access icon free Improved automated detection of glaucoma from fundus image using hybrid structural and textural features

Glaucoma is a group of eye disorders that damage the optic nerve. Considering a single eye condition for the diagnosis of glaucoma has failed to detect all glaucoma cases accurately. A reliable computer-aided diagnosis system is proposed based on a novel combination of hybrid structural and textural features. The system improves the decision-making process after analysing a variety of glaucoma conditions. It consists of two main modules hybrid structural feature-set (HSF) and hybrid texture feature-set (HTF). HSF module can classify a sample using support vector machine (SVM) from different structural glaucoma condition and the HTF module analyses the sample founded on various texture and intensity-based features and again using SVM makes a decision. In the case of any conflict in the results of both modules, a suspected class is introduced. A novel algorithm to compute the super-pixels has also been proposed to detect the damaged cup. This feature alone outperformed the current state-of-the-art methods with 94% sensitivity. Cup-to-disc ratio calculation method for cup and disc segmentation, involving two different channels has been introduced increasing the overall accuracy. The proposed system has given exceptional results with 100% accuracy for glaucoma referral.

Inspec keywords: support vector machines; feature extraction; diseases; image segmentation; eye; image texture; medical image processing

Other keywords: hybrid texture feature-set; cup-to-disc ratio calculation method; support vector machine; reliable computer-aided diagnosis system; eye disorders; fundus image; hybrid structural feature-set; glaucoma diagnosis; SVM; optic nerve; improved automated detection; single eye condition; decision-making process; HSF; glaucoma conditions; hybrid structural; glaucoma referral

Subjects: Optical, image and video signal processing; Biomedical measurement and imaging; Biology and medical computing; Patient diagnostic methods and instrumentation; Medical and biomedical uses of fields, radiations, and radioactivity; health physics; Knowledge engineering techniques; Computer vision and image processing techniques

References

    1. 1)
      • 30. Kociołek, M., Materka, A., Strzelecki, M.: ‘Discrete wavelet transform – derived features for digital image texture analysis’. Proc. of Int. Conf. on Signals and Electronic Systems, Lodz, Poland, September 2001, pp. 163168.
    2. 2)
      • 2. Quigley, H.A., Broman, A.T.: ‘The number of people with glaucoma worldwide in 2010 and 2020’, Br. J. Ophthalmol., 2006, 90, (3), pp. 262267.
    3. 3)
      • 28. Eleyan, A., Demirel, H.: ‘Co-occurrence based statistical approach for face recognition’. 2009 24th Int. Symp. on Computer and Information Sciences, Guzelyurt, 2009, pp. 611615.
    4. 4)
      • 19. ‘Maths Work: Regionprops’. Available at http://www.mathworks.com/help/images/ref/regionprops.html, accessed February 2016.
    5. 5)
      • 11. Dua, S., Acharya, U.R., Chowriappa, P., et al: ‘Wavelet-based energy features for glaucomatous image classification’, IEEE Trans. Inf. Technol. Biomed., 2012, 16, (1), pp. 8087.
    6. 6)
      • 20. Spaeth, G.L.: ‘Appearances of the optic disc in glaucoma: a pathogenetic classification’. Symp. on Glaucoma, Transactions of the New Orleans Academy of Ophthalmology, CV Mosby, St. Louis, 1981, pp. 114152.
    7. 7)
      • 29. Nitish, Z., Vrushsen, P.: ‘GLCM textural features for brain tumor classification’, IJCSI Int. J. Comput. Sci. Issues, 2012, 9, (3), pp. 354359.
    8. 8)
      • 34. ‘Analyze Menu’. Available at http://rsb.info.nih.gov/ij/docs/menus/analyze.html, accessed April 2016.
    9. 9)
      • 38. Bourne, R.: ‘Ethnicity and ocular imaging’, Eye, 2010, 25, (3), pp. 297300.
    10. 10)
      • 5. Dutta, M.K., Mourya, A.K., Singh, A., et al: ‘Glaucoma detection by segmenting the super pixels from fundus colour retinal images’. 2014 Int. Conf. on Medical Imaging, m-Health and Emerging Communication Systems (MedCom), Greater Noida, 2014, pp. 8690.
    11. 11)
      • 35. ‘Colour Moments’. Available at http://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/AV0405/KEEN/av_as2_nkeen.pdf, accessed April 2016.
    12. 12)
      • 18. ‘Maths Work: Bwareaopen’. Available at http://www.mathworks.com/help/images/ref/bwareaopen.html, accessed February 2016.
    13. 13)
      • 7. Agarwal, A., Gulia, S., Chaudhary, S., et al: ‘Automatic glaucoma detection using adaptive threshold based technique in fundus image’. 38th Int. Conf. on Telecommunications and Signal Processing (TSP), Prague, 2015, pp. 416420.
    14. 14)
      • 25. ‘Microvascular Changes Might Predict Glaucoma’. Medpagetoday.com, http://www.medpagetoday.com/ophthalmology/glaucoma/36692, accessed March 2017.
    15. 15)
      • 1. ‘World Health Organization: Prevention of Blindness and Visual Impairment’. Available at http://www.who.int/blindness/causes/priority/en/, accessed April 2016.
    16. 16)
      • 3. ‘Review of Ophthalmology: How to Evaluate the Suspicious Optic Disc’. Available at http://www.reviewofophthalmology.com/content/d/cover_focus/i/1315/c/25316/, accessed December 2015.
    17. 17)
      • 37. Akram, M., Tariq, A., Khalid, S., et al: ‘Glaucoma detection using novel optic disc localization, hybrid feature set and classification techniques’, Australas. Phys. Eng. Sci. Med., 2015, 38, (4), pp. 643655.
    18. 18)
      • 17. ‘Morphological Image Processing’. Available at https://www.cs.auckland.ac.nz/courses/compsci773s1c/lectures/ImageProcessing-html/topic4.htm, accessed February 2016.
    19. 19)
      • 21. Spaeth, G.L., Lopes, F., Junk, A.K.: ‘Systems for staging the amount of optic nerve damage in glaucoma: a critical review and new material’, Surv. Ophthalmol., 2006, 51, (4), pp. 293315.
    20. 20)
      • 15. ‘Intensity Histogram’. Available at http://homepages.inf.ed.ac.uk/rbf/HIPR2/histgram.htm, accessed February 2016.
    21. 21)
      • 23. Lamani, D., Manjunath, T.C., Ramegowda, : ‘Fractal dimension with object rotation: a case study with glaucoma eye’. 2014 Fifth Int. Conf. on Signal and Image Processing, Jeju Island, 2014, pp. 111116.
    22. 22)
      • 8. Joshi, G.D., Sivaswamy, J., Krishnadas, S.R.: ‘Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment’, IEEE Trans. Med. Imaging, 2011, 30, (6), pp. 11921205.
    23. 23)
      • 4. Cheng, J., Yin, F., Wong, D.W. K., et al: ‘Sparse dissimilarity-constrained coding for glaucoma screening’, IEEE Trans. Biomed. Eng., 2015, 62, (5), pp. 13951403.
    24. 24)
      • 27. Akram, M., Khan, S.: ‘Multilayered thresholding-based blood vessel segmentation for screening of diabetic retinopathy’, Eng. Comput., 2012, 29, (2), pp. 165173.
    25. 25)
      • 12. Deepak, K., Jain, M., Joshi, G., et al: ‘Motion pattern-based image features for glaucoma detection from retinal images’. Proc. of the Eighth Indian Conf. on Computer Vision, Graphics and Image Processing – ICVGIP ’12, Mumbai, India, December 2012, article No. 47.
    26. 26)
      • 33. Chu, A., Sehgal, C., Greenleaf, J.: ‘Use of gray value distribution of run lengths for texture analysis’, Pattern Recognit. Lett., 1990, 11, (6), pp. 415419.
    27. 27)
      • 24. Costa, A.F., Humpire-Mamani, G., Traina, M.: ‘An efficient algorithm for fractal analysis of textures’. 25th SIBGRAPI Conf. on Graphics, Patterns and Images, Ouro Preto, 2012, pp. 3946.
    28. 28)
      • 10. Acharya, U., Ng, E., Eugene, L., et al: ‘Decision support system for the glaucoma using Gabor transformation’, Biomed. Signal Proc. Control, 2015, 15, pp. 1826.
    29. 29)
      • 36. Kotsiantis, S.B.: ‘Supervised machine learning: a review of classification techniques’, Informatica, 2007, 31, pp. 249268.
    30. 30)
      • 14. ‘MathWorks: Crop an Image’. Available at http://www.mathworks.com/help/images/ref/imcrop.html, accessed February 2016.
    31. 31)
      • 26. Ho, C.Y., Pai, T.W., Chang, H.T., et al: ‘An atomatic fundus image analysis system for clinical diagnosis of glaucoma’. 2011 Int. Conf. on Complex, Intelligent, and Software Intensive Systems, Seoul, 2011, pp. 559564.
    32. 32)
      • 9. Hatanaka, Y., Noudo, A., Muramatsu, C., et al: ‘Vertical cup-to-disk ratio measurement for diagnosis of glaucoma fundus images’. Proc. SPIE 7624, Medical Imaging 2010: Computer-Aided Diagnosis, 76243C, March 2010.
    33. 33)
      • 31. Galloway, M.: ‘Texture analysis using gray level run lengths’, Comput. Graph. Image Process., 1975, 4, (2), pp. 172179.
    34. 34)
      • 16. Willis, C.: ‘Glaucoma in optometric practice: a survey of optometrists’, Ophthalmic Physiol. Opt., 2000, 20, (1), pp. 7075.
    35. 35)
      • 6. Khan, F., Khan, S.A., Yasin, U.U., et al: ‘Detection of glaucoma using retinal fundus images’. The 6th 2013 Biomedical Engineering Int. Conf., Amphur Muang, 2013, pp. 15.
    36. 36)
      • 13. Bhatt, P., Patel, S., Shah, A., et al: ‘Image Enhancement Using Various Interpolation Methods’, Int. J. Comput. Sci. Inf. Technol. Secur., 2012, 2, (4), pp. 799803.
    37. 37)
      • 32. Xiaoou, T.: ‘Texture information in run-length matrices’, IEEE Trans. Image Process., 1998, 7, (11), pp. 16021609.
    38. 38)
      • 22. Rangayyan, R.M., Nguyen, T.M.: ‘Fractal analysis of contours of breast masses in mammograms’, J. Digit. Imaging, 2007, 20, (3), pp. 223237.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2016.0812
Loading

Related content

content/journals/10.1049/iet-ipr.2016.0812
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading