Advertisement

Novel Approaches for Diagnosing Melanoma Skin Lesions Through Supervised and Deep Learning Algorithms

  • J. Premaladha
  • K. S. RavichandranEmail author
Systems-Level Quality Improvement
Part of the following topical collections:
  1. Systems-Level Quality Improvement

Abstract

Dermoscopy is a technique used to capture the images of skin, and these images are useful to analyze the different types of skin diseases. Malignant melanoma is a kind of skin cancer whose severity even leads to death. Earlier detection of melanoma prevents death and the clinicians can treat the patients to increase the chances of survival. Only few machine learning algorithms are developed to detect the melanoma using its features. This paper proposes a Computer Aided Diagnosis (CAD) system which equips efficient algorithms to classify and predict the melanoma. Enhancement of the images are done using Contrast Limited Adaptive Histogram Equalization technique (CLAHE) and median filter. A new segmentation algorithm called Normalized Otsu’s Segmentation (NOS) is implemented to segment the affected skin lesion from the normal skin, which overcomes the problem of variable illumination. Fifteen features are derived and extracted from the segmented images are fed into the proposed classification techniques like Deep Learning based Neural Networks and Hybrid Adaboost-Support Vector Machine (SVM) algorithms. The proposed system is tested and validated with nearly 992 images (malignant & benign lesions) and it provides a high classification accuracy of 93 %. The proposed CAD system can assist the dermatologists to confirm the decision of the diagnosis and to avoid excisional biopsies.

Keywords

Preprocessing Segmentation Classification Artificial neural networks Support vector machine Deep learning Adaboost 

Notes

Acknowledgments

We, the authors sincerely thank the Department of Science and Technology, India for providing the INSPIRE fellowship (IF120649) to carry out this research work. Our earnest thanks to the SASTRA University for providing all the facilities to proceed with the research.

References

  1. 1.
    Green, A., Martin, N., Pfitzner, J., O’Rourke, M., and Knight, N., Computer image analysis in the diagnosis of melanoma. J. Am. Acad. Dermatol. 31(6):958–964, 1994.CrossRefPubMedGoogle Scholar
  2. 2.
    Lee, H. C., Skin cancer diagnosis using hierarchical neural networks and fuzzy logic. Department of Computer Science, University of Missouri, Rolla, 1994.Google Scholar
  3. 3.
    Aitken, J. F., Pfitzner, J., Battistutta, S. O., Rourke, P. K., Green, A. C., and Martin, N. G., Reliability of computer image analysis of pigmented skin lesions of Australian adolescents. J. Cancer 78(2):252–257, 1996.CrossRefGoogle Scholar
  4. 4.
    Chang, Y., Stanley, R. J., Moss, R. H., and Van Stoecker, W., A systematic heuristic approach for feature selection for melanoma discrimination using clinical images. Skin Res. Technol. 11(3):165–78, 2005.CrossRefPubMedPubMedCentralGoogle Scholar
  5. 5.
    She, Z., Liu, Y., and Damatoa, A., Combination of features from skin pattern and ABCD analysis for lesion classification. Skin Res. Technol. 13(1)25–33, 2007, which has been published in final form at http://onlinelibrary.wiley.com.
  6. 6.
    Fassihi, N., Shanbehzadeh. J., Sarafzadeh, A., and Ghasemi, E., Melanoma diagnosis by the use of wavelet analysis based on morphological operators. Proceedings of the International Multiconference of Engineers and Computer Scientists. 16–18, 2011.Google Scholar
  7. 7.
    Garnavi, R., Computer-aided diagnosis of melanoma. PhD thesis. 2011.Google Scholar
  8. 8.
    Garnavi, R., Aldeen, M., and Bailey, J., Computer-aided diagnosis of melanoma using border-and wavelet-based texture analysis. IEEE Trans. Inf. Technol. Biomed. 16(6):1239–1252, 2012.CrossRefPubMedGoogle Scholar
  9. 9.
    Amaliah, B., Fatichah, C., and Widyanto, M. R., ABCD feature extraction of image dermatoscopic based on morphology analysis for melanoma skin cancer diagnosis. J. Comput. Inf. 3(2):82–90, 2012.Google Scholar
  10. 10.
    Safi, A., Baust, M., Pauly, O., Castaneda, V., Lasser, T., Mateus, D., Navab, N., Hein, R., and Ziai, M., Computer–aided diagnosis of pigmented skin dermoscopic images. MCBR-CDS 2011, LNCS 7075, 105–115. Springer-Verlag Berlin Heidelberg. 2012.Google Scholar
  11. 11.
    Masood, A., and Al-Jumaily, A. A., Computer aided diagnostic support system for skin cancer: a review of techniques and algorithms. Int. J. Biomed. Imaging, 2013. doi: 10.1155/2013/323268.PubMedPubMedCentralGoogle Scholar
  12. 12.
    LeAnder, R., Chindam, P., Das, M., and Umbaugh, S. E., Differentiation of melanoma from benign mimics using the relative‐color method. Skin Res. Technol. 16(3):297–304, 2010.PubMedGoogle Scholar
  13. 13.
    Premaladha, J., and Ravichandran, K. S., Detection of melanoma skin lesions using phylogeny. Natl. Acad. Sci. Lett. 38(4):333–338, 2015.CrossRefGoogle Scholar
  14. 14.
    Premaladha, J., and Ravichandran, K. S., Quantification of fuzzy borders and fuzzy asymmetry of malignant melanomas. Proc. Natl. Acad. Sci. India Sect. A. Phys. Sci. 85(2):303–314, 2015.CrossRefGoogle Scholar
  15. 15.
    Shao, S., and Grams, R. R., A proposed computer diagnostic system for malignant melanoma (CDSMM). J. Med. Syst. 18(2):85–96, 1994.CrossRefPubMedGoogle Scholar
  16. 16.
    Mendonça, T., Ferreira, P. M., Marques, J., Marcal, A. R. S., and Rozeira, J., PH2 - A dermoscopic image database for research and benchmarking. 35th International Conference of the IEEE Engineering in Medicine and Biology Society: Osaka, Japan. 2013.Google Scholar
  17. 17.
    Giotis, I., Molders, N., Land, S., Biehl, M., Jonkman, M. F., and Petkov, N., MED-NODE: a computer-assisted melanoma diagnosis system using non-dermoscopic images. Expert Syst. Appl. 42:6578–6585, 2015.CrossRefGoogle Scholar
  18. 18.
    Premaladha, J., Sujitha, S., Lakshmi Priya, M., and Ravichandran, K. S., A survey on melanoma diagnosis using image processing and soft computing techniques. Res. J. Inf. Technol. 6(2):65–80, 2014.CrossRefGoogle Scholar
  19. 19.
    Celebi, M. E., Iyatomi, H., Stoecker, W. V., Moss, R. H., Rabinovitz, H. S., Argenziano, G., and Peter, H., Automatic detection of blue-white veil and related structures in dermoscopy images. Comput. Med. Imaging Graph. 32:670–677, 2008.CrossRefPubMedPubMedCentralGoogle Scholar
  20. 20.
    Schaefer, G., Rajab, M. I., Celebi, M. E., and Iyatomi, H., Colour and contrast enhancement for improved skin lesion segmentation. Comput. Med. Imaging Graph. 35:99–104, 2010.CrossRefPubMedGoogle Scholar
  21. 21.
    Capdehourat, G., Corez, A., Bazzano, A., Alonso, R., and Musé, P., Toward a combined tool to assist dermatologists in melanoma detection from dermoscopic images of pigmented skin lesions. Pattern Recogn. Lett. 32:2187–2196, 2004.CrossRefGoogle Scholar
  22. 22.
    Schmid-Saugeon, P., Guillod, J., and Thiran, J. P., Towards a computer-aided diagnosis system for pigmented skin lesions. Comput. Med. Imaging Graph. 65–78, 2003.Google Scholar
  23. 23.
    Messadi, M., Bessaid, A., and Taleb-Ahmed, A., Extraction of specific parameters for skin tumour classification. J. Med. Eng. Technol. 33(4):288–295, 2009.CrossRefPubMedPubMedCentralGoogle Scholar
  24. 24.
    Hance, G. A., Umbaugh, S. E., Moss, R. H., and Stoecker, W. H., Unsupervised color image segmentation. IEEE Eng. Med. Biol. 15(1):104–111, 1996. doi: 10.1109/51.482850.CrossRefGoogle Scholar
  25. 25.
    Celebi, M. E., Iyatomi, H., Schaefer, G., and Stoecker, W. V., Lesion border detection in dermoscopy images. Comput. Med. Imaging Graph. 33:148–153, 2009.CrossRefPubMedPubMedCentralGoogle Scholar
  26. 26.
    Bandyopadhyay, S. K., Preprocessing of mammogram images. Int. J. Eng. Sci. Technol. 2(11):6753–6758, 2010.Google Scholar
  27. 27.
    Rajab, M. I., Woolfson, M. S., and Morgan, S. P., Application of region-based segmentation and neural network edge detection to skin lesions. Comput. Med. Imaging Graph. 28:61–68, 2004.CrossRefPubMedGoogle Scholar
  28. 28.
    Palus, H., and Bogdanski, M., Clustering techniques in colour image segmentation. AI-METH Artif. Intell. Methods. 5–7, 2003.Google Scholar
  29. 29.
    Silveira M., Nascimento, J. C., Marques, J. S., Marçal, A. R. S., Mendonça, T., Yamauchi, S., Maeda, J., and Rozeira, J., Comparison of segmentation methods for melanoma diagnosis in dermoscopy images. IEEE J. Sel. Top. Sign. Process. 3(1), 2009.Google Scholar
  30. 30.
    Yuan, X., Situ, N., and Zouridakis, G., A narrow band graph partitioning method for skin lesion segmentation. Pattern Recogn. 42:1017–1028, 2009.CrossRefGoogle Scholar
  31. 31.
    Saripan, Azmi, and Abdullah, et al., Illumination compensation in pig skin texture using local-global block analysis. Mod. Appl. Sci. 3(2), 2009.Google Scholar
  32. 32.
    Cai, Yang, and Cao, et al., A new iterative triclass thresholding technique in image segmentation. IEEE Trans. Image Process. 23(3), 2014.Google Scholar
  33. 33.
    Erkol, B., Moss, R. H., Stanley, R. J., Stoecker, W. V., and Hvatum, E., Automatic lesion boundary detection in dermoscopy images using gradient vector flow snakes. Skin Res. Technol. 11(1):17–26, 2005.CrossRefPubMedPubMedCentralGoogle Scholar
  34. 34.
    Celebi, M. E., Hassan, A. K., Iyatomi, H., Lee, J. K., Aslandogan, Y. A., Stoecker, W. V., Moss, R., Joseph, M. M., and Marghoob, A. A. Fast and accurate border detection in dermoscopy images using statistical region merging. Med. Imaging. 65123V–65123V, 2007.Google Scholar
  35. 35.
    Celebi, M. E., Hwang, S., Hitoshi, I., and Schaefer, G. Robust border detection in dermoscopy images using threshold fusion. 17th IEEE International Conference on Image Processing (ICIP). 2541–2544, 2010.Google Scholar
  36. 36.
    Celebi, M. E., Kingravi, H. A., Iyatomi, H., Aslandogan, Y. A., Stoecker, W. V., Moss, R. H., Malters, J. M., Grichnik, J. M., Marghoob, A. A., Rabinovitz, H. S., and Menzies, S. W., Border detection in dermoscopy images using statistical region merging. Skin Res. Technol. 14(3):347–353, 2008.CrossRefPubMedPubMedCentralGoogle Scholar
  37. 37.
    Sikorski, J., Identification of malignant melanoma by wavelet analysis. Proceedings of Student/Faculty Research Day, Pace University. 2004.Google Scholar
  38. 38.
    Chiem, A., Al-Jumaily, A., and Khushaba, N. R., A novel hybrid system for skin lesion detection. Proceedings of the 3rd International Conference on Intelligent Sensors. Sensor Networks and Information Processing (ISSNIP’07). 567–572, 2007.Google Scholar
  39. 39.
    Maglogiannis, I., Zafiropoulos, E., and Kyranoudis, C., Intelligent segmentation and classification of pigmented skin lesions in dermatological images. In: Advances in artificial intelligence. Springer, Berlin, pp. 214–223, 2006.CrossRefGoogle Scholar
  40. 40.
    Tanaka, T., Torii, S., Kabuta, I., Shimizu, K., Tanaka, M., and Oka, H., Pattern classification of nevus with texture analysis. Proceedings of the 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’04). 1459–1462, 2004.Google Scholar
  41. 41.
    Zhou, H., Chen, M., and Rehg, J. M., Dermoscopic interest point detector and descriptor. Proceedings of the 6th IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI’09). 1318–1321, 2009.Google Scholar
  42. 42.
    Lee, C., and Landgrebe, D. A., Feature extraction based on decision boundaries. IEEE Trans. Pattern Anal. Mach. Intell. 15(4):388–400, 1993.CrossRefGoogle Scholar
  43. 43.
    Anuradha, K., and Sankaranarayanan, K., Statistical Feature extraction to classify oral cancers. J. Glob. Res. Comput. Sci. 4(2):8–12, 2013.Google Scholar
  44. 44.
    Duda, R., Hart, P., and Stork, D., Pattern classification, 2nd edition. Wiley, New York, 2001.Google Scholar
  45. 45.
    Vanitha, L., and Venmathi, A. R., Classification of medical images using support vector machines. Int. Conf. Inf. Netw. Topol. 4, 2011.Google Scholar
  46. 46.
    Lau, H. T., and Al-Jumaily, A., Automatically early detection of skin cancer: study based on neural network classification. Int. Conf. Soft Comput. Pattern Recognit. 375–380, 2009.Google Scholar
  47. 47.
    Kilic, N., and Hosgormez, E., Automatic estimation of osteoporotic fracture cases by using ensemble learning approaches. J. Med. Syst. 40(3):61, 2016. doi: 10.1007/s10916-015-0413-1. Epub 2015 Dec 12.CrossRefPubMedGoogle Scholar
  48. 48.
    Mandal, I., and Sairam, N., Accurate prediction of coronary artery disease using reliable diagnosis system. J. Med. Syst. 36(5):3353–3373, 2012.CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.School of ComputingSASTRA UniversityThanjavurIndia

Personalised recommendations