A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images

被引：459
作者：
Li, Qiaoliang [1 ]
Feng, Bowei [1 ]
Xie, LinPei [1 ]
Liang, Ping [1 ]
Zhang, Huisheng [1 ]
Wang, Tianfu [1 ]
机构：
[1] Shenzhen Univ, Dept Biomed Engn, Guangdong Key Lab Biomed Measurements & Ultrasoun, Shenzhen 518060, Peoples R China
来源：
IEEE TRANSACTIONS ON MEDICAL IMAGING | 2016年 / 35卷 / 01期
基金：
美国国家科学基金会;
关键词：
Cross-modality learning; deep learning; retinal image; vessel segmentation; BLOOD-VESSELS; COLOR IMAGES; CLASSIFICATION; EXTRACTION; ALGORITHM; NETWORKS; FEATURES; DATABASE; FILTER; LEVEL;
D O I：
10.1109/TMI.2015.2457891
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
This paper presents a new supervised method for vessel segmentation in retinal images. This method remolds the task of segmentation as a problem of cross-modality data transformation from retinal image to vessel map. A wide and deep neural network with strong induction ability is proposed to model the transformation, and an efficient training strategy is presented. Instead of a single label of the center pixel, the network can output the label map of all pixels for a given image patch. Our approach outperforms reported state-of-the-art methods in terms of sensitivity, specificity and accuracy. The result of cross-training evaluation indicates its robustness to the training set. The approach needs no artificially designed feature and no preprocessing step, reducing the impact of subjective factors. The proposed method has the potential for application in image diagnosis of ophthalmologic diseases, and it may provide a new, general, high-performance computing framework for image segmentation.
引用
收藏
页码：109 / 118
页数：10
相关论文
共 35 条
[21]   Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction [J].
Mendonca, Ana Maria ;
Campilho, Aurelio .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2006, 25 (09) :1200-1213
[22]   Retinal Image Analysis Using Curvelet Transform and Multistructure Elements Morphology by Reconstruction [J].
Miri, Mohammad Saleh ;
Mahloojifar, Ali .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2011, 58 (05) :1183-1192
[23]   Comparative study of retinal vessel segmentation methods on a new publicly available database [J].
Niemeijer, M ;
Staal, J ;
van Ginneken, B ;
Loog, M ;
Abràmoff, MD .
MEDICAL IMAGING 2004: IMAGE PROCESSING, PTS 1-3, 2004, 5370 :648-656
[24]   Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database [J].
Odstrcilik, Jan ;
Kolar, Radim ;
Budai, Attila ;
Hornegger, Joachim ;
Jan, Jiri ;
Gazarek, Jiri ;
Kubena, Tomas ;
Cernosek, Pavel ;
Svoboda, Ondrej ;
Angelopoulou, Elli .
IET IMAGE PROCESSING, 2013, 7 (04) :373-383
[25]  
Osareh A, 2009, IRAN J SCI TECHNOL B, V33, P191
[26]   Retinal blood vessel segmentation using line operators and support vector classification [J].
Ricci, Elisa ;
Perfetti, Renzo .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2007, 26 (10) :1357-1365
[27]  
Rifai S, 2011, LECT NOTES ARTIF INT, V6912, P645, DOI 10.1007/978-3-642-23783-6_41
[28]   Mathematical modeling of retinal mosaic formation by mechanical interactions and dendritic overlap [J].
Ruggiero, Carmelina ;
Benvenuti, Simona ;
Giacomini, Mauro .
IEEE TRANSACTIONS ON NANOBIOSCIENCE, 2007, 6 (02) :180-185
[29]   Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification [J].
Soares, Joao V. B. ;
Leandro, Jorge J. G. ;
Cesar, Roberto M., Jr. ;
Jelinek, Herbert F. ;
Cree, Michael J. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2006, 25 (09) :1214-1222
[30]   Ridge-based vessel segmentation in color images of the retina [J].
Staal, J ;
Abràmoff, MD ;
Niemeijer, M ;
Viergever, MA ;
van Ginneken, B .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2004, 23 (04) :501-509
1234