Advertisement

Journal of Medical Systems

, 43:304 | Cite as

An Intelligent Segmentation and Diagnosis Method for Diabetic Retinopathy Based on Improved U-NET Network

  • Qianjin Li
  • Shanshan Fan
  • Changsheng ChenEmail author
Image & Signal Processing
  • 27 Downloads
Part of the following topical collections:
  1. Distributed Analytics and Deep Learning in Health Care

Abstract

Due to insufficient samples, the generalization performance of deep network is insufficient. In order to solve this problem, an improved U-net based image automatic segmentation and diagnosis algorithm was proposed, in which the max-pooling operation in original U-net model was replaced by the convolution operation to keep more feature information. Firstly, the regions of 128×128 were extracted from all slices of the patients as data samples. Secondly, the patient samples were divided into training sample set and testing sample set, and data augmentation was performed on the training samples. Finally, all the training samples were adopted to train the model. Compared with Fully Convolutional Network (FCN) model and max-pooling based U-net model, DSC and CR coefficients of the proposed method achieve the best results, while PM coefficient is 2.55 percentage lower than the maximum value in the two comparison models, and Average Symmetric Surface Distance is slightly higher than the minimum value of the two comparison models by 0.004. The experimental results show that the proposed model can achieve good segmentation and diagnosis results.

Keywords

Generalization performance Deep learning Diabetic retinopathy U-net model Fully convolutional network Intelligent diagnosis 

Notes

Compliance with Ethical Standards

Conflict of Interest

We declare that we have no conflict of interest.

Human and Animal Rights

The paper does not contain any studies with human participants or animals performed by any of the authors.

References

  1. 1.
    Ganesan, K., and Martis, R. J., Computer-aided diabetic retinopathy detection using trace transforms on digital fundus images[J]. Med. Biol. Eng. Comput. 52(8):663–672, 2014.CrossRefPubMedGoogle Scholar
  2. 2.
    Devaraj, D., and Zzz, M., A review on exudates detection in the diagnosis of diabetic retinopathy[J]. Acm Sigplan Notices 46(11):11–20, 2013.Google Scholar
  3. 3.
    Franklin, S. W., and Rajan, S. E., Diagnosis of diabetic retinopathy by employing image processing technique to detect exudates in retinal images[J]. IET Image Process. 8(10):601–609, 2014.CrossRefGoogle Scholar
  4. 4.
    Yun, W. L., Acharya, U. R., Venkatesh, Y. V. et al., Identification of different stages of diabetic retinopathy using retinal optical images[J]. Inform. Sci. 178(1):106–121, 2008.CrossRefGoogle Scholar
  5. 5.
    Fadzil, M. H. A., Izhar, L. I., Nugroho, H. et al., Analysis of retinal fundus images for grading of diabetic retinopathy severity[J]. Med. Biol. Eng. Comput. 49(6):693–700, 2011.CrossRefGoogle Scholar
  6. 6.
    Seoud, L., Hurtut, T., Chelbi, J. et al., Red lesion detection using dynamic shape features for diabetic retinopathy screening[J]. IEEE Trans. Med. Imag. 35(4):127–133, 2016.CrossRefGoogle Scholar
  7. 7.
    Rahim, S. S., Jayne, C., Palade, V. et al., Automatic detection of microaneurysms in colour fundus images for diabetic retinopathy screening[J]. Neural Comput. Applic. 27(5):1149–1164, 2015.CrossRefGoogle Scholar
  8. 8.
    Abbas, Q., Fondon, I., Sarmiento, A., Jiménez, S., and Alemany, P., Automatic recognition of severity level for diagnosis of diabetic retinopathy using deep visual features[J]. Med. Biol. Eng. Comput. 55(11):1959–1974, 2017.CrossRefGoogle Scholar
  9. 9.
    Jacko, J. A., Barnard, L., Yi, J. S. et al., Empirical validation of the Windows® accessibility settings and multimodal feedback for a menu selection task for users with Diabetic Retinopathy[J]. Behav. Inform. Technol. 24(6):16–34, 2005.CrossRefGoogle Scholar
  10. 10.
    Mookiah, M. R. K., Acharya, U. R., Martis, R. J., Chua, C. K., Lim, C. M., Ng, E. Y. K., and Laude, A., Evolutionary algorithm based classifier parameter tuning for automatic diabetic retinopathy grading: A hybrid feature extraction approach[J]. Knowl-Based Syst. 39(12):9–22, 2013.CrossRefGoogle Scholar
  11. 11.
    Zhang, J., Yang, J., and Huang, T., et al., Identification of novel proliferative diabetic retinopathy related genes on protein-protein interaction network[J]. Neurocomputing, :S0925231216306191, 2016.Google Scholar
  12. 12.
    Piri, S., Delen, D., Liu, T., and Zolbanin, H.M., A data analytics approach to building a clinical decision support system for diabetic retinopathy: Developing and deploying a model ensemble[J]. Dec. Support Syst. S0167923617300908, 2017.Google Scholar
  13. 13.
    Saleh, E., Błaszczyński, J., Moreno, A. et al., Learning ensemble classifiers for diabetic retinopathy assessment[J]. Artif. Intell. Med. 23(12):2371:2392, 2017.Google Scholar
  14. 14.
    Richa, R., Linhares, R., Comunello, E., von Wangenheim, A., Schnitzler, J. Y., Wassmer, B., Guillemot, C., Thuret, G., Gain, P., Hager, G., and Taylor, R., Fundus image mosaicking for information augmentation in computer-assisted slit-lamp imaging[J]. IEEE Trans. Med. Imag. 33(6):1304–1312, 2014.CrossRefGoogle Scholar
  15. 15.
    Boever, P. D., Malik, R., Afifi, N. et al., Deep learning to screen for referable diabetic retinopathy[J]. Acta Ophthalmologica 95(9):23–34, 2017.Google Scholar
  16. 16.
    Dashtbozorg, B., Zhang, J., Huang, F. et al., Retinal microaneurysms detection using local convergence index features[J]. IEEE Trans. Image Process. 24(12):1–13, 2018.Google Scholar
  17. 17.
    Autio, I., García, B., Carlos, J., Immonen, I. et al., A voting margin approach for the detection of retinal microaneurysms[J]. EYE Syst. 23(23):98–109, 2005.Google Scholar
  18. 18.
    Yizhang Jiang, Kaifa Zhao, Kaijian Xia, Jing Xue, Leyuan Zhou, Yang Ding, Pengjiang Qian.A Novel Distributed Multitask Fuzzy Clustering Algorithm for Automatic MR Brain Image Segmentation[J]. J. Medical Systems 43(5): 118:1-118:9, 2019Google Scholar
  19. 19.
    Gargeya, R., and Leng, T., Automated identification of diabetic retinopathy using deep learning[J]. Ophthalmology. S0161642016317742, 2017.Google Scholar
  20. 20.
    David, A. M., Yiyue, L., Ali, E. et al., Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning[J]. Investig. Opthalmol. Visual Sci. 57(13):5200, 2016.CrossRefGoogle Scholar
  21. 21.
    Saha, S. K., Fernando, B., Cuadros, J. et al., Deep learning for automated quality assessment of color fundus images in diabetic retinopathy screening[J]. J. Digit. Imag. 24(10):12–19, 2017.Google Scholar
  22. 22.
    Zhou, L., Zhao, Y., Yang, J., Yu, Q., and Xu, X., Deep multiple instance learning for automatic detection of diabetic retinopathy in retinal images[J]. IET Image Process. 12(4):563–571, 2018.CrossRefGoogle Scholar
  23. 23.
    Kaijian Xia, Hongsheng Yin, Yu-Dong Zhang, Deep Semantic Segmentation of Kidney and Space-Occupying Lesion Area Based on SCNN and ResNet Models Combined with SIFT-Flow Algorithm[J]. J. Medical Systems. 43(1): 2:1-2:12, 2019Google Scholar
  24. 24.
    Dai, L., Fang, R., Li, H. et al., Clinical report guided retinal microaneurysm detection with multi-sieving deep learning[J]. IEEE Trans. Med. Imag. 81(34):111–123, 2018.Google Scholar
  25. 25.
    Orlando, J. I., Prokofyeva, E., Del Fresno, M., et al., An ensemble deep learning based approach for red lesion detection in fundus images[J]. Computer Methods and Programs in Biomedicine, :S0169260717307897, 2017.Google Scholar
  26. 26.
    Rajala, U., Pajunpaa, H., Koskela, P., and Keinanen-Kiukaanniemi, S., High cardiovascular disease mortality in subjects with visual impairment caused by diabetic retinopathy[J]. Diab. Care 23(7):957–961, 2000.CrossRefGoogle Scholar
  27. 27.
    Priya, R., and Aruna, P., SVM and neural network based diagnosis of diabetic retinopathy[J]. Int. J. Comput. Applic. 41(1):6–12, 2013.Google Scholar
  28. 28.
    Yan, Z., Han, X., and Wang, C., et al., Learning mutually local-global U-nets for high-resolution retinal lesion segmentation in fundus images[J]. 24(21):345–355, 2019.Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.The Affiliated Hospital of Weifang Medical UniversityShandongChina

Personalised recommendations