Exudate Detection for Diabetic Retinopathy With Convolutional Neural Networks

被引:0
作者
Yu, Shuang [1 ]
Xiao, Di [1 ]
Kanagasingam, Yogesan [1 ]
机构
[1] CSIRO, Australian E Hlth Res Ctr, Canberra, ACT, Australia
来源
2017 39TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC) | 2017年
基金
英国医学研究理事会;
关键词
Deep Learning; Convolutional Neural Networks; Exudate Detection; Retinal Imaging; Diabetic Retinopathy; RETINAL IMAGES;
D O I
暂无
中图分类号
Q6 [生物物理学];
学科分类号
071011 ;
摘要
Exudate detection is an essential task for computer-aid diagnosis of diabetic retinopathy (DR), so as to monitor the progress of DR. In this paper, deep convolutional neural network (CNN) is adopted to achieve pixel-wise exudate identification. The CNN model is first trained with expert labeled exudates image patches and then saved as off-line classifier. In order to achieve pixel-level accuracy meanwhile reduce computational time, potential exudate candidate points are first extracted with morphological ultimate opening algorithm. Then the local region (64 x 64) surrounding the candidate points are forwarded to the trained CNN model for classification / identification. A pixel-wise accuracy of 91.92%, sensitivity of 88.85% and specificity of 96% is achieved with the proposed CNN architecture on the test database.
引用
收藏
页码:1744 / 1747
页数:4
相关论文
共 19 条
[1]  
Abramoff Michael D, 2010, IEEE Rev Biomed Eng, V3, P169, DOI 10.1109/RBME.2010.2084567
[2]  
Amel F., 2012, INT J IMAGE GRAPH SI, V4, P19, DOI [10.5815/ijigsp.2012.04.03, DOI 10.5815/ijigsp.2012.04.03, DOI 10.5815/IJIGSP.2012.04.03]
[3]  
[Anonymous], BRIT J OPHTHALMOLOGY
[4]   Numerical residues [J].
Beucher, Serge .
IMAGE AND VISION COMPUTING, 2007, 25 (04) :405-415
[5]   Diabetic retinopathy and diabetic macular edema - Pathophysiology, screening, and novel therapies [J].
Ciulla, TA ;
Amador, AG ;
Zinman, B .
DIABETES CARE, 2003, 26 (09) :2653-2664
[6]  
Fabrizio J, 2009, LECT NOTES COMPUT SC, V5720, P272, DOI 10.1007/978-3-642-03613-2_25
[7]   Neural network based detection of hard exudates in retinal images [J].
Garcia, Maria ;
Sanchez, Clara I. ;
Lopez, Maria I. ;
Abasolo, Daniel ;
Hornero, Roberto .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2009, 93 (01) :9-19
[8]  
Kovesi Peter., 1997, Tenth Australian Joint Converence on Artificial Intelligence, P2
[9]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[10]   Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis [J].
Niemeijer, Meindert ;
van Ginneken, Bram ;
Russell, Stephen R. ;
Suttorp-Schulten, Maria S. A. ;
Abramoff, Michael D. .
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE, 2007, 48 (05) :2260-2267