Treinando Rede Neural Profunda com Divisão Proporcional de Imagens para Segmentação de Estruturas da Retina
Resumo
Com o aumento da quantidade de patologias relacionadas ao olho humano, a segmentação da escavação e do disco óptico se tornaram principais objetos de estudo por parte de experimentos interligados a Deep Learning, visando um aperfeiçoamento na classificação das mesmas estruturas possibilitando uma melhor identificação. Este estudo propõe uma abordagem de segmentação da escavação e do disco óptico combinando a técnica de divisão proporcional de imagem, em relação a área de segmentação, e a arquitetura de rede U-Net com encoder da ResNet-34. A abordagem proposta apresentou resultados promissores, alcançando 96% de Dice na segmentação do disco nos datasets RIM-ONE e DRISHTI-GS e 90% e 85% de Dice na segmentação das escavação nos datasets DRISHTI-GS e RIM-ONE, respectivamente.
Referências
Afolabi, O., Nelwamondo, F., and Mabuza, G. (2019). Segmentation of optic cup and disc for diagnosis of glaucoma on retinal fundus images.
Al-Bander, B., Williams, B. M., Al-Nuaimy, W., Al-Taee, M. A., Pratt, H., and Zheng, Y. (2018). Dense fully convolutional segmentation of the optic disc and cup in colour fundus for glaucoma diagnosis. Symmetry, 10(4).
Baheti, B., Innani, S., Gajre, S. S., and Talbar, S. N. (2020). Eff-unet: A novel architecture for semantic segmentation in unstructured environment. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 1473-1481.
Bourne, R., Steinmetz, J. D., Flaxman, S., Briant, P. S., Taylor, H. R., Resnikoff, S., Casson, R. J., Abdoli, A., Abu-Gharbieh, E., Afshin, A., et al. (2021). Trends in prevalence of blindness and distance and near vision impairment over 30 years: an analysis for the global burden of disease study. The Lancet global health, 9(2):e130-e143.
Buslaev, A., Iglovikov, V. I., Khvedchenya, E., Parinov, A., Druzhinin, M., and Kalinin, A. A. (2020). Albumentations: Fast and flexible image augmentations. Information, 11(2).
Collaborators, G. and Study, V. (2021). Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to vision 2020: the right to sight: an analysis for the global burden of disease study. 9.
Fumero, F., Sigut, J., Alayón, S., and González-Hernández, González de la Rosa, M. (2015). Interactive tool and database for optic disc and cupsegmentation of stereo and monocular retinal fundus images.
Li, M., Soltanolkotabi, M., and Oymak, S. (2020). Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks. In Chiappa, S. and Calandra, R., editors, Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, volume 108 of Proceedings of Machine Learning Research, pages 4313-4324. PMLR.
Lima, A., Maia, L. B., dos Santos, P. T. C., Junior, B. J., de Almeida, J. D., and de Paiva, A. C. (2018). Evolving convolutional neural networks for glaucoma diagnosis. In Anais do XVIII Simpósio Brasileiro de Computação Aplicada à Saúde. SBC.
Lima, A. A., de Carvalho Araújo, A. C., de Moura Lima, A. C., de Sousa, J. A., de Almeida, J. D. S., de Paiva, A. C., and Júnior, B. J. (2020). Mask overlaying: a deep learning approach for individual optic cup segmentation from fundus image. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), pages 99-104. IEEE.
Moreira, J. M. M., de Almeida, J. D. S., Junior, B. J., and de Paiva, A. C. (2021). Detecção de glaucoma usando redes em cápsula. In Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde, pages 188-199. SBC.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825-2830.
Rodriguez, J. D., Perez, A., and Lozano, J. A. (2009). Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE transactions on pattern analysis and machine intelligence, 32(3):569-575.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234-241. Springer.
Sevastopolsky, A. (2017). Optic disc and cup segmentation methods for glaucoma detection with modification of u-net convolutional neural network. CoRR, abs/1704.00979.
Silva, M. G., Pessoa, A. C., de Almeida, J. D., Junior, B. J., and de Paiva, A. C. (2018). Diagnóstico do glaucoma em imagens de retinografia usando variantes de padroes locais binários. In Anais do XVIII Simpósio Brasileiro de Computação Aplicada à Saúde. SBC.
Sivaswamy, J., Krishnadas, S., Chakravarty, A., Gopal, D., Joshi, G., Ujjwal, and Syed, T. (2015). Jsm biomedical imaging data papers keywords @bullet @bullet @bullet nerve head @bullet @bullet disk a comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis. JSM Biomedical imaging data papers.
Tang, S., Qi, Z., Granley, J., and Beyeler, M. (2021). U-net with hierarchical bottleneck attention for landmark detection in fundus images of the degenerated retina. Lecture Notes in Computer Science, page 62-71.
Wu, Y., Szymanska, M., Hu, Y., Fazal, M. I., Jiang, N., Yetisen, A. K., and Cordeiro, M. F. (2022). Measures of disease activity in glaucoma. Biosensors and Bioelectronics, 196:113700.
Yu, S., Xiao, D., Frost, S., and Kanagasingam, Y. (2019). Robust optic disc and cup segmentation with deep learning for glaucoma detection. Computerized Medical Imaging and Graphics, 74:61-71.
Zilly, J., Buhmann, J. M., and Mahapatra, D. (2017). Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation. Computerized Medical Imaging and Graphics, 55:28-41. Special Issue on Ophthalmic Medical Image Analysis.
Al-Bander, B., Williams, B. M., Al-Nuaimy, W., Al-Taee, M. A., Pratt, H., and Zheng, Y. (2018). Dense fully convolutional segmentation of the optic disc and cup in colour fundus for glaucoma diagnosis. Symmetry, 10(4).
Baheti, B., Innani, S., Gajre, S. S., and Talbar, S. N. (2020). Eff-unet: A novel architecture for semantic segmentation in unstructured environment. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 1473-1481.
Bourne, R., Steinmetz, J. D., Flaxman, S., Briant, P. S., Taylor, H. R., Resnikoff, S., Casson, R. J., Abdoli, A., Abu-Gharbieh, E., Afshin, A., et al. (2021). Trends in prevalence of blindness and distance and near vision impairment over 30 years: an analysis for the global burden of disease study. The Lancet global health, 9(2):e130-e143.
Buslaev, A., Iglovikov, V. I., Khvedchenya, E., Parinov, A., Druzhinin, M., and Kalinin, A. A. (2020). Albumentations: Fast and flexible image augmentations. Information, 11(2).
Collaborators, G. and Study, V. (2021). Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to vision 2020: the right to sight: an analysis for the global burden of disease study. 9.
Fumero, F., Sigut, J., Alayón, S., and González-Hernández, González de la Rosa, M. (2015). Interactive tool and database for optic disc and cupsegmentation of stereo and monocular retinal fundus images.
Li, M., Soltanolkotabi, M., and Oymak, S. (2020). Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks. In Chiappa, S. and Calandra, R., editors, Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, volume 108 of Proceedings of Machine Learning Research, pages 4313-4324. PMLR.
Lima, A., Maia, L. B., dos Santos, P. T. C., Junior, B. J., de Almeida, J. D., and de Paiva, A. C. (2018). Evolving convolutional neural networks for glaucoma diagnosis. In Anais do XVIII Simpósio Brasileiro de Computação Aplicada à Saúde. SBC.
Lima, A. A., de Carvalho Araújo, A. C., de Moura Lima, A. C., de Sousa, J. A., de Almeida, J. D. S., de Paiva, A. C., and Júnior, B. J. (2020). Mask overlaying: a deep learning approach for individual optic cup segmentation from fundus image. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), pages 99-104. IEEE.
Moreira, J. M. M., de Almeida, J. D. S., Junior, B. J., and de Paiva, A. C. (2021). Detecção de glaucoma usando redes em cápsula. In Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde, pages 188-199. SBC.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825-2830.
Rodriguez, J. D., Perez, A., and Lozano, J. A. (2009). Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE transactions on pattern analysis and machine intelligence, 32(3):569-575.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234-241. Springer.
Sevastopolsky, A. (2017). Optic disc and cup segmentation methods for glaucoma detection with modification of u-net convolutional neural network. CoRR, abs/1704.00979.
Silva, M. G., Pessoa, A. C., de Almeida, J. D., Junior, B. J., and de Paiva, A. C. (2018). Diagnóstico do glaucoma em imagens de retinografia usando variantes de padroes locais binários. In Anais do XVIII Simpósio Brasileiro de Computação Aplicada à Saúde. SBC.
Sivaswamy, J., Krishnadas, S., Chakravarty, A., Gopal, D., Joshi, G., Ujjwal, and Syed, T. (2015). Jsm biomedical imaging data papers keywords @bullet @bullet @bullet nerve head @bullet @bullet disk a comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis. JSM Biomedical imaging data papers.
Tang, S., Qi, Z., Granley, J., and Beyeler, M. (2021). U-net with hierarchical bottleneck attention for landmark detection in fundus images of the degenerated retina. Lecture Notes in Computer Science, page 62-71.
Wu, Y., Szymanska, M., Hu, Y., Fazal, M. I., Jiang, N., Yetisen, A. K., and Cordeiro, M. F. (2022). Measures of disease activity in glaucoma. Biosensors and Bioelectronics, 196:113700.
Yu, S., Xiao, D., Frost, S., and Kanagasingam, Y. (2019). Robust optic disc and cup segmentation with deep learning for glaucoma detection. Computerized Medical Imaging and Graphics, 74:61-71.
Zilly, J., Buhmann, J. M., and Mahapatra, D. (2017). Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation. Computerized Medical Imaging and Graphics, 55:28-41. Special Issue on Ophthalmic Medical Image Analysis.
Publicado
07/06/2022
Como Citar
FONSECA, Pedro Victor de A.; ARAÚJO, Alexandre Carvalho; ALMEIDA, João Dallyson S. de; BRAZ JÚNIOR, Geraldo.
Treinando Rede Neural Profunda com Divisão Proporcional de Imagens para Segmentação de Estruturas da Retina. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 22. , 2022, Teresina.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 1-12.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2022.222421.
