Image-based Glaucoma Classification Using Fundus Images and Deep Learning


  • Hiram José Sandoval-Cuellar Universidad Autónoma de Querétaro, México
  • Gendry Alfonso-Francia Universidad Autónoma de Querétaro, México
  • Miguel Ángel Vázquez-Membrillo Instituto Mexicano de Oftalmología, México
  • Juan Manuel Ramos-Arreguín Instituto Mexicano de Oftalmología, México
  • Saúl Tovar Arriaga Universidad Autónoma de Querétaro, México



Deep Learning, Glaucoma diagnosis, Image-base classification, Convolutional Neural Network


Glaucoma is an eye disease that gradually affects the optic nerve. Intravascular high pressure can be controlled to prevent total vision loss, but early glaucoma detection is crucial. The optic disc has been a notable landmark for finding abnormalities in the retina. The rapid development of computer vision techniques has made it possible to analyze eye conditions from images enabling to help a specialist to make a diagnosis using a technique that is non-invasive in its initial stage through fundus images. We propose a methodology glaucoma detection using deep learning. A convolutional neural network (CNN) is trained to extract multiple features, to classify fundus images. The accuracy, sensitivity, and the area under the curve obtained using the ORIGA database are 93.22%, 94.14%, and 93.98%. The use of the algorithm for the automatic region of interest detection in conjunction with our CNN structure considerably increases the glaucoma detecting accuracy in the ORIGA database.


Download data is not yet available.


Raghavendra U, Fujita H, Bhandary SV, Gudigar A, et al. Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Inf Sci [Internet]. 2018;441:41-49. Available from:

Belghith A, Balasubramanian M, Bowd C, Weinreb RN, et al. Glaucoma progression detection using variational expectation maximization algorithm. In: 2013 IEEE 10th International Symposium on Biomedical Imaging [Internet]. San Francisco: IEEE. 2013:876-879. Available from:

Yin F, Liu J, Wong DWJ, Tan NM, et al. Automated segmentation of optic disc and optic cup in fundus images for glaucoma diagnosis. In: 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS). Rome: IEEE. 2012:1-6. Available from:

Zilly J, Buhmann JM, Mahapatra D. Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation. Comput Med Imaging Graph [Internet]. 2017;55:28-41. Available from:

Chen X, Xu Y, Kee Wong DWK, Wong TY, et al. Glaucoma detection based on deep convolutional neural network. In: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) [Internet]. Milan: IEEE. 2015:715-718. Available from:

Acharya UR, Ng EYN, Eugene LW, Noronha KP, et al. Decision support system for the glaucoma using Gabor transformation. Biomed Signal Process Control [Internet]. 2015;15:18-26. Available from:

Díaz Pinto AY. Machine Learning for Glaucoma Assessment using Fundus Images [Ph.D.'s thesis]. [Valencia]: Universitat Politècnica de València, 2019. 117P.

Gour N, Khanna P. Automated glaucoma detection using GIST and pyramid histogram of oriented gradients (PHOG) descriptors. Pattern Recognit Lett [Internet]. 2020;137:3-11. Available from:

Nawaldgi S. Review of automated glaucoma detection techniques. In: 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET) [Internet]. Chennai: IEEE. 2016:1435-1438. Available from:

Septiarini A, Harjoko A, Pulungan R, Ekantini R. Automated Detection of Retinal Nerve Fiber Layer by Texture-Based Analysis for Glaucoma Evaluation. Healthc Inform Res [Internet]. 2018;24(4):335. Available from:

Del Portillo C. Cómo Entender y Vivir Con Glaucoma. Glaucoma Research Foundation. [Internet]. 2013; Available from:

Li A, Wang Y, Cheng J, Liu J. Combining Multiple Deep Features for Glaucoma Classification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) [Internet]. Calgary: IEEE. 2018:985-989. Available from:

Carrillo J, Bautista L, Villamizar J, Rueda J, et al. Glaucoma Detection Using Fundus Images of the Eye. In: 2019 XXII Symposium on Image, Signal Processing and Artificial Vision (STSIVA) [Internet]. Bucaramanga: IEEE. 2019:1-4. Available from:

Sarhan A, Rokne J, Alhajj R. Glaucoma detection using image processing techniques: A literature review. Comput Med Imaging Graph [Internet]. 2019;78:101657. Available from:

Li L, Xu M, Liu H, Li Y, et al. A Large-Scale Database and a CNN Model for Attention-Based Glaucoma Detection. IEEE Trans Med Imaging [Internet]. 2020;39(2):413-424. Available from:

Zhang Z, Lee BH, Liu J, Wong DWK, et al. Optic disc region of interest localization in fundus image for Glaucoma detection in ARGALI. In: 2010 5th IEEE Conference on Industrial Electronics and Applications [Internet]. Taichung: IEEE. 2010:1686-1689. Available from:

Rani A, Mittal D. Measurement of Arterio-Venous Ratio for Detection of Hypertensive Retinopathy through Digital Color Fundus Images. J Biomed Eng Med Imaging [Internet]. 2015;2(5):35. Available from:

Zhang Z, Yin FS, Liu J, Wong WK, et al. ORIGA-light: An online retinal fundus image database for glaucoma analysis and research. In: 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology [Internet]. Buenos Aires: IEEE. 2010:3065-3068. Available from:

Sng CC, Foo L-L, Cheng C-Y, Allen JC, et al. Determinants of Anterior Chamber Depth: The Singapore Chinese Eye Study. Ophthalmology [Internet]. 2012;119(6):1143-1150. Available from:

Decencière E, Zhang X, Cazuguel G, Lay B, et al. Feedback on a publicly distributed image database: the Messidor database. Image Anal Stereol [Internet]. 2014;33:231-234. Available from:

Brandon L, Hoover A. Drusen Detection in a Retinal Image Using Multi-level Analysis. In: Ellis R.E., Peters T.M. (eds). Medical Image Computing and Computer-Assisted Intervention - MICCAI 2003 [Internet]. Springer, Berlin, Heidelberg: Lecture Notes in Computer Science. 2003:618-625p. Available from:

Sivaswamy J, Krishnadas SR, Joshi GD, Jain M, et al. Drishti-GS: Retinal image dataset for optic nerve head segmentation. In: 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI) [Internet]. Beijing: IEEE. 2014:53-56. Available from:

Han J, Kamber M, Pei J. Data Mining: Concepts and Techniques [Internet]. Waltham: Elsevier. 2011:113-114p. Available from:

Bhatkalkar BJ, Reddy DR, Prabhu S, Bhandary S. Improving the Performance of Convolutional Neural Network for the Segmentation of Optic Disc in Fundus Images Using Attention Gates and Conditional Random Fields. IEEE Access [Internet]. 2020;8:29299-29310. Available from:

Gheisari S, Shariflou S, Phu J, Kennedy PJ, et al. A combined convolutional and recurrent neural network for enhanced glaucoma detection. Sci Rep [Internet]. 2021;11(1):1995. Available from:

Gómez-Valverde J, Antón A, Fatti G, Liefers B, et al. Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning. Biomed Opt Express [Internet]. 2019;10(2):892-913. Available from:

Diaz-Pinto A, Morales S, Naranjo V, Köhler T, et al. CNNs for automatic glaucoma assessment using fundus images: an extensive validation. BioMed Eng Online [Internet]. 2019;18(1):1-19. Available from:

Unión Internacional de Telecomunicaciones. Parámetros de codificación de televisión digital para estudios con formatos de imagen normal 4:3 y de pantalla ancha 16:9. ITU [Internet]. 2011; Available from: RECOMENDACIÓN UIT-R BT.601-7 - Parámetros de codificación de televisión digital para estudios con formatos de imagen normal 4:3 y de pantalla ancha 16:9 (

Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv [Internet]. 2014; Available from:

Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun [Internet]. 2017; 60(6):84-90. Available from:

Erhan D, Bengio Y, Courville AC, Vincent P. Visualizing Higher-Layer Features of a Deep Network [Internet]; 2009. Report 1341. Available from: (PDF) Visualizing Higher-Layer Features of a Deep Network (

Zeiler MD, Taylor GW, Fergus R. Adaptive deconvolutional networks for mid and high level feature learning. In: 2011 International Conference on Computer Vision [Internet]. Barcelona: IEEE. 2011:2018-2025. Available from:

Dosovitskiy A, Brox T. Inverting Visual Representations with Convolutional Networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Las Vegas: IEEE. 2016:4829-4837. Available from:

Selvaraju RR, Cogswell M, Das A, Vedantam R, et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. In: 2017 IEEE International Conference on Computer Vision (ICCV) [Internet]. Venice: IEEE. 2017:618-626. Available from:




How to Cite

Sandoval-Cuellar, H. J. ., Alfonso-Francia, G., Vázquez-Membrillo, M. Ángel, Ramos-Arreguín, J. M., & Tovar Arriaga, S. (2021). Image-based Glaucoma Classification Using Fundus Images and Deep Learning. Revista Mexicana De Ingenieria Biomedica, 42(3), 28–41.



Research Articles

Share on:

Dimensions Citation