Automatic Screening of Diabetic Retinopathy Images with Convolution Neural Network Based on Caffe Framework

Objective Diabetic retinopathy (DR) is a serious complication of eye in diabetes mellitus (DM) patients. In order to automatically screen DR, we aim to use convolutional neural network (CNN) to screen DR fundus images automatically. Methods A total of 10,551 fundus images from Kaggle fundus image dataset were collected for this experiment. Firstly, the images were preprocessed by histogram equalization and image augmentation. Then, the CNN was constructed and trained with Caffe framework. Our designed CNN models were trained by 8,626 images. Finally, the performance of the trained CNN model was validated by classifying 1,925 fundus images into DR and non-DR ones. Results The performance results indicated that the CNN achieved accuracy of 75.70% in 1,925 test fundus images. Conclusions CNN model is useful to classify the DR fundus images, thus might be applicable in further DR screening program for larger DM population.

[1]  Frans Coenen,et al.  Convolutional Neural Networks for Diabetic Retinopathy , 2016, MIUA.

[2]  Mehmet Bilgili,et al.  Wind Speed Prediction of Target Station from Reference Stations Data , 2013 .

[3]  Claus Nebauer,et al.  Evaluation of convolutional neural networks for visual recognition , 1998, IEEE Trans. Neural Networks.

[4]  J. Anitha,et al.  An enhanced Counter Propagation Neural Network for abnormal retinal image classification , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[5]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  H. Kuper,et al.  Rapid assessment of avoidable blindness and diabetic retinopathy in Chiapas, Mexico. , 2012, Ophthalmology.

[7]  E. Stefánsson,et al.  The prevalence of retinopathy in subjects with and without type 2 diabetes mellitus , 2014, Acta ophthalmologica.

[8]  P. Aruna,et al.  SVM and Neural Network based Diagnosis of Diabetic Retinopathy , 2012 .

[9]  T. Williamson,et al.  Automatic detection of diabetic retinopathy using an artificial neural network: a screening tool. , 1996, The British journal of ophthalmology.

[10]  Carlos Bento,et al.  Intelligent road traffic status detection system through cellular networks handover information: An exploratory study , 2013 .

[11]  L. B. Felix,et al.  Artificial neural network prediction of chemical oxygen demand in dairy industry effluent treated by electrocoagulation , 2014 .

[12]  Lilian Tang,et al.  Filtering normal retinal images for diabetic retinopathy screening using multiple classifiers , 2009, 2009 9th International Conference on Information Technology and Applications in Biomedicine.

[13]  Rupa V. Lichode.  Automatic Diagnosis of Diabetic Retinopathy by Hybrid Multilayer Feed Forward Neural Network , 2013 .

[14]  B. Klein,et al.  Global Prevalence and Major Risk Factors of Diabetic Retinopathy , 2012, Diabetes Care.

[15]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[16]  Qeethara Al-Shayea.  Artificial Neural Networks in Medical Diagnosis , 2024, International Journal of Research Publication and Reviews.

[17]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[18]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[19]  Z. Shan,et al.  Prevalence of Diabetic Retinopathy in Mainland China: A Meta-Analysis , 2012, PloS one.

[20]  Yu Song,et al.  Application of artificial neural network for the prediction of stock market returns: The case of the Japanese stock market , 2016 .

[21]  F. E. A. El-Samie,et al.  Automated detection of diabetic retinopathy in blurred digital fundus images , 2012, 2012 8th International Computer Engineering Conference (ICENCO).