Detecção Automática de Doenças Oculares em Imagens de Tomografia de Coerência Óptica

• Caio H. R. Carvalho UFPI / IFBaiano
• Antônio M. S. Pinheiro UFPI
• Rodrigo M. S. Veras UFPI
• Romuere R. V. Silva UFPI

DOI: https://doi.org/10.5753/sbcas.2023.230144

Abstract

Eye diseases are problems caused by different reasons that often lead to blindness. Optical Coherence Tomography (OCT) is a non-invasive test that evaluates possible changes in the retina. This work uses Computer Vision techniques to develop classification models (binary and multiclass) of ocular anomalies on an OCT image dataset. Binary classification results reach accuracy between 97-100% and kappa 93-100%. Multiclass experiments achieved 91-92% accuracy and kappa between 86-90%. The models included in this study showed promise in classifying diseases on OCT images.

References

Alam, U., Asghar, O., Azmi, S., and Malik, R. A. (2014). Chapter 15 general aspects of diabetes mellitus. In Zochodne, D. W. and Malik, R. A., editors, Diabetes and the Nervous System, volume 126 of Handbook of Clinical Neurology, pages 211–222. Elsevier.

Chollet, F. (2016). Deep learning with separable convolutions. arXiv Prepr. arXiv1610, 2357.

Gholami, P., Roy, P., Parthasarathy, M. K., and Lakshminarayanan, V. (2020). Octid: Optical coherence tomography image database. Computers & Electrical Engineering, 81:106532.

Gholami, Peyman (2018). Developing algorithms for the analysis of retinal optical coherence tomography images. Master’s thesis.

Gonzalez, R. C. and Woods, R. E. (2002). Digital image processing. upper saddle river. J.: Prentice Hall.

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT press.

Grimm, K. J., Mazza, G. L., and Davoudzadeh, P. (2017). Model selection in finite mixture models: A k-fold cross-validation approach. Structural Equation Modeling: A Multidisciplinary Journal, 24(2):246–256.

Hassan, S. A. E., Akbar, S., Gull, S., Rehman, A., and Alaska, H. (2021). Deep learning-based automatic detection of central serous retinopathy using optical coherence tomographic images. In 2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA), pages 206–211. IEEE.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Identity mappings in deep residual networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, pages 630–645. Springer.

Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.

Kingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2017). Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90.

Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv preprint arXiv:1312.4400.

Mishra, S. S., Mandal, B., and Puhan, N. B. (2022). Macularnet: towards fully automated attention-based deep cnn for macular disease classification. SN Computer Science, 3(2):142.

Oliveira, C. M., Cristovao, L. M., Ribeiro, M. L., and Abreu, J. R. F. (2011). Improved automated screening of diabetic retinopathy. Ophthalmologica, 226(4):191–197.

Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115:211–252.

Santos, L. R. (2020). Identificação da retinopatia diabética por aprendizado de máquina.

Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI conference on artificial intelligence, volume 31.

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826.

Tanaka, S., Inoue, M., Inoue, T., Yamakawa, T., Uchio, E., Grewal, D. S., Mahmoud, T. H., and Kadonosono, K. (2020). Autologous retinal transplantation as a primary treatment for large chronic macular holes. Retina, 40(10):1938–1945.

Taylor, L. and Nitschke, G. (2018). Improving deep learning with generic data augmentation. In 2018 IEEE symposium series on computational intelligence (SSCI), pages 1542–1547. IEEE.

Thomas, A., Harikrishnan, P., Krishna, A. K., Palanisamy, P., and Gopi, V. P. (2021). A novel multiscale convolutional neural network based age-related macular degeneration detection using oct images. Biomedical Signal Processing and Control, 67:102538.

Tufail, A., Rudisill, C., Egan, C., Kapetanakis, V. V., Salas-Vega, S., Owen, C. G., Lee, A., Louw, V., Anderson, J., Liew, G., et al. (2017). Automated diabetic retinopathy image assessment software: diagnostic accuracy and cost-effectiveness compared with human graders. Ophthalmology, 124(3):343–351.

Vos, T., Barber, R. M., Bell, B., Bertozzi-Villa, A., Biryukov, S., Bolliger, I., Charlson, F., Davis, A., Degenhardt, L., Dicker, D., et al. (2015). Global, regional, and national incidence, prevalence, and years lived with disability for 301 acute and chronic diseases and injuries in 188 countries, 1990–2013: a systematic analysis for the global burden of disease study 2013. The lancet, 386(9995):743–800.

Zoph, B., Vasudevan, V., Shlens, J., and Le, Q. V. (2018). Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8697–8710.