Diagnóstico de Glaucoma Utilizando Atributos de Textura e CNN’s Pré-treinadas

Maíla Lima Claro, Rodrigo de Melo Souza Veras, André Macedo Santana, Luis Henrique Silva Vogado, Leonardo Pereira Sousa

Abstract


Glaucoma é uma doença ocular que danifica o nervo óptico causando a perda da visão. Ela é a segunda principal causa de cegueira no mundo. Vários sistemas de diagnóstico automático de glaucoma têm sido propostos, contudo é possível realizar melhorias nestas técnicas, visto que, os sistemas atuais não lidam com uma grande diversidade de imagens. Assim, este trabalho visa realizar a detecção automática do glaucoma nas imagens da retina, através do uso de descritores de textura e Redes Neurais Convolucionais (CNNs). Os resultados mostraram que a junção dos descritores GLCM e CNNs e a utilização do classificador Random Forest são promissores na detecção dessa patologia, obtendo uma acurácia de 91,06% em 873 imagens de 4 bases de dados públicas.

Keywords


medical images, glaucoma diagnosis, texture features, transfer learning

References


USMAN, M.; FRAZ, M. M.; BARMAN, S. A. Computer vision techniques applied for diagnostic analysis of retinal oct images: A review. Archives of Computational Methods in Engineering, p. 1–17, 2016.

QUIGLEY, H. A.; BROMAN, A. T. The number of people with glaucoma worldwide in 2010 and 2020. British Journal of Ophthalmology, v. 90, n. 3, p. 262–267, 2006.

MITTAPALLI, P. S.; KANDE, G. B. Segmentation of optic disk and optic cup from digital fundus images for the assessment of glaucoma. Biomedical Signal Processing and Control, v. 24, p. 34–46, 2016.

ACHARYA, U. R. et al. Automated diagnosis of glaucoma using texture and higher order spectra features. IEEE transactions on Information Technology in Biomedicine, v. 15, n. 3, p. 449–455, 2011.

SIMONTHOMAS, S.; THULASI, N.; ASHARAF, P. Automated diagnosis of glaucoma using haralick texture features. In: IEEE International Conference on Information Communication and Embedded Systems. [S.l.: s.n.], 2014. p. 1–6.

SALAM, A. A. et al. Automated detection of glaucoma using structural and non structural features. SpringerPlus, v. 5, n. 1, p. 1519–1540, 2016.

SRINIVASAN, C.; DUBEY, S.; GANESHBABU, T. Complex texture features for glaucomatous image classification system using fundus images. v. 2, n. 13, 2016.

KOTYK, T. et al. Semi-automated system for cup to disc measurement for diagnosing glaucoma using classification paradigm. In: Proceedings of the Second International Afro-European Conference for Industrial Advancement. [S.l.: s.n.], 2016. p. 653–663.

CLARO, M. et al. Automatic glaucoma detection based on optic disc segmentation and texture feature extraction. CLEI Electronic Journal, v. 19, n. 2, p. 5–5, 2016.

ORLANDO, J. I. et al. Convolutional neural network transfer for automated glaucoma identification. In: 12th International Symposium on Medical Information Processing and Analysis. [S.l.: s.n.], 2017. p. 101600U–101600U.

KRIZHEVSKY, A.; SUTSKEVER, I.; HINTON, G. E. Imagenet classification with deep convolutional neural networks. In: PEREIRA, F. et al. (Ed.). Advances in Neural Information Processing Systems 25. [S.l.: s.n.], 2012. p. 1097–1105.

JIA, Y. et al. Caffe: Convolutional architecture for fast feature embedding. In: Proceedings of the 22Nd ACM International Conference on Multimedia. New York, NY, USA: [s.n.], 2014. p. 675–678.

CHATFIELD, K. et al. Return of the devil in the details: Delving deep into convolutional nets. In: British Machine Vision Conference. [S.l.: s.n.], 2014.

OJALA,T.;PIETIKA ̈INEN,M.Unsupervisedtexture segmentation using feature distributions. In: International Conference on Image Analysis and Processing. [S.l.: s.n.], 1997. p. 311–318.

HARALICK, R. M.; SHANMUGAM, K. et al. Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, v. 3, n. 6, p. 610–621, 1973.

DALAL NAVNEET E TRIGGS, B. Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition. [S.l.: s.n.], 2005. v. 1, p. 886–893.

TAMURA, H.; MORI, S.; YAMAWAKI, T. Textural features corresponding to visual perception. IEEE Transactions on Systems, Man, and Cybernetics, v. 8, n. 6, p. 460–473, 1978.

GALLOWAY, M. M. Texture analysis using gray level run lengths. Computer Graphics and Image Processing, v. 4.

CHU, A.; SEHGAL, C. M.; GREENLEAF, J. F. Use of gray value distribution of run lengths for texture analysis. Pattern Recognition Letters, v. 11, n. 6, p. 415–419, 1990.

DASARATHY BELUR V E HOLDER, E. B. Image characterizations based on joint gray level—run length distributions. Pattern Recognition Letters, v. 12, n. 8, p. 497–502, 1991.

QUINLAN, J. R. Induction of decision trees. Machine learning, v. 1, n. 1, p. 81–106, 1986.

HALL, M. et al. The weka data mining software: an update. ACM SIGKDD explorations newsletter, v. 11, n. 1, p. 10–18, 2009.

CORTES, C.; VAPNIK, V. Support-vector networks. Machine learning, v. 20, n. 3, p. 273–297, 1995.

RUMELHART, D. E.; HINTON, G. E.; WILLIAMS, R. J. Learning internal representations by error propagation. [S.l.],1985.

BREIMAN, L. Random forests. Machine learning, v. 45, n. 1, p. 5–32, 2001.

CHIMIESKI, B. F.; FAGUNDES, R. D. R. Association and classification data mining algorithms comparison over medical datasets. Journal of health informatics, v. 5, n. 2, 2013.

POWERS, D. M. Evaluation: From Precision, Recall and F-Factor to ROC, Informedness, Markedness & Correlation, School of Informatics and Engineering, Flinders University, Adelaide, Australia. [S.l.], 2007.

ROSENFIELD, G. H.; FITZPATRICK-LINS, K. A coefficient of agreement as a measure of thematic classification accuracy. Photogrammetric engineering and remote sensing, v. 52, n. 2, p. 223–227, 1986.

LANDIS, J. R.; KOCH, G. G. The measurement of observer agreement for categorical data. Biometrics, p. 159–174, 1977.

SIVASWAMY, J. et al. Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation. In: IEEE 11th International Symposium on Biomedical Imaging. [S.l.: s.n.], 2014. p. 53–56.

FUMERO, F. et al. Rim-one: An open retinal image database for optic nerve evaluation. In: IEEE 24th International Symposium on Computer-Based Medical Systems. [S.l.: s.n.], 2011. p. 1–6.




DOI: http://dx.doi.org/10.22456/2175-2745.76387

Copyright (c) 2018 Maíla Lima Claro, Rodrigo de Melo Souza Veras, André Macedo Santana, Luis Henrique Silva Vogado, Leonardo Pereira Sousa

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.