Avaliação de Técnicas de Transformação de Intensidade na Detecção Automática de Retinopatia Diabética em Imagens
Resumo
Retinopatia diabética (RD) é uma complicação do diabetes. Pacientes com nı́veis altos de glicose tendem a lidar com a retinopatia. RD é uma das principais causas de cegueira na idade ativa. Quando é detectada nos estágios iniciais, alguns tratamentos podem retardar e reduzir o risco da perda visual. Oftalmologistas diagnosticam RD avaliando imagens retinoscópicas num processo oneroso. Este trabalho analisa e avalia o impacto de técnicas de transformações de intensidades (alargamento de contraste, logaritmos e potenciação) em evidenciar caracterı́sticas que distinguem imagens retinoscópicas com RD, o alargamento de contraste mostrou-se promissor obtendo ganho de 11% de acurácia e 25% de kappa em relação as imagens sem transformação.
Referências
Bland, M. (2015). An introduction to medical statistics.
Cohen, J. (1968). Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit.
Dutta, S., Manideep, B. C., Basha, S. M., Caytiles, R. D., and Iyengar, N. (2018). Classification of diabetic retinopathy images by using deep learning models. International Journal of Grid and Distributed Computing, 11(1):89–106.
Ege, B. M., Hejlesen, O. K., Larsen, O. V., Møller, K., Jennings, B., Kerr, D., and Cavan, D. A. Screening for diabetic retinopathy using computer based image analysis and statistical classification. Computer methods and programs in biomedicine.
Gargeya, R. and Leng, T. (2017). Automated identification of diabetic retinopathy using deep learning. Ophthalmology, 124(7):962–969.
Gonzalez, R. C. and Woods, R. C. (2010). Processamento digital de imagens. Pearson.
Gudla, S., Tenneti, D., Pande, M., and Tipparaju, S. M. (2018). Diabetic retinopathy: pathogenesis, treatment, and complications. In Drug delivery for the retina and posterior segment disease, pages 83–94. Springer.
Haralick, R. M., Shanmugam, K., et al. (1973). Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, (6):610–621.
Ho, T. K. (1995). Random decision forest.
Kwok, N. M., Ha, Q. P., Liu, D., and Fang, G. (2008). Contrast enhancement and intensity preservation for gray-level images using multiobjective particle swarm optimization. IEEE Transactions on Automation Science and Engineering, 6(1):145–155.
Mansour, R. F. (2018). Deep-learning-based automatic computer-aided diagnosis system for diabetic retinopathy. Biomedical engineering letters, 8(1):41–57.
Minsky, M. (1954). Theory of neural-analog reinforcement systems and its application to the brain-model problem. (9438).
Ojala, T., Pietikäinen, M., and Harwood, D. (1996). A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 29:51–59.
Peter, H, S. (2019). Diabetic retinopathy. Elsevier.
Porwal, P., Pachade, S., Kamble, R., Kokare, M., Deshmukh, G., Sahasrabuddhe, V., and Meriaudeau, F. (2018). Indian diabetic retinopathy image dataset (idrid): a database for diabetic retinopathy screening research. Data, 3(3):25.
ur Rehman, M., Abbas, Z., Khan, S. H., Ghani, S. H., et al. (2018). Diabetic retinopathy fundus image classification using discrete wavelet transform. In 2018 2nd International Conference on Engineering Innovation (ICEI), pages 75–80. IEEE.
Cohen, J. (1968). Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit.
Dutta, S., Manideep, B. C., Basha, S. M., Caytiles, R. D., and Iyengar, N. (2018). Classification of diabetic retinopathy images by using deep learning models. International Journal of Grid and Distributed Computing, 11(1):89–106.
Ege, B. M., Hejlesen, O. K., Larsen, O. V., Møller, K., Jennings, B., Kerr, D., and Cavan, D. A. Screening for diabetic retinopathy using computer based image analysis and statistical classification. Computer methods and programs in biomedicine.
Gargeya, R. and Leng, T. (2017). Automated identification of diabetic retinopathy using deep learning. Ophthalmology, 124(7):962–969.
Gonzalez, R. C. and Woods, R. C. (2010). Processamento digital de imagens. Pearson.
Gudla, S., Tenneti, D., Pande, M., and Tipparaju, S. M. (2018). Diabetic retinopathy: pathogenesis, treatment, and complications. In Drug delivery for the retina and posterior segment disease, pages 83–94. Springer.
Haralick, R. M., Shanmugam, K., et al. (1973). Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, (6):610–621.
Ho, T. K. (1995). Random decision forest.
Kwok, N. M., Ha, Q. P., Liu, D., and Fang, G. (2008). Contrast enhancement and intensity preservation for gray-level images using multiobjective particle swarm optimization. IEEE Transactions on Automation Science and Engineering, 6(1):145–155.
Mansour, R. F. (2018). Deep-learning-based automatic computer-aided diagnosis system for diabetic retinopathy. Biomedical engineering letters, 8(1):41–57.
Minsky, M. (1954). Theory of neural-analog reinforcement systems and its application to the brain-model problem. (9438).
Ojala, T., Pietikäinen, M., and Harwood, D. (1996). A comparative study of texture measures with classification based on featured distributions. Pattern recognition, 29:51–59.
Peter, H, S. (2019). Diabetic retinopathy. Elsevier.
Porwal, P., Pachade, S., Kamble, R., Kokare, M., Deshmukh, G., Sahasrabuddhe, V., and Meriaudeau, F. (2018). Indian diabetic retinopathy image dataset (idrid): a database for diabetic retinopathy screening research. Data, 3(3):25.
ur Rehman, M., Abbas, Z., Khan, S. H., Ghani, S. H., et al. (2018). Diabetic retinopathy fundus image classification using discrete wavelet transform. In 2018 2nd International Conference on Engineering Innovation (ICEI), pages 75–80. IEEE.
Publicado
26/12/2019
Como Citar
VIEIRA, Pablo; SILVA, Romuere ; LIMA, Thiago ; CARVALHO, Nonato ; GARCIA, Mateus ; CARVALHO JÚNIOR, Francisco .
Avaliação de Técnicas de Transformação de Intensidade na Detecção Automática de Retinopatia Diabética em Imagens. In: ESCOLA REGIONAL DE COMPUTAÇÃO APLICADA À SAÚDE (ERCAS), 7. , 2019, Teresina.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 318-323.
