Automatic Detection of Ocular Anomalies Using Convolutional Neural Networks

• Luiza Rosa de Moura IF Sudeste MG
• Alessandra Martins Coelho IF Sudeste MG
• Matheus de Freitas Oliveira Baffa IF Sudeste MG

DOI: https://doi.org/10.5753/encompif.2021.15953

Abstract

Analyzing the importance of vision care, the proposed work aims to develop a method to aid the diagnosis of different anomalies that affect the external region of the eye. The Convolutional Neural Network was then used to detect visual patterns of the images in the Warsaw BioBase Disease Iris v2.1 database, which were later classified as sick and healthy. The built classifier was evaluated following the Holdout experimentation protocol, obtaining a 94% hit rate. With this result, it is possible to conclude that the model developed has the potential to become a tool to aid diagnosis.

Keywords: Computer Vision, Deep Learning, Ocular Diseases

References

Bhatia, K. K., Graham, M. S., Terry, L., Wood, A., Tranos, P., Trikha, S., and Jaccard, N. (2020). Disease classification of macular optical coherence tomography scansusing deep learning software: validation on independent, multicenter data. Retina,40(8):1549–1557.

Borges-Osório, M. R. and Robinson, W. M. (2013). Genética Humana 3ed. Artmed Editora.

de Almeida, R. S. (2018).Iris: Aplicativo para identificação de leucocoria. Disponível em: http://dsc.inf.furb.br/arquivos/tccs/monografias/20182rafael-sabel-de-almeidamonografia.pdf. Acesso em: 08 mar. 2021.

de Faria, S. J. et al. (1997). Doenças oculares externas. Medicina (Ribeirao Preto), 30(1):52–55.

Gama, Í., Coelho, A., and Baffa, M. (2020). Fundus eye images classification for diabetic retinopathy detection using very deep convolutional neural network. In Anais do XVI Workshop de Visão Computacional, pages 24–29. SBC.

Husemann, R., Negreiros, M., Tomaggi, H., Araujo, A. L., and Roesler, V. (2019). Desenvolvimento de uma ferramenta para auxílio ao diagnóstico de catarata em telemedicina. In Anais Estendidos do XXV Simpósio Brasileiro de Sistemas Multimídia e Web, pages 155–158. SBC.

IPMMI, H. e. M. M. K. B. (2008).Oftalmologia. Disponível em: http://www.hospitalmarieta.com.br/. Acesso em: 08 mar. 2021.

Tortora, G. J. and Derrickson, B. (2016).Corpo Humano-: Fundamentos de Anatomia e Fisiologia. Artmed Editora.

Trokielewicz, M., Czajka, A., and Maciejewicz, P. (2015). Database of iris images acquired in the presence of ocular pathologies and assessment of iris recognition reliabilityfor disease-affected eyes. In 2015 IEEE 2nd International Conference on Cybernetics (CYBCONF), pages 495–500. IEEE.

Trokielewicz, M., Czajka, A., and Maciejewicz, P. (2017). Implications of ocular pathologies for iris recognition reliability. Image and Vision Computing, 58:158–167.