Abstract
Diabetic Retinopathy (DR) is a common medical disorder damaging the retinal blood vessels of diabetic patients. Regular screening of fundus images and timely detection of the initial symptoms of DR, namely microaneurysms and hemorrhages, are important to reduce the possibility of vision impairment. The proposed work explores the power of Convolutional Neural Network (CNN) in the analysis and detection of retinal disorders. An automated deep learning model named Deep Convolutional Neural Network-based Diabetic Retinopathy Detection (DCNN-DRD) has been proposed to analyze the retinal images and classify them as healthy or defective based on DR symptoms. A retinal image is fed into the DCNN-DRD model which consists of five convolution and five pooling layers followed by a dropout layer and three fully connected layers. The linear output data produced in every layer represents the weighted value based on DR symptoms and is fed into a gradient descent graph for refinement to improve the learning accuracy through several iterations. Thus, the DCNN-DRD model does not require any preprocessing and learns high-level discriminative features of DR symptoms from the pixel intensities to categorize the retinal image as either healthy or defective. The DCNN-DRD model has been trained with a subset of images from the MESSIDOR dataset and the ROC dataset. Experimental results show that the DCNN-DRD model successfully predicts the retinal image as either healthy or defective with 97% accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
S. Wild, G. Roglic, A Green et al., Global prevalence of diabetes: estimates for the year 2000 and projections for 2030. Diabetes Care, 27, l047–1053, (2004)
Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems, (2012), pp. 1097–1105
R. Girshick, J. Donahue, T. Darrell, J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014), pp. 580–587
J.L. Long, N. Zhang, T. Darrell, Do convnets learn correspondence? in In Advances in Neural Information Processing Systems (2014), pp. 1607–1609
A. Ciresan, L.M. Giusti, Gambardella, J. Schmidhuber, Deep neural networks segment neuronal membranes in electron microscopy images, in Advances in Neural Information Processing Systems (2012), pp. 2843–2851
C. Cernazanu-Glavan, S. Holban, Segmentation of bone structure in X-ray images using convolutional neural network Adv. Electr. Comput. Eng. 13(1), 87–94 (2013)
S. Li, A.B. Chan, 3d human pose estimation from monocular images with deep convolutional neural network, in: Computer Vision? ACCV 2014 (Springer International Publishing, 2014), pp. 332–347
G. Levi, T. Hassner, Age and gender classification using convolutional neural networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2015), pp. 34–42
P. Liskowski, K. Karmic, Segmenting retinal blood vessels with deep neural networks. IEEE Trans. Med. Imaging, 35(11) (2016)
U. Raghavendraa, H. Fujita, S. Bhandary, A. Gudigar, J.H. Tan, R. Acharya, Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Elsevier Inf. Sci. 441, 41–49 (2017) https://doi.org/10.1016/j.ins.2018.01.051
M.P. Paing, S. Choomchuay, Detection of lesions and classification of diabetic retinopathy using fundus images. Biomed. Eng. Int. Conf. (2016)
S.S. Rubini A. Kunthavai, Diabetic retinopathy detection based on eigenvalues of the hessian matrix. Procedia Comput. Sci. 47(C), 311–318 (2015)
P.K.R. Yelampalli, J. Nayak, V.H Gaidhane, Blood vessel segmentation and classification of diabetic retinopathy images using gradient operator and statistical analysis, in Proceedings of the World Congress on Engineering and Computer Science 2017 Vol IIWCECS 2017, October 25–27, 2017
S. Kaur, K.S. Mann, Optimized retinal blood vessel segmentation technique for detection of diabetic retinopathy. Int. J. Adv. Res. Comput. Sci. (2016). http://dx.doi.org/10.26483/ijarcs.v8i9.5071
D.W Safitri, D. Juniati, Classification of diabetic retinopathy using fractal dimension analysis of eye fundus image, in AIP Conference Proceedings, vol. 1867, p. 020011 (2017). https://doi.org/10.1063/1.4994414
B. Zhang, F. Karray, Q. Li, L. Zhang, Sparse Representation Classifier for microaneurysm detection andretinal blood vessel extraction. Inf. Sci. 200, 78–90 (2012). https://doi.org/10.1016/j.media.2009.05.005
P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, Y. LeCun, Overfeat: Integrated recognition, localization and detection using convolutional networks. Comput. Vis. Pattern Recognit. (2013). arXiv:1312.6229
W. Shen, X. Wang, Y. Wang, X. Bai, Z. Zhang, DeepContour: a deep convolutional feature learned by positive-sharing loss for contour detection, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Boston, MA, USA, 7–12 June 2015)
Q. Abbas, Glaucoma-deep: detection of glaucoma eye disease on retinal fundus images using deep learning (IJACSA). Int. J. Adv. Comput. Sci. Appl. 8(6), (2017)
M. Abadi et al. (2016) TensorFlow: large-scale machine learning on heterogeneous distributed systems, arXiv: 1603.04467 [cs.DC] (Mar. 2016)
CNN Tutorial, https://adeshpande3.github.io/adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks/
CNN tutorial, https://stackoverflow.com/questions/37340129/tensorflow-training-on-my-own-image
Acknowledgements
We would like to thank Dr. Ashish Sharma, Lotus Eye Care Hospital, Coimbatore, for his continuous effort in manually grading the retinal images and verifying the results achieved.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Saranya Rubini, S., Saai Nithil, R., Kunthavai, A., Sharma, A. (2019). Deep Convolutional Neural Network-Based Diabetic Retinopathy Detection in Digital Fundus Images. In: Wang, J., Reddy, G., Prasad, V., Reddy, V. (eds) Soft Computing and Signal Processing . Advances in Intelligent Systems and Computing, vol 900. Springer, Singapore. https://doi.org/10.1007/978-981-13-3600-3_19
Download citation
DOI: https://doi.org/10.1007/978-981-13-3600-3_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-3599-0
Online ISBN: 978-981-13-3600-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)