Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free WN-based approach to melanoma diagnosis from dermoscopy images

© The Institution of Engineering and Technology
Received 03/09/2016, Accepted 19/03/2017, Revised 27/01/2017, Published 23/03/2017

A new computer-aided diagnosis (CAD) system for detecting malignant melanoma from dermoscopy images based on a fixed grid wavelet network (FGWN) is proposed. This novel approach is unique in at least three ways: (i) the FGWN is a fixed WN which does not require gradient-type algorithms for its construction, (ii) the construction of FGWN is based on a new regressor selection technique: D-optimality orthogonal matching pursuit (DOOMP), and (iii) the entire CAD system relies on the proposed FGWN. These characteristics enhance the integrity and reliability of the results obtained from different stages of automatic melanoma diagnosis. The DOOMP algorithm optimises the network model approximation ability rapidly while improving the model adequacy and robustness. This FGWN is then used to build a CAD system, which performs image enhancement, segmentation, and classification. To classify the images, in the first stage, 441 features with respect to colour, texture, and shape of each lesion are extracted. By means of feature selection, these 441 features are then reduced to 10. The proposed CAD system achieved an accuracy of 91.82%, sensitivity of 92.61%, specificity of 91%, and area under the curve value of 0.944 on a challenging set of 1039 dermoscopy images.

Inspec keywords: cancer; tumours; regression analysis; image enhancement; image matching; medical image processing; feature extraction; feature selection; image classification; image colour analysis; biomedical optical imaging; image segmentation; wavelet neural nets; skin; image texture

Other keywords: regressor selection; D-optimality orthogonal matching pursuit; FGWN; area under-the-curve value; automatic melanoma diagnosis; image segmentation; dermoscopy images; feature selection; lesion shape; image enhancement; feature extraction; colour; texture; image classification; malignant melanoma; fixed grid wavelet network; network model approximation; melanoma diagnosis; computer-aided diagnosis system; WN-based approach; CAD system

Subjects: Patient diagnostic methods and instrumentation; Biology and medical computing; Optical and laser radiation (medical uses); Computer vision and image processing techniques; Image recognition; Optical and laser radiation (biomedical imaging/measurement); Data handling techniques; Other topics in statistics; Probability theory, stochastic processes, and statistics; Other topics in statistics

References

    1. 1)
      • 24. Huan, L., Setiono, R.: ‘Chi2: feature selection and discretization of numeric attributes’. Proc. Seventh Int. Conf. Tools with Artificial Intelligence, Washington, DC, USA, November 1995, pp. 388–391.
    2. 2)
      • 8. Iyatomi, H., Oka, H., Saito, M., et al: ‘Quantitative assessment of tumour extraction from dermoscopy images and evaluation of computer-based extraction methods for an automatic melanoma diagnostic system’, Melanoma Res., 2006, 16, (2), pp. 183–190.
    3. 3)
      • 25. Arizona State University: ‘Advancing feature selection research-ASU feature selection repository’ (Arizona State University, Glendale, AZ, USA, 2010), pp. 1–28.
    4. 4)
      • 23. Peng, H., Long, F., Ding, C.: ‘Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (8), pp. 1226–1238.
    5. 5)
      • 9. Ballerini, L., Xiang, L., Fisher, R.B., et al: ‘A query-by-example content-based image retrieval system of non-melanoma skin lesions’. Proc. MICCAI-09 Workshop MCBR-CDS 2009: Medical Content based Retrieval for Clinical Decision Support, 2010 (LNCS, 5853), pp. 31–38.
    6. 6)
      • 6. Garnavi, R., Aldeen, M., Bailey, J.: ‘Computer-aided diagnosis of melanoma using border and wavelet-based texture analysis’, IEEE Trans. Inf. Technol. Biomed., 2012, 16, (6), pp. 1239–1252.
    7. 7)
      • 13. Xu, J., Ho, D.W.C.: ‘A basis selection algorithm for wavelet neural networks’, Neurocomputing, 2002, 48, (1), pp. 681–689.
    8. 8)
      • 28. Zhang, Q., Benveniste, A.: ‘Wavelet networks’, IEEE Trans. Neural Netw., 1992, 3, (6), pp. 889–898.
    9. 9)
      • 17. Sadri, A.R., Zekri, M., Sadri, S., et al: ‘Impulse noise cancellation of medical images using wavelet networks and median filters’, J. Med. Signals Sens., 2012, 2, (1), pp. 25–37.
    10. 10)
      • 16. Zhang, Q.: ‘Using wavelet network in nonparametric estimation’, IEEE Trans. Neural Netw., 1997, 8, (2), pp. 227–236.
    11. 11)
      • 5. Wighton, P., Lee, T.K., Lui, H., et al: ‘Generalizing common tasks in automated skin lesion diagnosis’, IEEE Trans. Inf. Technol. Biomed., 2011, 15, (4), pp. 622–629.
    12. 12)
      • 21. Yu, L., Liu, H.: ‘Feature selection for high-dimensional data: a fast correlation-based filter solution’. Proc. 20th Int. Conf. Machine Learning, Washington, DC, USA, August 2003, pp. 856–863.
    13. 13)
      • 15. Kira, K., Rendell, L.A.: ‘A practical approach to feature selection’. Proc. Ninth Int. Workshop Machine Learning, Aberdeen, Scotland, UK, July 1992, pp. 249–256.
    14. 14)
      • 4. Sadri, A.R., Zekri, M., Sadri, S., et al: ‘Segmentation of dermoscopy images using wavelet networks’, IEEE Trans. Biomed. Eng., 2013, 60, (4), pp. 1134–1141.
    15. 15)
      • 26. Huang, K., Aviyente, S.: ‘Wavelet feature selection for image classification’, IEEE Trans. Image Process., 2008, 17, (9), pp. 1709–1720.
    16. 16)
      • 7. Ganster, H., Pinz, A., Rohrer, R., et al: ‘Automated melanoma recognition’, IEEE Trans. Med. Imaging, 2001, 20, (3), pp. 233–239.
    17. 17)
      • 18. Lee, T., Ng, V., Gallagher, R., et al: ‘Dullrazor®: a software approach to hair removal from images’, Comput. Biol. Med., 1997, 27, (6), pp. 533–543.
    18. 18)
      • 3. Gonzalez-Castro, V., Debayle, J., Wazaefi, Y., et al: ‘Automatic classification of skin lesions using color mathematical morphology-based texture descriptors’. Proc. Int. Conf. Quality Control by Artificial Vision, Le Creusot, France, June 2015.
    19. 19)
      • 11. Billings, S.A., Hua-Liang, W.: ‘A new class of wavelet networks for nonlinear system identification’, IEEE Trans. Neural Netw., 2005, 16, (4), pp. 862–874.
    20. 20)
      • 12. Hosseinabadi, H.Z., Nazari, B., Amirfattahi, R., et al: ‘Wavelet network approach for structural damage identification using guided ultrasonic waves’, IEEE Trans. Instrum. Meas., 2014, 63, (7), pp. 1680–1692.
    21. 21)
      • 22. Duda, R., Hart, P., Stork, D.: ‘Pattern classification’ (John Wiley & Sons, New York, 2001, 2nd edn.), 2012.
    22. 22)
      • 19. Celebi, M.E., Kingravi, H.A., Uddin, B., et al: ‘A methodological approach to the classification of dermoscopy images’, Comput. Med. Imaging Graph., 2007, 31, (6), pp. 362–373.
    23. 23)
      • 14. Hong, X., Harris, C.J.: ‘Nonlinear model structure design and construction using orthogonal least squares and D-optimality design’, IEEE Trans. Neural Netw., 2002, 13, (5), pp. 1245–1250.
    24. 24)
      • 20. Huang, J., Kumar, S.R., Mitra, M., et al: ‘Image indexing using color correlograms’. Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, San Juan, Puerto Rico, June 1997, pp. 762–768.
    25. 25)
      • 1. Kasmi, R., Mokrani, K.: ‘Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule’, IET Image Process., 2016, 10, (6), pp. 448–455.
    26. 26)
      • 10. González-Castro, V., Debayle, J., Wazaefi, Y., et al: ‘Texture descriptors based on adaptive neighborhoods for classification of pigmented skin lesions’, J. Electron. Imaging, 2015, 24, (6), p. 061104.
    27. 27)
      • 27. Kohavi, R.: ‘A study of cross-validation and bootstrap for accuracy estimation and model selection’. Proc. 14th Int. Conf. Tools with Artificial Intelligence, Montreal, Quebec, Canada, August 1995, pp. 1137–1145.
    28. 28)
      • 2. Xiang, L., Aldridge, B., Fisher, R., et al: ‘Estimating the ground truth from multiple individual segmentations incorporating prior pattern analysis with application to skin lesion segmentation’. Proc. Eighth Int. Symp. on Biomedical Imaging (ISBI.11), Electronic Proc., April 2011, pp. 1438–1441.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2016.0681
Loading

Related content

content/journals/10.1049/iet-ipr.2016.0681
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address