11946-11958. Available from: https://doi.org/10.1109/ACCESS.2018.2890426

Akter, M, Uddin MS, Khan MH. Morphology-Based Exudates Detection from Color Fundus Images in Diabetic Retinopathy. In 2014 International Conference on Electrical Engineering and Information & Communication Technology [Internet]. Dhaka: IEEE; 2014:1-4. Available from: https://doi.org/10.1109/ICEEICT.2014.6919124

Fleming AD, Philip S, Goatman KA, et al. Automated microaneurysm detection using local contrast normalization and local vessel detection. IEEE Trans Med Imag [Internet]. 2006;25(9):1223–1232. Available from: https://doi.org/10.1109/TMI.2006.879953

Hipwell JH, Strachan F, Olson JA, et al. Automated detection of microaneurysms in digital red-free photographs: a diabetic retinopathy screening tool. Diabet Med [Internet]. 2000;17(8):588–594. Available from: https://doi.org/10.1046/j.1464-5491.2000.00338.x

Published
2021-05-20
How to Cite
Bernal Catalán, E., De la Cruz Gámez, E., Montero Valverde, J. A., Hernández Reyna, R., & Hernández Hernández, J. L. (2021). Detection of Exudates and Microaneurysms in the Retina by Segmentation in Fundus Images. Mexican Journal of Biomedical Engineering, 42(2), 67-77. Retrieved from http://rmib.mx/index.php/rmib/article/view/1136
Section
Research Articles