Recent development on automatic computer aided diagnosis for early detection of diabetic retinopathy using k-means clustering and fuzzy logic

  • Authors

    • Harshpreet Kaur
    • Chetan Marwaha
    2018-06-08
    https://doi.org/10.14419/ijet.v7i2.33.15520
  • Blood Vessels, Clustering, Computer Aided Diagnosis, Diabetic Retinopathy, Fundus Image, Fuzzy Logic, Optical Coherence Tomography (OCT).
  • Diabetic retinopathy is a common disease caused among diabetic patients around the world. Resulting from diabetes mellitus, this disease is mostly caused by retinal microvasculature. If undetected, this disease may result in severe health loss and even blindness among patients. Researchers around the world are putting forth various developments for its early detection. Techniques like manual examination of structure images to find morphological changes in microaneurysms, exudates, blood vessels, hemorrhages are extremely a protracted task. Manual examination of structure pictures to discover morphological changes in microaneurysms, exudates, blood vessels, hemorrhages is terribly a long task. Other techniques include Optical Coherence Tomography (OCT), which is one of the most widely used technique for the detection of retinopathy due to its early detection of the disease. Inspired by these, the work presented in this paper is focused on comparing these two retinopathic detection techniques and analyze the results for the future resear ch. In the presented work, different retinal datasets are considered are analyzed for the detection of retinopathy. Moreover, various performance parameters are evaluated like specificity, sensitivity, and accuracy for overall assessment of the presented model.

     

     

  • References

    1. [1] B. H. Priyadharsini and M. R. Devi, “Analysis of retinal blood vessels using image processing techniques,†2014 Int. Conf. Intell. Comput. Appl., pp. 244–248, 2014.

      [2] S. Abdul, R. Bekinalkar, B. Raghavendra, T. G. Goud, and V. Sc, “A study of the prevalence of type 2 diabetes mellitus among urban adults of Ballari, India,†vol. 2, no. 4, pp. 660–665, 2015.

      [3] T. Walter, J.-C. Klein, P. Massin, and A. Erginay, “A contribution of image processing to the diagnosis of diabetic retinopathy--detection of exudates in color fundus images of the human retina.,†IEEE Trans. Med. Imaging, vol. 21, no. 10, pp. 1236–1243, 2002.

      [4] M. Venkatesh and V. S. Ramamurthy, “Classification of Diabetic Retinopathy Using Image Processing and Soft Computing Techniques,†vol. 3, no. 5, pp. 533–537, 2014.

      [5] M. B. Patwari, R. R. Manza, Y. M. Rajput, M. Saswade, and N. Deshpande, “Personal Identification Algorithm Based on Retinal Blood Vessels Bifurcation,†2014 Int. Conf. Intell. Comput. Appl., pp. 203–207, 2014.

      [6] T. R. Rakshitha, D. Deepashree, and K. S. C. Prasanna, “Comparative study of imaging transform on diabetic retinopathy images,†2016 IEEE Int. Conf. Recent Trends Electron. Inf. Commun. Technol. RTEICT 2016 - Proc., pp. 118–122, 2017.

      [7] R. M. Sri and V. Rajesh, “Early detection of diabetic retinopathy from retinal fundus images using Eigenvalue analysis.†2015 Int. Conf. Control. Instrumentation, Commun. Comput. Technol., pp. 766–769, 2015.

      [8] Ref 18 google.â€

      [9] K. Kansal and E. R. Nishi, “Automated detection of exudates for diabetic retinopathy screening in fundus images using CS-ACO optimization approach,†Int. J. Bio-Science Bio-Technology, vol. 8, no. 3, pp. 323–340, 2016.

      [10] M. A. U. Khan, T. M. Khan, T. A. Soomro, N. Mir, and J. GAO, “Boosting sensitivity of a retinal vessel segmentation algorithm,†Pattern Anal. Appl., 2017.

      [11] B. L. Sikorski, G. Malukiewicz, J. Stafiej, H. Lesiewska-junk, and D. Raczynska, “The Diagnostic Function of OCT in Diabetic Maculopathy The Diagnostic Function of OCT in Diabetic Maculopathy,†no. January 2014, 2013.

      [12] A. B. Mutiara, R. Refianti, and M. C. Kamu, “Qualitative evaluation of quantum enhancement for edge detection of medical images,†J. Theor. Appl. Inf. Technol., vol. 72, no. 3, pp. 451–457, 2015.

      [13] M. B. Patwari, R. R. Manza, Y. M. Rajput, M. Saswade, and N. Deshpande, “Detection and Counting the Microaneurysms using Image Processing Techniques,†Int. J. Appl. Inf. Syst., vol. 6, no. 5, pp. 11–17, 2013.

      [14] A. B. M. A. Hossain, “Detection and Classification of Diabetic Retinopathy Using K-Means Clustering and Fuzzy Logic,†18th International Conf. Comput. Inf. Technol., pp. 534–538, 2015.

      [15] Y. M. Rajput, R. R. Manza, M. B. Patwari, D. D. Rathod, P. L. Borde, and P. L. Yannawar, “Detection of non-proliferative diabetic retinopathy lesions using wavelet and classification using K-means clustering,†2015 Int. Conf. Commun. Networks, no. November, pp. 381–387, 2015.

      [16] S. B. Manoj Kumar, R. Manjunath, and H. S. Sheshadri, “Feature extraction from the fundus images for the diagnosis of Diabetic Retinopathy,†Int. Conf. Emerg. Res. Electron. Comput. Sci. Technol., pp. 240–245, 2015.

      [17] S. D. Kasurde and S.N.Randive, “An Automatic Detection of Proliferative Diabetic Retinopathy,†Energy Syst. Appl. 2015 Int. Conf., no. Icesa, pp. 86–90, 2015.

  • Downloads

  • How to Cite

    Kaur, H., & Marwaha, C. (2018). Recent development on automatic computer aided diagnosis for early detection of diabetic retinopathy using k-means clustering and fuzzy logic. International Journal of Engineering & Technology, 7(2.33), 869-873. https://doi.org/10.14419/ijet.v7i2.33.15520