access icon free Fusion of structural and textural features for melanoma recognition

Melanoma is one the most increasing cancers since past decades. For accurate detection and classification, discriminative features are required to distinguish between benign and malignant cases. In this study, the authors introduce a fusion of structural and textural features from two descriptors. The structural features are extracted from wavelet and curvelet transforms, whereas the textural features are extracted from different variants of local binary pattern operator. The proposed method is implemented on 200 images from dermoscopy database including 160 non-melanoma and 40 melanoma images, where a rigorous statistical analysis for the database is performed. Using support vector machine (SVM) classifier with random sampling cross-validation method between the three cases of skin lesions given in the database, the validated results showed a very encouraging performance with a sensitivity of 78.93%, a specificity of 93.25% and an accuracy of 86.07%. The proposed approach outperforms the existing methods on the database.

Inspec keywords: image recognition; wavelet transforms; cancer; feature extraction; support vector machines; image fusion; medical image processing

Other keywords: local binary pattern operator; cancers; SVM classifier; dermoscopy; textural features; support vector machine; structural features; melanoma recognition

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

References

    1. 1)
      • 17. Celebi, M.E., Iyatomi, H., Schaefer, G., et al: ‘Lesion border detection in dermoscopy images’, Comput. Med. Imaging Graph., 2009, 33, (2), pp. 148153.
    2. 2)
      • 7. Celebi, M.E., Wen, Q., Iyatomi, H., et al: ‘A state-of-the-art survey on lesion border detection in dermoscopy images’ (CRC Press, Boca Raton, 2015).
    3. 3)
      • 18. 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. 362373.
    4. 4)
      • 20. Safi, A., Baust, M., Pauly, O., et al: ‘Computer-aided diagnosis of pigmented skin dermoscopic images’. MICCAI Int. Workshop on Medical Content-Based Retrieval for Clinical Decision Support, 2011, pp. 105115.
    5. 5)
      • 44. Adjed, F., Faye, I., Ababsa, F., et al: ‘Classification of skin cancer images using local binary pattern and SVM classifier’. AIP Conf. Proc., 2016, vol. 1787, p. 080006.
    6. 6)
      • 23. Adjed, F., Faye, I., Ababsa, F.: ‘Segmentation of skin cancer images using an extension of chan and vese model’. 2015 Seventh Int. Conf. Information Technology and Electrical Engineering (ICITEE), 2015, pp. 442447.
    7. 7)
      • 14. Koehoorn, J., Sobiecki, A.C., Boda, D., et al: ‘Automated digital hair removal by threshold decomposition and morphological analysis’. Int. Symp. Mathematical Morphology and its Applications to Signal and Image Processing, 2015, pp. 1526.
    8. 8)
      • 15. Mirzaalian, H., Lee, T.K., Hamarneh, G.: ‘Hair enhancement in dermoscopic images using dual-channel quaternion tubularness filters and MRF-based multilabel optimization’, IEEE Trans. Image Process., 2014, 23, (12), pp. 54865496.
    9. 9)
      • 36. Ahonen, T., Hadid, A., Pietikäinen, M.: ‘Face description with local binary patterns: application to face recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (12), pp. 20372041.
    10. 10)
      • 6. Korotkov, K., Garcia, R.: ‘Computerized analysis of pigmented skin lesions: a review’, Artif. Intell. Med., 2012, 56, (2), pp. 6990.
    11. 11)
      • 25. Abuzaghleh, O., Barkana, B.D., Faezipour, M.: ‘Automated skin lesion analysis based on color and shape geometry feature set for melanoma early detection and prevention’. 2014 IEEE Long Island Systems, Applications and Technology Conf. (LISAT), 2014, pp. 16.
    12. 12)
      • 11. Argenziano, G., Fabbrocini, G., Carli, P., et al: ‘Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions: comparison of the ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis’, Arch. Dermatol., 1998, 134, (12), pp. 15631570.
    13. 13)
      • 50. Celebi, M.E., Mendonca, T., Marques, J.S.: ‘Dermoscopy image analysis’, vol. 10 (CRC Press, 2015).
    14. 14)
      • 47. Dolianitis, C., Kelly, J., Wolfe, R., et al: ‘Comparative performance of 4 dermoscopic algorithms by nonexperts for the diagnosis of melanocytic lesions’, Arch. Dermatol., 2005, 141, (8), pp. 10081014.
    15. 15)
      • 12. Abbas, Q., Garcia, I.F., Emre Celebi, M., et al: ‘A feature-preserving hair removal algorithm for dermoscopy images’, Skin Res. Technol., 2013, 19, (1), pp. e27e36.
    16. 16)
      • 30. Mallat, S.G.: ‘A theory for multiresolution signal decomposition: the wavelet representation’, IEEE Trans. Pattern Anal. Mach. Intell., 1989, 11, (7), pp. 674693.
    17. 17)
      • 42. Wolf, L., Hassner, T., Taigman, Y.: ‘Descriptor based methods in the wild’. Workshop on Faces in ‘Real life’ images: Detection, Alignment, and Recognition, 2008.
    18. 18)
      • 32. Candes, E., Demanet, L., Donoho, D., et al: ‘Fast discrete curvelet transforms’, Multiscale Model. Simul., 2006, 5, (3), pp. 861899.
    19. 19)
      • 43. Pietikäinen, M., Hadid, A., Zhao, G., et al: ‘Computer vision using local binary patterns’, vol. 40 (Springer Science & Business Media, 2011).
    20. 20)
      • 27. Codella, N., Cai, J., Abedini, M., et al: ‘Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images’. Int. Workshop on Machine Learning in Medical Imaging, 2015, pp. 118126.
    21. 21)
      • 2. ©Les cancer en France en 2013: ‘Collection état des lieux et des connaissances, ouvrage collectif édité par l'inca’, January 2014. Available at http://www.e-cancer.fr/Expertises-et-publications/Catalogue-des-publications/Les-cancers-en-France-Edition-2013.
    22. 22)
      • 49. Li, S., Yang, B.: ‘Multifocus image fusion by combining curvelet and wavelet transform’, Pattern Recognit. Lett., 2008, 29, (9), pp. 12951301.
    23. 23)
      • 29. Grossmann, A., Morlet, J.: ‘Decomposition of hardy functions into square integrable wavelets of constant shape’, SIAM J. Math. Anal., 1984, 15, (4), pp. 723736.
    24. 24)
      • 5. Cancer Research UK: ‘Treating skin cancer’, 2016. Available at http://www.cancerresearchuk.org/about-cancer/type/skin-cancer/treatment/, accessed on 14 October 2016.
    25. 25)
      • 37. Porebski, A., Vandenbroucke, N., Macaire, L.: ‘Haralick feature extraction from LBP images for color texture classification’. 2008 First Workshops on Image Processing Theory, Tools and Applications, 2008, pp. 18.
    26. 26)
      • 35. Alzubi, S., Islam, N., Abbod, M.: ‘Multiresolution analysis using wavelet, ridgelet, and curvelet transforms for medical image segmentation’, J. Biomed. Imaging, 2011, 2011, p. 4.
    27. 27)
      • 22. Chan, T.F., Vese, L.A.: ‘Active contours without edges’, IEEE Trans. Image Process., 2001, 10, (2), pp. 266277.
    28. 28)
      • 4. Arroyo, J.L.G., Zapirain, B.G.: ‘Detection of pigment network in dermoscopy images using supervised machine learning and structural analysis’, Comput. Biol. Med., 2014, 44, pp. 144157.
    29. 29)
      • 24. Clawson, K.M., Morrow, P., Scotney, B., et al: ‘Analysis of pigmented skin lesion border irregularity using the harmonic wavelet transform’. 13th Int. Machine Vision and Image Processing Conf. 2009 IMVIP'09, 2009, pp. 1823.
    30. 30)
      • 19. Capdehourat, G., Corez, A., Bazzano, A., et al: ‘Toward a combined tool to assist dermatologists in melanoma detection from dermoscopic images of pigmented skin lesions’, Pattern Recognit. Lett., 2011, 32, (16), pp. 21872196.
    31. 31)
      • 39. Ojala, T., Pietikainen, M., Maenpaa, T.: ‘Multiresolution gray-scale and rotation invariant texture classification with local binary patterns’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (7), pp. 971987.
    32. 32)
      • 46. Mendonça, T.F., Ferreira, M.P., Marcal, A.R.S., et al: ‘PH2: a public database for the analysis of dermoscopic images’, in Celebi, M.E., Mendonca, T., Marques, J.S. (EDs.): ‘Dermoscopy image analysis’ (CRC Press, 2015, vol. 10), pp. 419439.
    33. 33)
      • 9. Barata, C., Ruela, M., Francisco, M., et al: ‘Two systems for the detection of melanomas in dermoscopy images using texture and color features’, IEEE Syst. J., 2014, 8, (3), pp. 965979.
    34. 34)
      • 40. Heikkilä, M., Pietikäinen, M., Schmid, C.: ‘Description of interest regions with center-symmetric local binary patterns’. ICVGIP, 2006, vol. 6, pp. 5869.
    35. 35)
      • 48. Fadili, J.M., Starck, J.L.: ‘Curvelets and ridgelets’ (Springer New York, 2009).
    36. 36)
      • 16. Frangi, A.F., Niessen, W.J., Vincken, K.L., et al: ‘Multiscale vessel enhancement filtering’. Int. Conf. Medical Image Computing and Computer-Assisted Intervention, 1998, pp. 130137.
    37. 37)
      • 51. Database, I.A.: ‘ISIC archive: international skin imaging collaboration’, accessed on 27 February 2017.
    38. 38)
      • 10. Stolz, W., Riemann, A., Cognetta, A., et al: ‘ABCD rule of dermatoscopy-a new practical method for early recognition of malignant melanoma’, Eur. J. Dermatol., 1994, 4, (7), pp. 521527.
    39. 39)
      • 38. Ojala, T., Valkealahti, K., Oja, E., et al: ‘Texture discrimination with multidimensional distributions of signed gray-level differences’, Pattern Recognit., 2001, 34, (3), pp. 727739.
    40. 40)
      • 34. Gardezi, S., Faye, I.: ‘Fusion of completed local binary pattern features with curvelet features for mammogram classification’, Appl. Math. Inf. Sci., 2015, 9, (6), pp. 30373048.
    41. 41)
      • 28. Barata, C., Celebi, M.E., Marques, J.S.: ‘Improving dermoscopy image classification using color constancy’, IEEE J. Biomed. Health Inf., 2015, 19, (3), pp. 11461152.
    42. 42)
      • 3. Fundation, S.C.: ‘Skin cancer information’, 2016. Available at, http://www.skincancer.org/skin-cancer-information, accessed on 20 August 2016.
    43. 43)
      • 1. World Health Organization: ‘How common is skin cancer?’, 2015. Available at, http://www.who.int/uv/faq/skincancer/en/index1.html, accessed on 18 August 2016.
    44. 44)
      • 31. Candes, E.J., Donoho, D.L.: ‘Curvelets: a surprisingly effective nonadaptive representation for objects with edges’ (Stanford University, Department of Statistics, 2000).
    45. 45)
      • 8. Lee, T., Ng, V., Gallagher, R., et al: ‘Dullrazor: a software approach to hair removal from images’, Comput. Biol. Med., 1997, 27, (6), pp. 533543.
    46. 46)
      • 33. Mandal, T., Majumdar, A., Wu, Q.J.: ‘Face recognition by curvelet based feature extraction’. Int. Conf. Image Analysis and Recognition, 2007, pp. 806817.
    47. 47)
      • 26. Maglogiannis, I., Doukas, C.N.: ‘Overview of advanced computer vision systems for skin lesions characterization’, IEEE Trans. Inf. Technol. Biomed., 2009, 13, (5), pp. 721733.
    48. 48)
      • 41. Zhang, L., Chu, R., Xiang, S., et al: ‘Face detection based on multi-block LBP representation’. Advances in biometrics, 2007, pp. 1118.
    49. 49)
      • 45. Mendonca, T., Ferreira, P.M., Marques, J.S., et al: ‘PH2 – a dermoscopic image database for research and benchmarking’. 2013 35th Annual Int. Conf. the IEEE Engineering in Medicine and Biology Society (EMBC), 2013, pp. 54375440.
    50. 50)
      • 13. Barata, C., Marques, J.S., Rozeira, J.: ‘A system for the detection of pigment network in dermoscopy images using directional filters’, IEEE Trans. Biomed. Eng., 2012, 59, (10), pp. 27442754.
    51. 51)
      • 21. Li, F., Shen, C., Li, C.: ‘Multiphase soft segmentation with total variation and h1 regularization’, J. Math. Imaging Vis., 2010, 37, (2), pp. 98111.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2017.0193
Loading

Related content

content/journals/10.1049/iet-cvi.2017.0193
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading