Meta Aprendizagem Aplicada ao Diagnóstico de Glaucoma
Resumo
O glaucoma é uma doença silenciosa que pode levar a cegueira caso não seja tratada com urgência. Métodos de diagnóstico que utilizam inteligência computacional têm sido propostos com a finalidade de aumentar a taxa de detecções da doença ainda na sua fase inicial, e proporcionar melhor qualidade de vida aos pacientes. Porém, a descoberta de melhores técnicas e métodos de diagnóstico automatizado, é necessária grande quantidade de testes de diferentes metodologias e abordagens sobre o problema, tornando o processo lento e sujeito a erros. Este trabalho propõe uma solução através da meta aprendizagem de métodos de pré processamento, decomposição, extração de características que devem ser usados de maneira eficiente para solucionar o problema. Os resultados obtidos são promissores, atingindo 93,40\% de acurácia após 144 execuções e deve melhorar proporcionalmente à quantidade de testes realizados.
Palavras-chave:
Glaucoma, Diagnóstico, processamento de imagens
Referências
Acharya, U. R., Ng, E., Eugene, L. W. J., Noronha, K. P., Min, L. C., Nayak, K. P., and Bhandary, S. V. (2015). Decision support system for the glaucoma using gabor transformation. Biomedical Signal Processing and Control, 15(Supplement C):18 – 26.
Amadasun, M. and King, R. (1989). Textural features corresponding to textural properties. IEEE Transactions on Systems, Man, and Cybernetics, 19(5):1264–1274.
Bergstra, J., Yamins, D., and Cox, D. D. (2013a). Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms. In van derWalt, S., Millman,
J., and Huff, K., editors, Proceedings of the 12th Python in Science Conference, pages 13 – 20.
Bergstra, J., Yamins, D., and Cox, D. D. (2013b). Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms. In Proceedings of the 12th Python in science conference, pages 13–20. Citeseer.
Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.
Chen, T. and Guestrin, C. (2016). Xgboost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD ’16.
Chen, X., Xu, Y., Wong, D. W. K., Wong, T. Y., and Liu, J. (2015). Glaucoma detection based on deep convolutional neural network. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 715–718, Milan, Italy. IEEE.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1251–1258.
de Sousa, J. A., de Paiva, A. C., Sousa de Almeida, J. D., Silva, A. C., Junior, G. B., and Gattass, M. (2017). Texture based on geostatistic for glaucoma diagnosis from fundus eye image. Multimedia Tools and Applications, 76(18):19173–19190.
Faisal, A., Emam, H., A.S.M., H. B., and Hossen, S. (2011). Compound local binary pattern (clbp) for rotation invariant texture classification.
Freeman, W. T. and Roth, M. (1994). Orientation histograms for hand gesture recognition.
Technical Report TR94-03, MERL - Mitsubishi Electric Research Laboratories, Cambridge, MA 02139.
Fumero, F., Alayon, S., Sanchez, J. L., Sigut, J., and Gonzalez-Hernandez, M. (2011). RIM-ONE: An open retinal image database for optic nerve evaluation. In 2011 24th International Symposium on Computer-Based Medical Systems (CBMS), pages 1–6, Bristol, UK. IEEE.
Gonzalez, R. C. and Woods, R. E. (2010). Processamento Digital de Imagens. Pearson, 3a edition.
Haralick, R., Shanmugam, K., and Dinstein, I. (1973). Texture features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 3(6).
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Heikkil¨a, M., Pietik¨ainen, M., and Schmid, C. (2009). Description of interest regions with local binary patterns. Pattern Recognition, 42(3):425 – 436.
Hinton, G. E., Osindero, S., and Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets. Neural Comput., 18(7):1527–1554.
Huang, G., Liu, Z., Maaten, L. v. d., and Weinberger, K. Q. (2017). Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Kawde, M. M. and Bairagi, V. K. (2016). Early detection of glaucoma disease using image processing. Indian Journal of Science and Technology, 9(30).
Kim, S. J., Cho, K. J., and Oh, S. (2017). Development of machine learning models for diagnosis of glaucoma. PLOS ONE, 12(5):1–16.
Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324.
Magurran, A. (2004). Measuring Biological Diversity, volume 29.
Meyer, Y. (1993). Wavelets and Operators, volume 1 of Cambridge Studies in Advanced Mathematics. Cambridge University Press.
Nanni, L., Lumini, A., and Brahnam, S. (2010). Local binary patterns variants as texture descriptors for medical image analysis. Artificial Intelligence in Medicine, 49(2):117 – 125.
Pizer, S. M., Amburn, E. P., Austin, J. D., Cromartie, R., Geselowitz, A., Greer, T., ter Haar Romeny, B., Zimmerman, J. B., and Zuiderveld, K. (1987). Adaptive histogram equalization and its variations. Computer Vision, Graphics, and Image Processing, 39(3):355 – 368.
Ranzato, M. and Hinton, G. E. (2010). Modeling pixel means and covariances using factorized third-order boltzmann machines. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 2551–2558.
Silva, M. G., Pessoa, A. C., de Almeida, J. D., Junior, G. B., and de Paiva, A. C. (2018). Diagn´ostico do glaucoma em imagens de retinografia usando variantes de padr˜oes locais bin´arios. In 18o Simp´osio Brasileiro de Computac¸ ˜ao Aplicada `a Sa´ude (SBCAS 2018), volume 18. SBC.
Silveira, R. M., Almeida, J. D., Teixeira, J. A., Maia, I. M., Paiva, A. C., and J´unior,
G. B. (2018). Dispositivo de baixo custo para detecc¸ ˜ao de patologias da vis˜ao. In 18o Simp´osio Brasileiro de Computac¸ ˜ao Aplicada `a Sa´ude (SBCAS 2018), volume 18. SBC.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Sun, C. and Wee, W. G. (1983). Neighboring gray level dependence matrix for texture classification. Computer Vision, Graphics, and Image Processing, 23(3):341 – 352.
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2016a). Inception-v4, inceptionresnet and the impact of residual connections on learning.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016b). Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
T. Ojala, M. Pietikainen, D. H. (1996). A comparative study of texture measures with classification based on featured distribution. Pattern Recognit, 29:51–59.
Thibault, G., FERTIL, B., Navarro, C., Pereira, S., L´evy, N., SEQUEIRA, J., and MARI, J.-L. (2009). Texture indexes and gray level size zone matrix application to cell nuclei classification.
Tustison, N. and Gee, J. (2011). Run-length matrices for texture analysis. Yu, H.-F., Huang, F.-L., and Lin, C.-J. (2011). Dual coordinate descent methods for logistic regression and maximum entropy models. Machine Learning, 85(1):41–75.
Amadasun, M. and King, R. (1989). Textural features corresponding to textural properties. IEEE Transactions on Systems, Man, and Cybernetics, 19(5):1264–1274.
Bergstra, J., Yamins, D., and Cox, D. D. (2013a). Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms. In van derWalt, S., Millman,
J., and Huff, K., editors, Proceedings of the 12th Python in Science Conference, pages 13 – 20.
Bergstra, J., Yamins, D., and Cox, D. D. (2013b). Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms. In Proceedings of the 12th Python in science conference, pages 13–20. Citeseer.
Breiman, L. (2001). Random forests. Machine Learning, 45(1):5–32.
Chen, T. and Guestrin, C. (2016). Xgboost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD ’16.
Chen, X., Xu, Y., Wong, D. W. K., Wong, T. Y., and Liu, J. (2015). Glaucoma detection based on deep convolutional neural network. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 715–718, Milan, Italy. IEEE.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1251–1258.
de Sousa, J. A., de Paiva, A. C., Sousa de Almeida, J. D., Silva, A. C., Junior, G. B., and Gattass, M. (2017). Texture based on geostatistic for glaucoma diagnosis from fundus eye image. Multimedia Tools and Applications, 76(18):19173–19190.
Faisal, A., Emam, H., A.S.M., H. B., and Hossen, S. (2011). Compound local binary pattern (clbp) for rotation invariant texture classification.
Freeman, W. T. and Roth, M. (1994). Orientation histograms for hand gesture recognition.
Technical Report TR94-03, MERL - Mitsubishi Electric Research Laboratories, Cambridge, MA 02139.
Fumero, F., Alayon, S., Sanchez, J. L., Sigut, J., and Gonzalez-Hernandez, M. (2011). RIM-ONE: An open retinal image database for optic nerve evaluation. In 2011 24th International Symposium on Computer-Based Medical Systems (CBMS), pages 1–6, Bristol, UK. IEEE.
Gonzalez, R. C. and Woods, R. E. (2010). Processamento Digital de Imagens. Pearson, 3a edition.
Haralick, R., Shanmugam, K., and Dinstein, I. (1973). Texture features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 3(6).
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Heikkil¨a, M., Pietik¨ainen, M., and Schmid, C. (2009). Description of interest regions with local binary patterns. Pattern Recognition, 42(3):425 – 436.
Hinton, G. E., Osindero, S., and Teh, Y.-W. (2006). A fast learning algorithm for deep belief nets. Neural Comput., 18(7):1527–1554.
Huang, G., Liu, Z., Maaten, L. v. d., and Weinberger, K. Q. (2017). Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
Kawde, M. M. and Bairagi, V. K. (2016). Early detection of glaucoma disease using image processing. Indian Journal of Science and Technology, 9(30).
Kim, S. J., Cho, K. J., and Oh, S. (2017). Development of machine learning models for diagnosis of glaucoma. PLOS ONE, 12(5):1–16.
Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324.
Magurran, A. (2004). Measuring Biological Diversity, volume 29.
Meyer, Y. (1993). Wavelets and Operators, volume 1 of Cambridge Studies in Advanced Mathematics. Cambridge University Press.
Nanni, L., Lumini, A., and Brahnam, S. (2010). Local binary patterns variants as texture descriptors for medical image analysis. Artificial Intelligence in Medicine, 49(2):117 – 125.
Pizer, S. M., Amburn, E. P., Austin, J. D., Cromartie, R., Geselowitz, A., Greer, T., ter Haar Romeny, B., Zimmerman, J. B., and Zuiderveld, K. (1987). Adaptive histogram equalization and its variations. Computer Vision, Graphics, and Image Processing, 39(3):355 – 368.
Ranzato, M. and Hinton, G. E. (2010). Modeling pixel means and covariances using factorized third-order boltzmann machines. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 2551–2558.
Silva, M. G., Pessoa, A. C., de Almeida, J. D., Junior, G. B., and de Paiva, A. C. (2018). Diagn´ostico do glaucoma em imagens de retinografia usando variantes de padr˜oes locais bin´arios. In 18o Simp´osio Brasileiro de Computac¸ ˜ao Aplicada `a Sa´ude (SBCAS 2018), volume 18. SBC.
Silveira, R. M., Almeida, J. D., Teixeira, J. A., Maia, I. M., Paiva, A. C., and J´unior,
G. B. (2018). Dispositivo de baixo custo para detecc¸ ˜ao de patologias da vis˜ao. In 18o Simp´osio Brasileiro de Computac¸ ˜ao Aplicada `a Sa´ude (SBCAS 2018), volume 18. SBC.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Sun, C. and Wee, W. G. (1983). Neighboring gray level dependence matrix for texture classification. Computer Vision, Graphics, and Image Processing, 23(3):341 – 352.
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2016a). Inception-v4, inceptionresnet and the impact of residual connections on learning.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016b). Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
T. Ojala, M. Pietikainen, D. H. (1996). A comparative study of texture measures with classification based on featured distribution. Pattern Recognit, 29:51–59.
Thibault, G., FERTIL, B., Navarro, C., Pereira, S., L´evy, N., SEQUEIRA, J., and MARI, J.-L. (2009). Texture indexes and gray level size zone matrix application to cell nuclei classification.
Tustison, N. and Gee, J. (2011). Run-length matrices for texture analysis. Yu, H.-F., Huang, F.-L., and Lin, C.-J. (2011). Dual coordinate descent methods for logistic regression and maximum entropy models. Machine Learning, 85(1):41–75.
Publicado
25/09/2019
Como Citar
FERNANDES, Arthur Guilherme Santos; MARTINS, Caio Manfredini da Silva; BRAZ JUNIOR, Geraldo ; BOARO, José Mateus Carvalho; DE PAIVA, Lisle Faray.
Meta Aprendizagem Aplicada ao Diagnóstico de Glaucoma. In: ESCOLA REGIONAL DE COMPUTAÇÃO DO CEARÁ, MARANHÃO E PIAUÍ (ERCEMAPI), 7. , 2019, São Luís/MA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 63-70.
