Convolutional neural network and texture descriptor-based automatic detection and diagnosis of glaucoma

被引:51
作者
dos Santos Ferreira, Marcos Vinicius [1 ]
de Carvalho Filho, Antonio Oseas [1 ]
de Sousa, Alcilene Dalilia [1 ]
Silva, Aristofanes Correa [2 ]
Gattass, Marcelo [3 ]
机构
[1] Univ Fed Piaui, Rua Cicero Duarte SN,Campus Picos, BR-64600000 Picos, PI, Brazil
[2] Univ Fed Maranhao, Av Portugueses SN,Campus Bacanga, BR-65085580 Sao Luis, Ma Bacanga, Brazil
[3] Pontifical Catholic Univ Rio de Janeiro, R Sao Vicente 225, BR-22453900 Rio De Janeiro, RJ, Brazil
关键词
Medical image; Glaucoma; Convolutional neural network; Phylogenetic diversity index; CLASSIFICATION; SEGMENTATION; REGIONS;
D O I
10.1016/j.eswa.2018.06.010
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Glaucoma is an asymptomatic disease caused by damage to the optic nerve due to elevated intraocular pressure. With early diagnosis, the chances of controlling progression are greater. Glaucoma is a major global health problem as a cause of blindness, second only to cataracts. This paper presents the development of a method for the automatic detection of glaucoma in retinal images using a deep learning approach together with the exploration of texture attributes through phylogenetic diversity indexes. The methodology employed is as follows: First, image acquisition is done from the RIM-ONE, DRIONS-DB, and DRISHTI-GS databases, followed by training the convolutional neural network for optical disk segmentation. After this segmentation, it is necessary to perform removal of the blood vessels after which feature extraction is applied to the images generated from the RGB channels and the gray levels. The extracted attributes are based only on the features of texture using phylogenetic diversity indexes. Classification was performed using an approach based on the convolutional neural network. The method proved to be promising, achieving accuracy, sensitivity, and specificity of 100%. The medical expertise developed by the proposed method proved to be robust and efficient for the automatic detection task of glaucoma through retinal image analysis, using image processing and computational intelligence techniques. We thus propose a specialist system through the construction of a complete CAD tool to integrate into real clinical environments, providing a second opinion on the diagnosis of glaucoma quickly, efficiently, and at low cost. (C) 2018 Elsevier Ltd. All rights reserved.
引用
收藏
页码:250 / 263
页数:14
相关论文
共 64 条
[31]  
Devasia T, 2014, INT J ADV COMPUT SC, V5, P117
[32]  
Dosovitskiy A, 2014, ADV NEUR IN, V27
[33]   Exploring Representativeness and Informativeness for Active Learning [J].
Du, Bo ;
Wang, Zengmao ;
Zhang, Lefei ;
Zhang, Liangpei ;
Liu, Wei ;
Shen, Jialie ;
Tao, Dacheng .
IEEE TRANSACTIONS ON CYBERNETICS, 2017, 47 (01) :14-26
[34]   CONSERVATION EVALUATION AND PHYLOGENETIC DIVERSITY [J].
FAITH, DP .
BIOLOGICAL CONSERVATION, 1992, 61 (01) :1-10
[35]  
Fondon I., 2015, Computer as a Tool. EUROCON 2015. 16th IEEE International Conference on, P1
[36]  
Fumero F., 2011, PROC 24 INT S COMPUT, P1, DOI [DOI 10.1109/CBMS.2011.5999143, 10.1109/CBMS.2011.5999143]
[37]   Contextual Action Recognition with R*CNN [J].
Gkioxari, Georgia ;
Girshick, Ross ;
Malik, Jitendra .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1080-1088
[38]  
Guo Y., 2016, Proceedings of the Ophthalmic Image Analysis Workshop, P129
[39]   Phylogenetic measures of biodiversity [J].
Helmus, Matthew R. ;
Bland, Thomas J. ;
Williams, Christopher K. ;
Ives, Anthony R. .
AMERICAN NATURALIST, 2007, 169 (03) :E68-E83
[40]   Evolution - Bayesian inference of phylogeny and its impact on evolutionary biology [J].
Huelsenbeck, JP ;
Ronquist, F ;
Nielsen, R ;
Bollback, JP .
SCIENCE, 2001, 294 (5550) :2310-2314