Dilated Convolutions in Retinal Blood Vessels Segmentation

被引：21

作者：

Lopes, Ana P. ^{[1
]}

Ribeiro, Alexandrine ^{[1
]}

Silva, Carlos A. ^{[1
]}

机构：

[1] Univ Minho, Dept Elect, Braga, Portugal

来源：

2019 6TH IEEE PORTUGUESE MEETING IN BIOENGINEERING (ENBENG) | 2019年

关键词：

Retinal blood vessel segmentation; Dilated convolution; Context information; IMAGES;

D O I：

10.1109/enbeng.2019.8692520

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

Segmentation of retinal blood vessels allows a quantitative analysis of vessels, hence it helps to diagnose several cardiovascular and ophthalmologic diseases. Manual segmentation is time-consuming, therefore, an automatic method is needed. Dilated convolutions have been recently adopted for semantic segmentation task and higher performances have been achieved. In this paper, we investigate the use of dilated convolutions for retinal vessel segmentation. The proposed architectures are evaluated in the DRIVE dataset. The context information provided by dilated convolutions demonstrated to be valuable for the presented task, leading to more accurate segmentations. Our best model achieves accuracy, specificity and sensitivity of 0.9567, 0.9813 and 0.7903, respectively.

引用

页数：4

共 17 条

[1] Abramoff Michael D, 2010, IEEE Rev Biomed Eng, V3, P169, DOI 10.1109/RBME.2010.2084567
[2] Optimizing the trainable B-COSFIRE filter for retinal blood vessel segmentation
Badawi, Sufian A.
Fraz, Muhammad Moazam
[J]. PEERJ, 2018, 6
[3] DRUNET: a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images
Devalla, Sripad Krishna
Renukanand, Prajwal K.
Sreedhar, Bharathwaj K.
Subramanian, Giridhar
Zhang, Liang
Perera, Shamira
Mari, Jean-Martial
Chin, Khai Sing
Tun, Tin A.
Strouthidis, Nicholas G.
Aung, Tin
Thiery, Alexandre H.
Girard, Michael J. A.
[J]. BIOMEDICAL OPTICS EXPRESS, 2018, 9 (07): : 3244 - 3265
[4] Dumoulin V, 2018, Arxiv, DOI [arXiv:1603.07285, 10.48550/arXiv.1603.07285]
[5] Feng ZW, 2017, IEEE IMAGE PROC, P1742, DOI 10.1109/ICIP.2017.8296580
[6] Blood vessel segmentation methodologies in retinal images - A survey
Fraz, M. M.
Remagnino, P.
Hoppe, A.
Uyyanonvara, B.
Rudnicka, A. R.
Owen, C. G.
Barman, S. A.
[J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2012, 108 (01) : 407 - 433
[7] Holschneider M., 1990, Wavelets, P286
[8] Retinal vessel segmentation of color fundus images using multiscale convolutional neural network with an improved cross-entropy loss function
Hu, Kai
Zhang, Zhenzhen
Niu, Xiaorui
Zhang, Yuan
Cao, Chunhong
Xiao, Fen
Gao, Xieping
[J]. NEUROCOMPUTING, 2018, 309 : 179 - 191
[9] Kanski's Clinical Ophthalmology: A Systematic Approach, 8th edition
Karpecki, Paul M.
[J]. OPTOMETRY AND VISION SCIENCE, 2015, 92 (10) : e386 - e386
[10] Li DP, 2015, PROC CVPR IEEE, P213, DOI 10.1109/CVPR.2015.7298617

← 1 2 →