Deep Learning for Glaucoma Detection: R-CNN ResNet-50 and Image Segmentation

被引:7
作者
Puchaicela-Lozano, Marlene S. [1 ]
Zhinin-Vera, Luis [2 ,3 ]
Andrade-Reyes, Ana J. [1 ]
Baque-Arteaga, Dayanna M. [1 ]
Cadena-Morejon, Carolina [2 ]
Tirado-Espin, Andres [2 ]
Ramirez-Cando, Lenin [1 ]
Almeida-Galarraga, Diego [1 ]
Cruz-Varela, Jonathan [1 ]
Villalba Meneses, Fernando [1 ]
机构
[1] Yachay Tech Univ, Sch Biol Sci & Engn, Urcuqui, Ecuador
[2] Yachay Tech Univ, Sch Math & Computat Sci, Urcuqui, Ecuador
[3] Univ Castilla La Mancha, LoUISE Res Grp, I3A, Albacete, Spain
关键词
glaucoma; convolutional neural networks; fundus images; CUP SEGMENTATION; OPTIC DISC; CLASSIFICATION; NETWORK;
D O I
10.12720/jait.14.6.1186-1197
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Glaucoma is a leading cause of irreversible blindness worldwide, affecting millions of people. Early diagnosis is essential to reduce visual loss, and various techniques are used for glaucoma detection. In this work, a hybrid method for glaucoma fundus image localization using pre-trained Region-based Convolutional Neural Networks (R-CNN) ResNet-50 and cup-to-disk area segmentation is proposed. The ACRIMA and ORIGA databases were used to evaluate the proposed approach. The results showed an average confidence of 0.879 for the ResNet-50 model, indicating it as a reliable alternative for glaucoma detection. Moreover, the cup-to-disc ratio was calculated using Gradient-color-based optic disc segmentation, coinciding with the ResNet-50 results in 80% of cases, having an average confidence score of 0.84. The approach suggested in this study can determine if glaucoma is present or not, with a final accuracy of 95% with specific criteria provided to guide the specialist for an accurate diagnosis. In summary, the proposed model provides a reliable and secure method for diagnosing glaucoma using fundus images.
引用
收藏
页码:1186 / 1197
页数:12
相关论文
共 80 条
[1]   Hair removal methods: A comparative study for dermoscopy images [J].
Abbas, Qaisar ;
Celebi, M. E. ;
Fondon Garcia, Irene .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2011, 6 (04) :395-404
[2]  
Afaq S., 2020, Int. J. Sci. Technol. Res, V9, P485
[3]  
Aguiar Salazar E. D., 2020, Information and Communication Technologies: 8th Conference, TICEC 2020. Communications in Computer and Information Science (1307), P3, DOI 10.1007/978-3-030-62833-8_1
[4]  
Ajitha S., 2020, Journal of Physics: Conference Series, V1706, DOI 10.1088/1742-6596/1706/1/012170
[5]  
AlGhamdi M., 2020, J. Comput. Sci., V16, P591
[6]   Optic Disk and Cup Segmentation Through Fuzzy Broad Learning System for Glaucoma Screening [J].
Ali, Riaz ;
Sheng, Bin ;
Li, Ping ;
Chen, Yan ;
Li, Huating ;
Yang, Po ;
Jung, Younhyun ;
Kim, Jinman ;
Chen, C. L. Philip .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2021, 17 (04) :2476-2487
[7]  
Almeida-Galarraga Diego, 2021, 2021 Second International Conference on Information Systems and Software Technologies (ICI2ST), P39, DOI 10.1109/ICI2ST51859.2021.00014
[8]   Two-Stage Mask-RCNN Approach for Detecting and Segmenting the Optic Nerve Head, Optic Disc, and Optic Cup in Fundus Images [J].
Almubarak, Haidar ;
Bazi, Yakoub ;
Alajlan, Naif .
APPLIED SCIENCES-BASEL, 2020, 10 (11)
[9]   Classification and Visualisation of Normal and Abnormal Radiographs; A Comparison between Eleven Convolutional Neural Network Architectures [J].
Ananda, Ananda ;
Ngan, Kwun Ho ;
Karabag, Cefa ;
Ter-Sarkisov, Aram ;
Alonso, Eduardo ;
Reyes-Aldasoro, Constantino Carlos .
SENSORS, 2021, 21 (16)
[10]  
[Anonymous], 2014, Int. J. Innov. Res. Comput. Commun. Eng.