Advertisement

Tsallis Entropy Segmentation and Weighted KNN Classifier-Based Automatic DR Detection from Retinal Fundus Images

  • Ravindra D. Badgujar
  • Pramod J. Deore
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 624)

Abstract

Retina of individuals suffering from diabetes mellitus for several years signifies characteristic group of lesions of diabetic retinopathy (DR). DR is an asymptotic disease and emerging as one of the primary cause of vision loss in developing world. Ophthalmologist uses the retinal fundus image for manual screening of DR. To overcome the limitations of manual screening like highly subjective, time-consuming, prone to error, and requirement of expert availability, automated techniques are developed. We propose automated DR detection algorithm which uses retinal fundus images and detects exudates as sign of DR. Initially, the fundus image is preprocessed using Gaussian filter to remove the image noise. The preprocessing is followed by segmentation of fundus image. Optic disc is segmented using morphological operation and eliminated. The exudates which are prime sign of DR are segmented using Tsallis entropy segmentation and classified using weighted KNN. Various performance measures of the proposed technique are evaluated and compared with the existing exudate detection algorithms.

Keywords

Diabetic retinopathy Exudate Tsallis entropy w-KNN classifier 

References

  1. 1.
    World Health Organization Factsheet 2005: http://www.who.int/mediacentre/factsheets/fs282/en (Accessed on Dec 25, 2016).
  2. 2.
    International Diabetes Federation, Fifth Edition 2011: http://www.idf.org/diabetesatlas/news/fifth-edition-release.
  3. 3.
    M. Usman Akram, Shehzad Khalid, Anam Tariq, Shoab A. Khan, Farooque Azam, “Detection and classification of retinal lesions for grading of diabetic retinopathy” Elsevier Journal of Computers in Biology and Medicine 45 (2014) pp: 161–171.Google Scholar
  4. 4.
    Mahendran G, Dhanasekaran R. “Investigation of the severity level of diabetic retinopathy using supervised classifier algorithms.” Comput Electr Eng (2015), http://dx.doi.org/10.1016/j.compeleceng.2015.01.013.
  5. 5.
    P. R. Asha and S. Karpagavalli, “Diabetic Retinal Exudates Detection using Machine Learning Techniques”, International Conference on Advanced Computing and Communication Systems (ICACCS-2015), Jan. 05–07, 2015, Coimbatore, INDIA.Google Scholar
  6. 6.
    Malay Kishore Dutta, Kshitij Srivastava, Shaunak Ganguly, Shaumik Ganguly, M. Parthasarathi, Radim Burget, and Jiri Prinosil, “Exudates Detection in Digital Fundus Image Using Edge Based Method & Strategic Thresholding”, 8th International Conference on Telecommunications and Signal Processing, TSP 2015, Prague, Czech Republic, July 9–11, 2015. IEEE 2015, ISBN 978-1-4799-8498-5.Google Scholar
  7. 7.
    Pavle Prentašić, and Sven Lončarić, “Detection of Exudates in Fundus Photographs using Convolutional Neural Networks”, 9th International Symposium on Image and Signal Processing and Analysis (ISPA 2015), September 7–9, 2015, Zagreb, Croatia.Google Scholar
  8. 8.
    Anushikha Singh, Namita Sengar, Malay Kishore Dutta, Kamil Riha, and Jiri Minar, “Automatic Exudates Detection in Fundus Image using Intensity Thresholding and Morphology.” 7th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT).Google Scholar
  9. 9.
    Xiwei Zhang et al, “Exudate Detection in Color Retinal Images for Mass Screening of Diabetic Retinopathy”, Accepted Manuscript (To appear in Medical Image Analysis).Google Scholar
  10. 10.
    P. Perona, J. Malik, ‘Scale Space and Edge Detection Using Anisotropic Diffusion’ IEEE Transaction on Pattern Analysis, Vol. 12, July 1990, pp 629–639.Google Scholar
  11. 11.
    Kazufumi Ito and Kaiqi Xiong, “Gaussian Filters for Nonlinear Filtering Problems”, IEEE Transactions on Automatic Control, Vol. 45, No. 5, May 2000, pp 910–927.Google Scholar
  12. 12.
    Portes de Albuquerque, M.et al “Image thresholding using Tsallis entropy.”, Pattern Recognition Letters, 25, 1059–1065. DOI: 10.1016/j.patrec.2004.03.003.
  13. 13.
    Abhir Bhalerao et al. “Robust Detection of Microaneurysms for Sight Threatening Retinopathy Screening.” IEEE Computer society, 2008, pp 520–527.Google Scholar
  14. 14.
    Iqbal, M.I et al. “Automatic Diagnosis of Diabetic Retinopathy using Fundus Images.”, Blekinge Institute of Technology. 2006.Google Scholar
  15. 15.
    Akara Sopharak et al. “Automatic Microaneurysm Detection from Non-dilated Diabetic Retinopathy Retinal Images Using Mathematical Morphology Methods.” IAENG International Journal of Computer Science, 2011.Google Scholar
  16. 16.
    Alan D. Fleming et al. “Automated Microaneurysm Detection Using Local Contrast Normalization and Local Vessel Detection.”, IEEE Transactions on Medical Imaging, Vol. 25, No. 9., September 2006, pp 1223–1232.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Electronics & Telecommunication EngineeringRCPITShirpurIndia

Personalised recommendations