This study presents an efficient disease classification approach based on medical images. The approach is more efficient as it reduces the computational complexity. The implementation uses only two wavelet filters in selecting the texture features as compared with five filters used in the earlier research works. The computed average and energy features are fed to feed-forward neural network (FFNN) and support vector machine (SVM) classifiers. The SVM is proved as a better classifier than the FFNN for all the three diseases related to skin, breast and retina with an improved accuracies of 89%, 92% and 100%, respectively. Also, a graphical user interface is developed useful for various disease classification based on the whole dataset of size 100.

References

1. 1)
  - 16. Goppner, D., Muller, J., Kruger, S., et al: ‘High incidence of naevi-associated BRAF wild-type melanomaand dysplastic naevi under treatment with the class I BRAF inhibitor vemurafenib’, Acta Derm. Venereol., 2014, 94, (5), pp. 517–520 (doi: 10.2340/00015555-1813).
2. 2)
  - 23. Jamarani, S.M.H., Rezai-rad, G., Behnam, H.: ‘A novel method for breast cancer prognosis using wavelet packet based neural network’. Proc. 27th Annual Int. Conf. of the Engineering in Medicine and Biology Society (IEEE-EMBS ‘05), Shanghai, China, September 2005, pp. 3414–3417.
3. 3)
  - 21. ‘Clinical Dermatology’. Available at http://www.danderm-pdv.is.kkh.dk/atlas/index.html, accessed 12 November 2015.
4. 4)
  - 25. Polyak, N., Pearlman, W.A.: ‘A new flexible biorthogonal filter design for multiresolution filterbanks with application to image compression’, IEEE Trans. Signal Process., 2000, 48, (8), pp. 2279–2288 (doi: 10.1109/78.852009).
5. 5)
  - 6. Tirtajaya, A., Santika, D.: ‘Classification of microcalcificationusing dual-tree complex wavelet transform and support vector machine’. Proc. of the 2nd Int. Conf. on Advances in Computing, Control and Telecommunication Technologies (ACT ‘10), Jakarta, Indonesia, December 2010, pp. 164–166.
6. 6)
  - 20. ‘Structured Analysis of the Retina’. Available at http://www.ces.clemson.edu/ahoover/stare/, accessed 1 February 2016.
7. 7)
  - 10. Summeet, D., Rajendra Acharya, U., Chowriappa, P., et al: ‘Wavelet-based energy features for glucomatous image classification’, IEEE Trans. Inf. Technol. Biomed., 2012, 16, (2), pp. 121–142.
8. 8)
  - 31. Celebi, M.E., Iyatomi, H., Schaefer, G., et al: ‘Lesion border detection in dermoscopy images’, Comput. Med. Imaging Graph, 2009, 33, (2), pp. 148–153 (doi: 10.1016/j.compmedimag.2008.11.002).
9. 9)
  - 5. Dong, A., Wang, B.: ‘Feature selection and analysis on mammogram classification’. Proc. IEEE PacificRim Conf. on Communications, Computers and Signal Processing (PACRIM ‘09), Victoria, BC, Canada, August 2009, pp. 731–735.
10. 10)
  - 1. Verma, B., Zakos, J.: ‘A computer-aided diagnosis system for digital mammograms based on fuzzy-neural and feature extraction techniques’, IEEE Trans. Inf. Technol. Biomed., 2001, 5, (1), pp. 46–54 (doi: 10.1109/4233.908389).
11. 11)
  - 4. Abbas, Q., Celebi, M.E., Garcıa, I.F.: ‘Skin tumor area extractionusing an improved dynamic programming approach’, Skin Res. Technol., 2012, 18, (1), pp. 133–142 (doi: 10.1111/j.1600-0846.2011.00544.x).
12. 12)
  - 13. Acharya, U.R., Dua, S., Du, X., et al: ‘Automated diagnosis of glaucoma using texture and higher order spectra features’, IEEE Trans. Inf. Technol. Biomed., 2011, 15, (3), pp. 449–455 (doi: 10.1109/TITB.2011.2119322).
13. 13)
  - 18. ‘Digital Mammography’. Available at http://marathon.csee.usf.edu/Mammography/Database.html, accessed 15 November 2015.
14. 14)
  - 15. Manousaki, G., Manios, A.G., Tsompanaki, E.I., et al: ‘A simple digital image processing system to aid in melanoma diagnosis in an everyday melanocytic skin lesion unit: a preliminary report’, Int. J. Dermatol., 2006, 45, (3), pp. 402–410 (doi: 10.1111/j.1365-4632.2006.02726.x).
15. 15)
  - 7. Moayedi, F., Azimifar, Z., Boostani, R., et al: ‘Contourlet-based mammography mass classification using the SVMfamily’, Comput. Biol. Med., 2010, 40, (4), pp. 373–383 (doi: 10.1016/j.compbiomed.2009.12.006).
16. 16)
  - 22. ‘The dermatology resource’. Available at http://www.dermnetnz.org/, accessed 25 October 2015.
17. 17)
  - 11. Weiss, S., Kulikowski, C.A., Saﬂr, A.: ‘Glaucoma consultation by computer’, Comput. Biol. Med., 1998, 8, (1), pp. 24–40.
18. 18)
  - 19. ‘DataBase’. Available at http://www.isi.uu.nl/Research/Databases/DRIVE/download.php, accessed 31 January 2016.
19. 19)
  - 12. Weiss, S., , Kulikowski, C.A., , Amarel, S.: ‘A model-based method for computer-aided medical decision-making’, Artif. Intell., 1978, 11, (2), pp. 145–172 (doi: 10.1016/0004-3702(78)90015-2).
20. 20)
  - 8. Maglogiannis, I., Doukas, C.: ‘Overview of advanced computer vision systems for skin lesions characterization’, IEEE Trans. Inf. Technol. Biomed., 2009, 13, (5), pp. 721–733 (doi: 10.1109/TITB.2009.2017529).
21. 21)
  - 8. Khademi, A., Krishnan, S.: ‘Shift-invariant discrete wavelet transform analysis for retinal image classification’, Med. Biol. Eng. Comput., 2007, 45, (12), pp. 1211–1222 (doi: 10.1007/s11517-007-0273-z).
22. 22)
  - 24. Simon, N., Hymavathy, K.P.: ‘Early stage glaucoma screening and segmentation using FFNN’, Int. J. Eng. Res. Technol., 2015, 4, (4), pp. 17–28.
23. 23)
  - 2. Korotkov, K., Garcia, R.: ‘Computerized analysis of pigmented skin lesions: a review’, Artif. Intell. Med., 2012, 56, (2), pp. 69–90 (doi: 10.1016/j.artmed.2012.08.002).
24. 24)
  - 14. Maglogiannis, I.G., Zafiropoulos, E.P.: ‘Characterization of digital medical images utilizing support vector machines’, BMC Med. Inf. Decis. Mak., 2004, 4, (2), pp. 1–8.
25. 25)
  - 9. Lee, N., Laine, A.F., Smith, T.R.: ‘Learning non-homogenous textures and the unlearning problem with application to drusen detection in retinal images’. Proc. fifth IEEE Int. Symp. on Biomedical Imaging: From Nano toMacro (ISBI ‘08), Paris, France, May 2008, pp. 1215–1218.

Classification of multiple diseases based on wavelet features

References

Related content