Abstract
The convolutional neural network (CNN) has been effectively used to do feature extraction in medical image analysis including fundus images for diabetic retinopathy. However, some important detail features are easily ignored, which causes low prediction accuracy. To solve this problem, a CNN feature extraction method based on a novel pixel-level attention mechanism is proposed to achieve an efficient and accurate identification of diabetic retinopathy. Firstly, data normalization and data augmentation are used to improve the quality of datasets. Then, according to the structure characteristics of the two backbone networks Inception- ResnetV2 and EfficientNet-B5, the corresponding attention modules are introduced respectively. Finally, attention networks are trained as feature extractors of fundus images, and complementary deep attention feature descriptors are formed through feature fusion, which can effectively improve the accuracy of the classification model. The experimental results on EyePACS, Messidor and OIA datasets show that the proposed method outperforms the previous ones.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cho, N.H., Shaw, J.E., Karuranga, S., et al.: IDF diabetes atlas: global estimates of diabetes prevalence for 2017 and projections for 2045. Diabetes Res. Clin. Pract. 138, 271–281 (2018)
Zhang, G., Chen, H., Chen, W., et al.: Prevalence and risk factors for diabetic retinopathy in China: a multi-hospital-based cross-sectional study. Br. J. Ophthalmol. 101(12), 1591–1595 (2017)
Kourgialis, N.: Diabetic retinopathy-silently blinding millions of people world-wide. Invest Ophtalmol. Vis. Sci. 57, 6669–6682 (2017)
Deka, A., Sarma, K.K.: SVD and PCA features for ANN based detection of diabetes using retinopathy. In: Proceedings of the CUBE International Information Technology Conference, pp. 38–41 (2012)
Kumar, M., Nath, M.K.: Detection of microaneurysms and exudates from color fundus images by using SBGFRLS algorithm. In: Proceedings of the International Conference on Informatics and Analytics, pp. 1–6 (2016)
Xie, Y., Huang, H., Hu, J.: Staging and lesion detection of diabetic retinopathy based on deep convolution neural network. J. Comput. Appl. 40(8), 2460–2464 (2020)
Zhou, Y., Wang, B., He, X., et al.: DR-GAN: conditional generative adversarial network for fine-grained lesion synthesis on diabetic retinopathy images. arXiv preprint arXiv:1912.04670 (2019)
Zeng, X.L., Chen, H.Q., Luo, Y., et al.: Automated detection of diabetic retinopathy using a binocular siamese-like convolutional network. In: 2019 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1–5. IEEE (2019)
Wang, Z., Yin, Y., Shi, J., et al.: Zoom-in-net: deep mining lesions for diabetic retinopathy detection. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 267–275 (2017)
Bajwa, M.N., Taniguchi, Y., Malik, M.I., et al.: Combining fine-and coarse-grained classifiers for diabetic retinopathy detection. In: Annual Conference on Medical Image Understanding and Analysis, pp. 242–253 (2019)
Fukui, H., Hirakawa, T., Yamashita, T., et al.: Attention branch network: learning of attention mechanism for visual explanation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10705–10714 (2019)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132–7141 (2018)
Mei, X., Pan, E., Ma, Y., et al.: Spectral-spatial attention networks for hyperspectral image classification. Remote Sens. 11(8), 963 (2019)
Russakovsky, O., Deng, J., Su, H., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Szegedy, C., Ioffe, S., Vanhoucke, V., et al.: Inception-v4, inception-resnet and the impact of residual connections on learning. arXiv preprint arXiv:1602.07261 (2016)
Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)
Ke, G., Meng, Q., Finley, T., et al.: Lightgbm: a highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems, pp. 3146–3154 (2017)
Hussien, E., Elsayed, Z.: Improving error back propagation algorithm by using cross entropy error function and adaptive learning rate. Int. J. Comput. Appl. 161(8), 5–9 (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Seoud, L., Hurtut, T., Chelbi, J., et al.: Red lesion detection using dynamic shape features for diabetic retinopathy screening. IEEE Trans. Med. Imag. 35(4), 1116–1126 (2016)
Vo, H.H., Verma, A.: New deep neural nets for fine-grained diabetic retinopathy recognition on hybrid color space. In: 2016 IEEE International Symposium on Multimedia (ISM), pp. 209–215. IEEE (2016)
Nguyen, Q.H., Muthuraman, R., Singh, L., et al.: Diabetic retinopathy detection using deep learning. In: Proceedings of the 4th International Conference on Machine Learning and Soft Computing, pp. 103–107 (2020)
Selvaraju, R.R., Cogswelli, M., Das, A., et al.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vision 128(2), 336–359 (2020)
Acknowledgments
The authors thank the members of Machine Learning and Artificial Intelligence Laboratory, School of Computer Science and Technology, Wuhan University of Science and Technology, for their helpful discussion within seminars. This work was supported by, National Natural Science Foundation of China (61972299, U1803262, 61702381), Hubei Province Natural Science Foundation of China (No. 2018CFB526).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zou, J., Zhang, X., Lin, X. (2021). A Diabetic Retinopathy Classification Method Based on Novel Attention Mechanism. In: Huang, DS., Jo, KH., Li, J., Gribova, V., Bevilacqua, V. (eds) Intelligent Computing Theories and Application. ICIC 2021. Lecture Notes in Computer Science(), vol 12836. Springer, Cham. https://doi.org/10.1007/978-3-030-84522-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-84522-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-84521-6
Online ISBN: 978-3-030-84522-3
eBook Packages: Computer ScienceComputer Science (R0)