Using Convolutional Neural Networks to Detect and Extract Retinal Blood Vessels in Fundoscopic Images

被引：4

作者：

Standfield, Benjamin ^{[1
]}

Chen, Wei-Bang ^{[1
]}

Wang, Yujuan ^{[2
]}

Lu, Yongjin ^{[3
]}

Abdelzaher, Ahmed F. ^{[1
]}

Wang, Xiaoliang ^{[4
]}

Yang, Xin-Guang ^{[5
]}

机构：

[1] Virginia State Univ, Dept Engn & Comp Sci, Petersburg, VA 23806 USA

[2] Sun Yat Sen Univ, State Key Lab Ophthalmol, Zhongshan Ophthalm Ctr, Guangzhou, Guangdong, Peoples R China

[3] Virginia State Univ, Dept Math & Econ, Petersburg, VA 23806 USA

[4] Virginia State Univ, Dept Technol, Petersburg, VA 23806 USA

[5] Henan Normal Univ, Dept Math & Informat Sci, Xinxiang, Henan, Peoples R China

来源：

2019 2ND IEEE CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2019) | 2019年

关键词：

convolutional neural networks; supervised machine learning; diabetes mellitus; diabetic retinopathy; retinal blood vessel detection; image segmentation; SEGMENTATION;

D O I：

10.1109/MIPR.2019.00047

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Diabetes mellitus (DM) is a worldwide major medical problem. Diabetic retinopathy (DR) staging is important for the estimation of DM and the evaluation of associated retinopathy. According to the international clinical diabetic retinopathy & diabetic macular edema disease severity scales, most of the dilated ophthalmoscopy observable findings are associated with retinal blood vessels. In order to objectively and accurately determine the diabetic retinopathy stages, it is essential to automatically detect and extract retinal blood vessels in fundoscopic images. This paper introduces and compares various convolutional neural networks to recognize retinal blood vessels in fundoscopic images. The experimental results demonstrate the effectiveness of the proposed approach.

引用

页码：222 / 227

页数：6

共 23 条

[1]

[Anonymous], 2015, P 3 INT C LEARN REPR

[2]

Deb D, 2012, ASIA PAC CONF ANTEN, P17, DOI 10.1109/APCAP.2012.6333126

[3]

Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848

[4] Blood vessel segmentation methodologies in retinal images - A survey [J].

Fraz, M. M. ;

Remagnino, P. ;

Hoppe, A. ;

Uyyanonvara, B. ;

Rudnicka, A. R. ;

Owen, C. G. ;

Barman, S. A. .

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2012, 108 (01) :407-433

[5] ImageNet Classification with Deep Convolutional Neural Networks [J].

Krizhevsky, Alex ;

Sutskever, Ilya ;

Hinton, Geoffrey E. .

COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90

[6] Impact of current and past blood pressure on retinal arteriolar diameter in an older population [J].

Leung, H ;

Wang, JJ ;

Rochtchina, E ;

Wong, TY ;

Klein, R ;

Mitchell, P .

JOURNAL OF HYPERTENSION, 2004, 22 (08) :1543-1549

[7] Segmenting Retinal Blood Vessels With Deep Neural Networks [J].

Liskowski, Pawel ;

Krawiec, Krzysztof .

IEEE TRANSACTIONS ON MEDICAL IMAGING, 2016, 35 (11) :2369-2380

[8] FABC: Retinal Vessel Segmentation Using AdaBoost [J].

Lupascu, Carmen Alina ;

Tegolo, Domenico ;

Trucco, Emanuele .

IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 2010, 14 (05) :1267-1274

[9] Personal authentication using digital retinal images [J].

Marino, C. ;

Penedo, M. G. ;

Penas, M. ;

Carreira, M. J. ;

Gonzalez, F. .

PATTERN ANALYSIS AND APPLICATIONS, 2006, 9 (01) :21-33

[10] Detection of glaucomatous change based on vessel shape analysis [J].

Matsopoulos, George K. ;

Asvestas, Pantelis A. ;

Delibasis, Konstantinos K. ;

Mouravilansky, Nikolaos A. ;

Zeyen, Thierry G. .

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2008, 32 (03) :183-192

← 1 2 3 →