Referable diabetic retinopathy identification from eye fundus images with weighted path for convolutional neural network

Liu，Yi Peng1; Li，Zhanqing2; Xu，Cong3; Li，Jing4; Liang，Ronghua1

2019-08-01

10.1016/j.artmed.2019.07.002

ARTIFICIAL INTELLIGENCE IN MEDICINE   影响因子和分区

0933-3657

1873-2860

Diabetic retinopathy (DR) is the most common cause of blindness in middle-age subjects and low DR screening rates demonstrates the need for an automated image assessment system, which can benefit from the development of deep learning techniques. Therefore, the effective classification performance is significant in favor of the referable DR identification task. In this paper, we propose a new strategy, which applies multiple weighted paths into convolutional neural network, called the WP-CNN, motivated by the ensemble learning. In WP-CNN, multiple path weight coefficients are optimized by back propagation, and the output features are averaged for redundancy reduction and fast convergence. The experiment results show that with the efficient training convergence rate WP-CNN achieves an accuracy of 94.23% with sensitivity of 90.94%, specificity of 95.74%, an area under the receiver operating curve of 0.9823 and F1-score of 0.9087. By taking full advantage of the multipath mechanism, the proposed WP-CNN is shown to be accurate and effective for referable DR identification compared to the state-of-art algorithms.

Convolutional neural network Deep learning Diabetic retinopathy Eye fundus images

SCI ; EI

英语

其他

National Natural Science Foundation of China[61502426]

Computer Science ; Engineering ; Medical Informatics

Computer Science, Artificial Intelligence ; Engineering, Biomedical ; Medical Informatics

WOS:000493222300004

ELSEVIER

20193307304321

Backpropagation ; Convolution ; Deep learning ; Deep neural networks ; Medical imaging ; Neural networks

Information Theory and Signal Processing:716.1 ; Artificial Intelligence:723.4 ; Imaging Techniques:746 ; Accidents and Accident Prevention:914.1

CLINICAL MEDICINE

2-s2.0-85070416651

Scopus

1.College of Computer Science & TechnologyZhejiang University of Technology,Hangzhou,310023,China
2.College of Information EngineeringZhejiang University of Technology,Hangzhou,310023,China
3.The Department of PhysicsSouthern University of Science and Technology,Shenzhen,518055,China
4.Cancer Institute of Integrative MedicineTongde Hospital of Zhejiang Province,Hangzhou,310012,China

Liu，Yi Peng,Li，Zhanqing,Xu，Cong,et al. Referable diabetic retinopathy identification from eye fundus images with weighted path for convolutional neural network[J]. ARTIFICIAL INTELLIGENCE IN MEDICINE,2019,99.

Liu，Yi Peng,Li，Zhanqing,Xu，Cong,Li，Jing,&Liang，Ronghua.(2019).Referable diabetic retinopathy identification from eye fundus images with weighted path for convolutional neural network.ARTIFICIAL INTELLIGENCE IN MEDICINE,99.

Liu，Yi Peng,et al."Referable diabetic retinopathy identification from eye fundus images with weighted path for convolutional neural network".ARTIFICIAL INTELLIGENCE IN MEDICINE 99(2019).