Detecção De Glaucoma Usando Redes Em Cápsula

• João Marcelo M. Moreira UFMA
• João Dallyson S. de Almeida UFMA
• Geraldo Braz Júnior UFMA
• Anselmo Cardoso de Paiva UFMA

DOI: https://doi.org/10.5753/sbcas.2021.16064

Abstract

Glaucoma is a disease that degrades the optic nerve causing irreversible loss of vision and whose symptoms usually appear in advanced stages. The leading resource against glaucoma is its early diagnosis, which shows the importance of computer-aided diagnostic systems, as these provide a second opinion to the specialist, helping in the correct diagnosis. Thus, this work presents a computational method for detecting glaucoma using capsule networks. The tests were performed by joining eight public databases of images from glaucoma exams, totaling 2,086 images. Our method obtained 85.29% accuracy, 81.77% sensitivity, and 88.28% specificity.

References

Acharya, U. R. et al. (2017) “Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network”, https://doi.org/10.1016/j.ins.2017.04.012.

Afshar, P. (2019) “Capsule Networks for Brain Tumor Classification Based on MRI Images and Coarse Tumor Boundaries”, ICASSP.

Anupama, A. et al. (2019) “Breast Cancer Classification using Capsule Network with Preprocessed Histology Images”, 2019 International Conference on Communication and Signal Processing (ICCSP), Chennai, Índia, https://doi.org/10.1109/ICCSP.2019.8698043.

Araújo, F. H. D. et al. (2017) “Redes Neurais Convolucionais com Tensorflow: Teoria e Prática”, III Escola Regional de Informática do Piauí. Livro Anais - Artigos e Minicursos, v. 1, n. 1, p. 382-406.

Barreto, J. M. (2002) “Introdução às Redes Neurais Artificiais”, http://www.inf.ufsc.br/~j.barreto/tutoriais/Survey.pdf.

Bergstra, J. et al. (2011) “Algorithms for Hyper-Parameter Optimization”, 25th Annual Conference on Neural Information Processing Systems (NIPS 2011), Granada, Espanha.

Bergstra, J. et al. (2015) “Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms”, https://doi.org/10.1088/1749-4699/8/1/014008.

Buades A. et al. (2011) “Non-Local Means Denoising”, http://dx.doi.org/10.5201/ipol.2011.bcm_nlm.

Claro, M. et al. (2019) “An hybrid feature space from texture information and transfer learning for glaucoma classification”, https://doi.org/10.1016/j.jvcir.2019.102597.

Ferreira, A. S. (2017) Redes Neurais Convolucionais Profundas na Detecção de Plantas Daninhas em Lavoura de Soja. Dissertação de Mestrado, Universidade Federal do Mato Grosso do Sul.

Flaxman, S. R. et al. (2017) “Global causes of blindness and distance vision impairment 1990–2020: a systematic review and meta-analysis”, The Lancet Glob Health.

Goodfellow, I. et al. (2016) Deep Learning. MIT, ISBN 9780262035613.

Haykin, S. (2001) Redes neurais: princípios e prática. Porto Alegre: Bookman.

Huang, G. et al. (2016) “Densely Connected Convolutional Networks”, arXiv:1608.06993v5.

Sabour, et al. (2017) “Dynamic Routing Between Capsules”, arXiv:1710.09829v2.

Iesmantas, T. e Alzbutas, R. (2018) “. Convolutional capsule network for classification of breast cancer histology images”, https://doi.org/10.1007/978-3-319-93000-8_97.

Keras (2020). Documentação. Disponível em: https://keras.io/.

Kurup, R. et al (2020) “Effect of Data Pre-processing on Brain Tumor Classification Using Capsulenet”, https://doi.org/10.1007/978-981-13-8461-5_13.

Lauretti, R. C. e Filho, A. L. (1997) Glaucomas. Simpósio: Oftalmologia para o clínico, 56-65.

Li, Z. et al. (2018) “Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs”, https://doi.org/10.1016/j.ophtha.2018.01.023.

Lima, A. C. M. (2019) Aprendizagem Profunda Aplicada ao Diagnóstico de Glaucoma. Dissertação de Mestrado, Universidade Federal do Maranhão.

Lopes, U. K. (2017) Redes Neurais Convolucionais Aplicadas ao Diagnóstico de Tuberculose Por Meio de Imagens Radiológicas. Dissertação de mestrado, Universidade do Vale do Rio dos Sinos.

Mobiny, A. e Nguyen, H. V. (2018) “Fast CapsNet for Lung Cancer Screening”, https://doi.org/10.1007/978-3-030-00934-2_82.

Moraes, L. A. G. (2018) Utilização de Redes em Cápsula para Classificação de Regiões Promotoras em Sequências de DNA. Dissertação de mestrado, Universidade Federal de Ouro Preto.

OpenCV (2020). Disponível em: https://opencv.org/.

Patrick, M. K. et al. (2019) “Capsule Network – A Survey”, https://doi.org/10.1016/j.jksuci.2019.09.014.

Pereira, R. M. P. (2017) Estudo do Desempenho de Redes Neurais Convolucionais Aplicada ao Reconhecimento de Símbolos Musicais, Glaucoma e Texto. Monografia, Universidade Federal do Maranhão.

Pizer, S. M. (1987) “Adaptive Histogram Equalization and its Variations. Computer Vision, Graphics and Image Processing”, vol. 39, 1987, pp. 355–368.

Raghavendra, U. et al. (2018) “Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images”, https://doi.org/10.1016/j.ins.2018.01.051.

Reis, N. C. et al. (2018) “Diagnóstico Automático de Glaucoma em Imagens de Retinografia baseado no CDR usando U-Net”, VII Jornada de Informática do Maranhão.

Ribeiro, J. L. M. (2018) “Meta-aprendizado aplicado ao Problema de Reconhecimento de Expressões Faciais”, Monografia, Universidade Federal do Maranhão.

Sanchez, A. J. (2018) “Capsule Networks against Medical Imaging Data Challenges”, arXiv:1807.07559v1.

Scikit-Image (2020). Disponível em: https://scikit-image.org/.

Shanti, R. e Prabakaran, S. (2018) “Detection of Microaneurysms and Hemorrhages in Fundus Image for Glaucoma Diagnosis” International Journal of Engineering and Technology, Vol. 7, https://doi.org /10.14419/ijet.v7i2.24.12092.

Silva, M. G. (2018) “Diagnóstico do glaucoma em retinografias usando descritores de textura”, Centro de Ciências Exatas e Tecnologia, Universidade Federal do Maranhão.

Simonyan, K. e Zisserman, A. (2014) “Very Deep Convolutional Networks For Large-Scale Image Recognition”, arXiv 1409.1556.

Tham, Y. C. et al. (2014) “Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis”, Ophthalmology, 2014, 121(11), 2081–2090. https://doi.org/10.1016/j.ophtha.2014.05.013.

World Health Organization (2019). World Report on Vision, ISBN 978-92-4-151657-0.

Zhang, K. Y. J. e Main, P. (1990) “Histogram Matching as a New Density Modification Technique for Phase Refinement and Extension of Protein Molecules”, https://doi.org/10.1107/S0108767389009311