Detecção automática de glaucoma através de contornos ativos e características de textura.

• Danilo Oliveira UFC
• Edivan Nunes UFC
• Iális Paula UFC

Abstract

Glaucoma is one of the leading causes of blindness worldwide. This pathology has no cure and its treatment in the early stages is fundamental to avoid loss of vision. In these cases, computer systems can be used to aid diagnosis. Thus, this study aims to develop an efficient method for detecting glaucoma. The proposal uses new approaches to image preparation, active contour segmentation and extraction of Local Binary Pattern (LBP) texture features. Finally, the classification is performed, validating the methodology. The results were significant, showing better metrics to the Artificial Neural Network, with accuracy of 96.13%, sensitivity of 94.17%, specificity of 98.13%, and kappa statistic of 0.922.

References

Chan, T., Vese, L. (2001) “Active contours without edges”, IEEE Trans. Image Processing, v. 10, p. 266–277.

Coppin, Ben. (2010) “Inteligência artificial”, Rio de Janeiro: LTC.

Doucette, L. P., Rasnitsyn, A., Seifi, M., Walter, M. A. (2015 ) “The Interactions of Genes, Age, and Environment in Glaucoma Pathogenesis”. Survey of Ophthalmology, v. 60, n. 4, p. 310-326.

Faust, O., Mookiah, M. R. K. (2013) “Automated glaucoma detection using hybrid feature extraction in retinal fundus images”, Journal of Mechanics in Medicine and Biology, v. 13, n. 1.

Henriques, H. A. M. (2015) “Caraterização do fluxo sanguíneo de uma bifurcação da artéria carótida comum com estenose”, Dissertação, Universidade do Porto.

Lamani, D., Manjunath, T., Mahesh, M., Nijagunarya, Y. (2014). “Early detection of glaucoma through retinal nerve fiber layer analysis using fractal dimension and texture feature. International Journal of Research in Engineering and Technology”, v. 3, n. 10, p. 158-163.

Liu, J., Yin, F., Wong, D., Zhang, Z., Tan, N., Cheung, C., Baskaran, M., Aung, T. and Wong, T. (2011). “Automatic glaucoma diagnosis from fundus image”, Engineering in Medicine and Biology Society, EMBC, Annual International Conference of the IEEE, p. 3383–3386.

Pellucci, P. R. S., Paula, R. R. de, Silva, W. B. de O., Ladeira, A. P. (2011) “Utilização de técnicas de aprendizado de máquina no reconhecimento de entidades nomeadas no português”, E-xacta, v. 4, n. 1, p. 73-81.

Rodrigues, A. C., Silva, M. R. B. M., Schellini, A. S. (1998 ) “Número de olhos cegos por glaucoma detectados em primeira consulta num hospital universitário”. Arquivos Brasileiros de Oftalmologia, v. 61, n. 5, p. 573-578.

Rodrigues, L., T., R. (2012) “Glaucoma e sua componente genética”, Dissertação, Universidade da Beira Interior.

Sengar, N., Dutta, M. K., Burget, R., Ranjoha, M. (2017) “Automated detection of suspected glaucoma in digital fundus images”, 40th International Conference on Telecommunications and Signal Processing (TSP), p. 749-752.

WHO. (2012) “Global data on visual impairments 2010”. World Health Organization. Geneva.