NON-INVASIVE MELANOMA DIAGNOSIS USING MULTISPECTRAL IMAGING

Ianisse Quinzán Suárez, Pedro Latorre Carmona, Pedro García Sevilla, Enrique Boldo, Filiberto Pla, Vicente García Jiménez, Rafael Lozoya, Guillermo Pérez de Lucía

2012

Abstract

The early analysis of pigmented skin lesions is important for clinicians in order to recognize malignant melanoma. However, it is difficult to differentiate it from benign skin lesions due to their similarity based on their appearance. Since melanoma has a tendency to grow inside the skin and the depth of penetration of light into the skin is wavelength dependent, a multispectral imaging acquisition and processing approach to classify pigmented lesions as melanoma seems appropriate. This paper presents a method to diagnose melanoma lesions over a group of 26 samples acquired with a multispectral system, where 6 of them are melanomas, and the other 20 are other types of pigmented lesions. A Leave-One-Out strategy is used to create the training/test set. The classification imbalance problem inherent to this dataset is alleviated using a SMOTE technique. The random component of the SMOTE methodology is dealt with running it 25 times and a Qualified Majority Voting (QMV) scheme is used to do the final classification, using SVM. Results show this strategy allows to obtain competitive classification quality results.

References

  1. Abbasi, N. R., Shaw, H. M., and Riegel, D. S. (2004). Early diagnosis of cutaneous melanoma: revisiting the abcd criteria. Journal of the American Medical Association, 292:2771-2776.
  2. Batista, G. E. A. P. A., Prati, R. C., and Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explorations Newsletter, 6(1):20-29.
  3. Binder, M., Kittler, H., Seeber, A., SteinerA, A., Pehamberger, H., and Wolff, K. (1998). Epiluminiscence microscopy-based classification of pigmented skin lesions using computerized image analysis and an artificial neuronal network. Melanoma Research, 8(3):261-266.
  4. Carrara, M., Tomatis, S., Bono, A., Bartoli, C., Moglia, D., Lualdi, M., Colombo, A., Santinami, M., and Marchesini, R. (2005). Automated segmentation of pigmented skin lesions in multispectral imaging. Physics in Medicine and Biology, 50:345-357.
  5. Chang, C. I., Q. Du, T. L. S., and Althouse, M. L. G. (1999). A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification. IEEE Trans. Geosc. Remote Sens., 37(6):2631-2641.
  6. Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority oversampling technique. J. Artif. Intell. Res., 16:321-357.
  7. Cheng, Y., Swamisai, R., Umbaugh, S. E., Moss, R. H., Stoecker, W. V., Teegala, S., and Srinivasan, S. K. (2008). Skin lesion classification using relative color features. Skin Research and Technology, 14:53-64.
  8. Deshabhoina, S. V., Umbaugh, S. E., Stoecker, W. V., Moss, R. H., and Srinivasan, S. K. (2003). Melanoma and seborrheic queratosis differentiation using texture features. Melanoma Research, 9(4):348-356.
  9. Dhawan, A. P., D'Alessandro, B., Patwardhan, S., and Mullani, N. (2005). An over-sampling expert system for learing from imbalanced data sets. In Proc. of the International Conference on Neural Networks and Brain (ICNN & B 7805), volume 1, pages 537-541.
  10. Diebele, I., Kuzmina, I., Kapostinsh, J., Derjabo, A., and Spigulis, J. (2011). Melanoma-nevus differentiation by multispectral imaging. In Proc. of SPIE-OSA Biomedical Optics, volume 8087, pages 80872G1- 80872G6.
  11. ECO (2011). Cancer: Melanoma of skin. In European Cancer Observatory http://eu-cancer.iarc.fr/cancer11-melanoma-of-skin.html,en.
  12. Fernández, A., García, S., and Herrera, F. (2011). Addressing the classification with imbalanced data: Open problems and new challenges on class distribution. In Corchado, E., Kurzynski, M., and Wozniak, M., editors, Hybrid Artificial Intelligent Systems, volume 6678 of Lecture Notes in Computer Science, pages 1- 10.
  13. Friedman, R. J., Rigel, D. S., and Kopf, A. W. (1985). Early detection of malignant melanoma: the role of physician examination and self-examination of skin. CA: A Cancer Journal for Clinicians, 35:130-151.
  14. He, G., Han, H., and Wang, W. (2005). An over-sampling expert system for learing from imbalanced data sets. In Proc. of the International Conference on Neural Networks and Brain (ICNN & B 7805), volume 1, pages 537-541.
  15. He, H. and Garcia, E. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9):1263-1284.
  16. Hulse, J. V., Khoshgoftaar, T. M., and Napolitano, A. (2007). Experimental perspectives on learning from imbalanced data. In Proc. of the 24th international conference on Machine learning (ICML'07), pages 935-942.
  17. Jemal, A., Siegel, R., Xu, J., and Ward, E. (2010). Cancer statistics, 2010. CA: A Cancer Journal for Clinicians, 60:277-300.
  18. Kubat, M. and Matwin, S. (1997). Addressing the curse of imbalanced training sets: one-sided selection. In 14th ICML, pages 179-186.
  19. Kuzmina, I., Diebele, I., Jakovels, D., Spigulis, J., Valeine, L., Kapostinsh, J., and Berzina, A. (2011a). Towards noncontact skin melanoma selection by multispectral imaging analysis. Journal of Biomedical optics, 16(6):0605021-0605023.
  20. Kuzmina, I., Diebele, I., Valeine, L., Jakovels, D., Kempele, A., Kapostinsh, J., and Spigulis, J. (2011b). Multispectral imaging analysis of pigmented and vascular skin lesions: results of a clinical trial. In Proc. of SPIE, volume 7883, pages 7883121-7883127.
  21. Maes, F., Collignon, A., Vandermeulen, D., Marchal, G., and Suetens, P. (1997). Multimodality image registration by maximization of mutual information. IEEE Trans. Med. Imaging, 16(2):187-198.
  22. Mazzoli, A., Munaretto, R., and Scalise, L. (2010). Preliminary results on the use of a noninvasive instrument for the evaluation of the depth of pigmented skin lesions: numerical simulations and experimental measurements. Lasers Med. Sci., 25:403-410.
  23. Mogensen, M. and Jemec, G. (2007). Diagnosis of nonmelanoma skin cancer/keratinocyte carcinoma: a review of diagnostic accuracy of nonmelanoma skin cancer diagnostic tests and technologies. Dermatol. Surg., 33:1158-1174.
  24. Nagaoka, T., Nakamura, A., Okutani, H., Kiyohara, Y., and Sota, T. (2011). A possible melanoma discrimination index based on hyperspectral data: a pilot study. Skin Research and Technology, (DOI:10.1111/j.1600- 0846.2011.00571.x):1-10.
  25. Pluim, J. P. W., Maintz, J. B. A., and Viergever, M. A. (2003). Mutual-information-based registration of medical images: A survey. IEEE Trans. Med. Imaging, 22(8):986-1004.
  26. Press, W., Teukolsky, S. A., Vetterling, W. T., and Flannery, B. P. (1992). Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press.
  27. Rajaram, N., Aramil, T. J., Lee, K., Reichenberg, J. S., Nguyen, T. H., and Tunnell, J. W. (2010). Design and validation of a clinical instrument for spectral diagnosis of cutaneous malignancy. Applied Optics, 49(2):142-152.
  28. Raposio, E. and et. al (2007). Spectrophotometric technology for the early detection of cutaneous melanoma. International Journal of Simulation Systems, Science & Technology, 8(4):46-54.
  29. Rigel, D. S. and Friedman, R. J. (1993). The rationale of the abcds of early melanoma. J. Am. Acadm. Dermatol., 29:1060-1061.
  30. Rigel, D. S., Russak, J., and Friedman, R. (2010). The evolution of melanoma diagnosis: 25 years beyond the abcds. CA: A Cancer Journal for Clinicians, 60:301- 316.
  31. SCHNEIDER (2011). Industrial optics: Oem. In http:// www.schneiderkreuznach.com.
  32. Sokolova, M., Japkowicz, N., and Szpakowicz, S. (2006). Beyond accuracy, f-score and roc: A family of discriminant measures for performance evaluation. In Sattar, A. and Kang, B.-h., editors, AI 2006: Advances in Artificial Intelligence, volume 4304 of Lecture Notes in Computer Science, pages 1015-1021.
  33. Sorg, B. S., Moeller, B. J., Donovan, O., Cao, Y., and Dewhirst, M. W. (2005). Hyperspectral imaging of hemoglobin saturation in tumor microvasculature and tumor hipoxia development. Journal Biomedical Optics, 10(4):044004.
  34. Stanley, R. J., Stoecker, W. V., and Moss, R. H. (2007). A relative color approach to color discrimination for malignant melanoma detection in dermoscopy images. Skin Research and Technology, 13:62-72.
  35. Stoecker, W. V., Wronkiewiecz, M., Chowdhury, R., Stanley, R. J., Xu, J., Bangert, A., Shrestha, B., Calcara, D. A., Rabinovitz, H. S., Oliviero, M., Ahmed, F., Perry, L. A., and Drugge, R. (2011). Detection of granularity in dermoscopy images of malignant melanoma using color and texture features. Computerized Medical Imaging and Graphics, 35:144-147.
  36. Tenenhaus, A., Nkengne, A., Horn, J.-F., Serruys, C., Giron, A., and Fertil, B. (2010). Detection of melanoma from dermoscopic images of naevi acquired under uncontrolled conditions. Skin Research and Technology, 16:85-97.
  37. Tomatis, S., Bono, A., Bartoli, C., Carrara, M., LualdiM, M., Tragni, G., and Marchesini, R. (2003). Automated melanoma detection, multispectral imaging and neuronal network approach for classification. Melanoma Research, 30(2):212-221.
  38. Uribe, A. G., Smith, E. B., Zou, J., Duvic, M., Prieto, V., and Wang, L. V. (2011). In-vivo characterization of optical properties of pigmented skin lesions including melanoma using oblique incidence diffuse reflectance spectrometry. Journal of Biomedical optics, 16(2):0205011-0205013.
Download


Paper Citation


in Harvard Style

Quinzán Suárez I., Latorre Carmona P., García Sevilla P., Boldo E., Pla F., García Jiménez V., Lozoya R. and Pérez de Lucía G. (2012). NON-INVASIVE MELANOMA DIAGNOSIS USING MULTISPECTRAL IMAGING . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: PRARSHIA, (ICPRAM 2012) ISBN 978-989-8425-98-0, pages 386-393. DOI: 10.5220/0003843803860393


in Bibtex Style

@conference{prarshia12,
author={Ianisse Quinzán Suárez and Pedro Latorre Carmona and Pedro García Sevilla and Enrique Boldo and Filiberto Pla and Vicente García Jiménez and Rafael Lozoya and Guillermo Pérez de Lucía},
title={NON-INVASIVE MELANOMA DIAGNOSIS USING MULTISPECTRAL IMAGING},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: PRARSHIA, (ICPRAM 2012)},
year={2012},
pages={386-393},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003843803860393},
isbn={978-989-8425-98-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: PRARSHIA, (ICPRAM 2012)
TI - NON-INVASIVE MELANOMA DIAGNOSIS USING MULTISPECTRAL IMAGING
SN - 978-989-8425-98-0
AU - Quinzán Suárez I.
AU - Latorre Carmona P.
AU - García Sevilla P.
AU - Boldo E.
AU - Pla F.
AU - García Jiménez V.
AU - Lozoya R.
AU - Pérez de Lucía G.
PY - 2012
SP - 386
EP - 393
DO - 10.5220/0003843803860393