A Multi-dataset Approach for DME Risk Detection in Eye Fundus Images

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12132)


Diabetic macular edema is a leading cause of visual loss for patients with diabetes. While diagnosis can only be performed by optical coherence tomography, diabetic macular edema risk assessment is often performed in eye fundus images in screening scenarios through the detection of hard exudates. Such screening scenarios are often associated with large amounts of data, high costs and high burden on specialists, motivating then the development of methodologies for automatic diabetic macular edema risk prediction. Nevertheless, significant dataset domain bias, due to different acquisition equipment, protocols and/or different populations can have significantly detrimental impact on the performance of automatic methods when transitioning to a new dataset, center or scenario. As such, in this study, a method based on residual neural networks is proposed for the classification of diabetic macular edema risk. This method is then validated across multiple public datasets, simulating the deployment in a multi-center setting and thereby studying the method’s generalization capability and existing dataset domain bias. Furthermore, the method is tested on a private dataset which more closely represents a realistic screening scenario. An average area under the curve across all public datasets of 0.891 ± 0.013 was obtained with a ResNet50 architecture trained on a limited amount of images from a single public dataset (IDRiD). It is also shown that screening scenarios are significantly more challenging and that training across multiple datasets leads to an improvement of performance (area under the curve of 0.911 ± 0.009).


Diabetic macular edema Eye fundus Screening Classification 



This work is financed by the ERDF - European Regional Development Fund through the Operational Programme for Competitiveness and Internationalisation - COMPETE 2020 Programme and by National Funds through the FCT Fundação para a Ciência e a Tecnologia within project CMUP-ERI/TIC/0028/2014.

The Messidor database was kindly provided by the Messidor program partners (see


  1. 1.
    Abbasi-Sureshjani, S., Dashtbozorg, B., ter Haar Romeny, B.M., Fleuret, F.: Boosted exudate segmentation in retinal images using residual nets. In: Cardoso, M., et al. (eds.) Fetal, Infant and Ophthalmic Medical Image Analysis. Lecture Notes in Computer Science, vol. 10554, pp. 210–218. Springer, Cham (2017). Scholar
  2. 2.
    Acharya, U.R., Mookiah, M.R.K., Koh, J.E., Tan, J.H., Bhandary, S.V., Rao, A.K., et al.: Automated diabetic macular edema (DME) grading system using DWT, DCT features and maculopathy index. Comput. Biol. Med. 84, 59–68 (2017)CrossRefGoogle Scholar
  3. 3.
    Akram, M.U., Tariq, A., Khan, S.A., Javed, M.Y.: Automated detection of exudates and macula for grading of diabetic macular edema. Comput. Methods Programs Biomed. 114(2), 141–152 (2014)CrossRefGoogle Scholar
  4. 4.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Cham (2006). Scholar
  5. 5.
    Bradley, A.P.: The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn. 30(7), 1145–1159 (1997)CrossRefGoogle Scholar
  6. 6.
    Bresnick, G.H., Mukamel, D.B., Dickinson, J.C., Cole, D.R.: A screening approach to the surveillance of patients with diabetes for the presence of vision-threatening retinopathy. Ophthalmology 107(1), 19–24 (2000)CrossRefGoogle Scholar
  7. 7.
    Decencière, E., Cazuguel, G., Zhang, X., Thibault, G., Klein, J.C., Meyer, F., et al.: TeleOphta: machine learning and image processing methods for teleophthalmology. Irbm 34(2), 196–203 (2013)CrossRefGoogle Scholar
  8. 8.
    Decencière, E., Zhang, X., Cazuguel, G., Lay, B., Cochener, B., Trone, C., et al.: Feedback on a publicly distributed image database: the Messidor database. Image Anal. Stereol. 33(3), 231–234 (2014)CrossRefGoogle Scholar
  9. 9.
    Giancardo, L., Meriaudeau, F., Karnowski, T.P., Li, Y., Garg, S., Tobin Jr., K.W., et al.: Exudate-based diabetic macular edema detection in fundus images using publicly available datasets. Med. Image Anal. 16(1), 216–226 (2012)CrossRefGoogle Scholar
  10. 10.
    Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: 14th International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)Google Scholar
  11. 11.
    Harangi, B., Hajdu, A.: Automatic exudate detection by fusing multiple active contours and regionwise classification. Comput. Biol. Med. 54, 156–171 (2014) CrossRefGoogle Scholar
  12. 12.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  13. 13.
    Hoover, A.: Structured Analysis of the Retina.
  14. 14.
    Imani, E., Pourreza, H.R.: A novel method for retinal exudate segmentation using signal separation algorithm. Comput. Methods Programs Biomed. 133, 195–205 (2016)CrossRefGoogle Scholar
  15. 15.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  16. 16.
    Kälviäinen, R., Uusitalo, H.: DIARETDB1 diabetic retinopathy database and evaluation protocol. In: Medical Image Understanding and Analysis, vol. 2007, p. 61. Citeseer (2007)Google Scholar
  17. 17.
    Kauppi, T., Kalesnykiene, V., Kamarainen, J.K., Lensu, L., Sorri, I., Uusitalo, H., et al.: DIARETDB0: evaluation database and methodology for diabetic retinopathy algorithms. Mach. Vis. Pattern Recogn. Res. Group Lappeenranta Univ. Technol. Finl. 73, 1–17 (2006)Google Scholar
  18. 18.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  19. 19.
    Lam, C., Yu, C., Huang, L., Rubin, D.: Retinal lesion detection with deep learning using image patches. Investig. Ophthalmol. Vis. Sci. 59(1), 590–596 (2018)CrossRefGoogle Scholar
  20. 20.
    Lim, S., Zaki, W.M.D.W., Hussain, A., Lim, S., Kusalavan, S.: Automatic classification of diabetic macular edema in digital fundus images. In: 2011 IEEE Colloquium on Humanities, Science and Engineering, pp. 265–269. IEEE (2011)Google Scholar
  21. 21.
    Liu, Q., Zou, B., Chen, J., Ke, W., Yue, K., Chen, Z., et al.: A location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images. Comput. Med. Imaging Graph. 55, 78–86 (2017)CrossRefGoogle Scholar
  22. 22.
    Long, S., Huang, X., Chen, Z., Pardhan, S., Zheng, D.: Automatic detection of hard exudates in color retinal images using dynamic threshold and SVM classification: algorithm development and evaluation. BioMed Res. Int. 2019, 13 (2019)CrossRefGoogle Scholar
  23. 23.
    Medeiros, M.D., Mesquita, E., Papoila, A.L., Genro, V., Raposo, J.F.: First diabetic retinopathy prevalence study in Portugal: RETINODIAB study - evaluation of the screening programme for Lisbon and Tagus Valley region. Br. J. Ophthalmol. 99(10), 1328–1333 (2015)CrossRefGoogle Scholar
  24. 24.
    Mo, J., Zhang, L., Feng, Y.: Exudate-based diabetic macular edema recognition in retinal images using cascaded deep residual networks. Neurocomputing 290, 161–171 (2018)CrossRefGoogle Scholar
  25. 25.
    Pires, R., Jelinek, H.F., Wainer, J., Valle, E., Rocha, A.: Advancing bag-of-visual-words representations for lesion classification in retinal images. PloS One 9(6), e96814 (2014)CrossRefGoogle Scholar
  26. 26.
    Porwal, P., Pachade, S., Kamble, R., Kokare, M., Deshmukh, G., Sahasrabuddhe, V., et al.: Indian diabetic retinopathy image dataset (IDRiD). IEEE Dataport (2018)Google Scholar
  27. 27.
    Porwal, P., Pachade, S., Kamble, R., Kokare, M., Deshmukh, G., Sahasrabuddhe, V., et al.: Indian diabetic retinopathy image dataset (IDRiD): a database for diabetic retinopathy screening research. Data 3(3), 25 (2018)CrossRefGoogle Scholar
  28. 28.
    Porwal, P., Pachade, S., Kokare, M., Deshmukh, G., Son, J., Bae, W., et al.: IDRiD: diabetic retinopathy-segmentation and grading challenge. Med. Image Anal. 59, 101561 (2020)CrossRefGoogle Scholar
  29. 29.
    Prentašić, P., Lončarić, S., Vatavuk, Z., Benčić, G., Subašić, M., Petković, T., et al.: Diabetic retinopathy image database (DRiDB): a new database for diabetic retinopathy screening programs research. In: 2013 8th International Symposium on Image and Signal Processing and Analysis (ISPA), pp. 711–716. IEEE (2013)Google Scholar
  30. 30.
    Rahim, S.S., Palade, V., Almakky, I., Holzinger, A.: Detection of diabetic retinopathy and maculopathy in eye fundus images using deep learning and image augmentation. In: Holzinger, A., Kieseberg, P., Tjoa, A.M., Weippl, E. (eds.) CD-MAKE 2019. LNCS, vol. 11713, pp. 114–127. Springer, Cham (2019). Scholar
  31. 31.
    Rekhi, R.S., Issac, A., Dutta, M.K., Travieso, C.M.: Automated classification of exudates from digital fundus images. In: 2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI), pp. 1–6. IEEE (2017)Google Scholar
  32. 32.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). Scholar
  33. 33.
    Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: Green AI. arXiv preprint arXiv:1907.10597 (2019)
  34. 34.
    Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: IEEE International Conference on Computer Vision, pp. 618–626 (2017)Google Scholar
  35. 35.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res/ 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  36. 36.
    Tariq, A., Akram, M.U., Shaukat, A., Khan, S.A.: Automated detection and grading of diabetic maculopathy in digital retinal images. J. Digit. Imaging 26(4), 803–812 (2013)CrossRefGoogle Scholar
  37. 37.
    Wanderley, D.S., Araújo, T., Carvalho, C.B., Maia, C., Penas, S., Carneiro, Â., et al.: Analysis of the performance of specialists and an automatic algorithm in retinal image quality assessment. In: 2019 IEEE 6th Portuguese Meeting on Bioengineering (ENBENG), pp. 1–4. IEEE (2019)Google Scholar
  38. 38.
    Zander, E., Herfurth, S., Bohl, B., Heinke, P., Herrmann, U., Kohnert, K.D., et al.: Maculopathy in patients with diabetes mellitus type 1 and type 2: associations with risk factors. Br. J. Ophthalmol. 84(8), 871–876 (2000)CrossRefGoogle Scholar
  39. 39.
    Zhang, X., Thibault, G., Decencière, E., Marcotegui, B., Laÿ, B., Danno, R., et al.: Exudate detection in color retinal images for mass screening of diabetic retinopathy. Med. Image Anal. 18(7), 1026–1043 (2014)CrossRefGoogle Scholar
  40. 40.
    Zhang, Y., Wu, H., Liu, H., Tong, L., Wang, M.D.: Improve model generalization and robustness to dataset bias with bias-regularized learning and domain-guided augmentation. arXiv preprint arXiv:1910.06745 (2019)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Institute for Systems and Computer Engineering, Technology and Science (INESC TEC)PortoPortugal
  2. 2.Centro Hospitalar Universitário São João (CHUSJ)PortoPortugal
  3. 3.Faculdade de Medicina da Universidade do Porto (FMUP)PortoPortugal
  4. 4.Hospital de BragaBragaPortugal
  5. 5.Faculdade de Engenharia da Universidade do Porto (FEUP)PortoPortugal

Personalised recommendations