Wavelet based classification of skin lesion images

• Autorzy: Surówka G. , Merkwirth C. , Żabińska-Płazak E. , Graca A.

Warianty tytułu

PL

Klasyfikacja obrazów zmian skórnych

• Języki publikacji: EN

Abstrakty

EN

Visual examination of the early stages of the melanocytic skin cancer (melanoma) may often lead to a false diagnosis. Only the resection and then histologic examination of the lesion can fully detect malignant transformations of the skin. This is the reason why development of non-invasive methods for dermatological diagnosis, like dermatoscopy, is of key importance. We build a MLP-based binary classifier for discriminating melanoma from dysplastic nevus utilizing textural information contained in the skin lesion images taken in dermatoscopic examinations. Our analysis is based on the multiresolution wavelet-based decomposition of the images. Significant features of both classes are found by means of the Ridge regression models. Discriminating melanoma from dysplastic nevus with this method yields a sensitivity and specificity of 89.5% and 90%, respectively.

PL

Wizualna ocena wczesnych stanów procesu nowotworzenia skóry może prowadzić do błędnej diagnozy. Jedynie resekcja oraz histologiczna ocena może ocenić obecność procesu nowotworzenia. Stąd potrzeba nieinwazyjnej oceny w dermatologii jest potrzebą chwili. Zbudowaliśmy bazujący na MLP binarny klasyfikator dla dyskryminacji melanoma w oparciu o obrazy uzyskane dermatoskopowo. Metoda bazuje na dekompozycji obrazu. Model regresji Ridge'go został zaadaptowany dla klasyfikacji obrazu co dało specyficzność oceny rzędu 89.5% i 90%.

Słowa kluczowe

EN

melanoma; dermatoscopy; wavelet transform; machine learning; automatic diagnosis

PL

melanoma; dermatoskopia; uczenie maszyny; diagnoza automatyczna

• Wydawca: Uniwersytet Jagielloński - Collegium Medicum ; Index Copernicus Sp. z o.o.
• Czasopismo: Bio-Algorithms and Med-Systems
• Rocznik: 2006
• Tom: Vol. 2, no. 4
• Strony: 43--49
• Opis fizyczny: Bibliogr. 31 poz., rys., tab., wykr.

Twórcy

autor

Surówka G.

• Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Kraków, Poland

autor

Merkwirth C.

• Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Kraków, Poland

autor

Żabińska-Płazak E.

• Department of Dermatoiogy, Coliegium Medicum, Jagiellonian University, Kraków, Poland

autor

Graca A.

• Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Kraków, Poland

Bibliografia

• 1. Marks R., Epidemiology of melanoma, Clin. Exp. Dermatol. 25: 459-463 (2000).
• 2. Thorn M., Ponten R, Bergstrom R. et al., Clinical and histopathologic predictors of survival in patients with malignant melanoma: a population-based study in Sweden. J Natl Cancer Inst 86: 761-769 (1994).
• 3. Westerhoff K., McCarthy W.H., Menzies S.W., Increase in the sensitivity for melanoma diagnosis by primary care physicians using skin surface microscopy. Br J Dermatol 143:1016-1020 (2000).
• 4. Odom R.B., James W.H., Berger T.G., Melanocytic nevi and neoplasms, in: Andrews' Diseases of the Skin, 9th ed., 881-889 Philadelphia (2000).
• 5. Dial W.F., ABCD rule aids in preoperative diagnosis of malignant melanoma, Cosmetic Dermatol. 8: 32-34 (1995).
• 6. Carli P., De Giorgi V., Palli D. et al., Preoperative assessment of melanoma thickness by ABCD score of dermatoscopy, J. Am. Acad. Dermatol., 43:459-466 (2000).
• 7. Johr R.H., Dermatoscopy: alternative melanocytic algorithms the ABCD rule of dermatoscopy, Menzies scoring method, and 7-point checklist, Clinics in Dermatology, 20: 240-247 (2002).
• 8. 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. 134: 1563-70 (1998).
• 9. Żabińska-Płazak E., Wojas-Pelc A., Dyduch G.: Video-dermatoscopy in the diagnosis of melanocytic skin lesions, Bio-Algorithms and Med-Systems, 1: 333-338 (2005).
• 10. Carli P., De Giorgi V., Gianotti B. et al., Dermatoscopy and early diagnosis of melanoma. Arch Dermatol 137:1641-1644 (2001).
• 11. Menzies S.W., Automated epiluminescence microscopy: human vs machine in the diagnosis of melanoma. Arch Dermatol 135: 1538-1540 (1999).
• 12. http://www.dermogenius.com/ http://www.dermamedical-systems.com/
• 13. Dhawan A.P., Early detection of cutaneous malignant melanoma by three dimensional nevoscopy, Comp. Meth. Prog. Biomed. 21: 59-68 (1985).
• 14. Piccolo D., Smolle J., Argenziano G. et al., Teledermatoscopy results of a multicentre study on 43 pigmented skin lesions, J. Telemed. Telecare., 6: 132-137 (2000).
• 15. Robinson J.K., Nickoloff B.J., Digital epiluminescence microscopy monitoring of high-risk patients, Arch. Dermatol. 140: 49-56 (2004).
• 16. Piccolo D., Smolle J., Wolf I.H. et al., Face-to-face diagnosis vs telediagnosis of pigmented skin tumors: a teledermato-scopic study. Arch Dermatol. 135:1467-1471 (1999).
• 17. Paine S., Cockburn J., Noy S. et al., Early detection of skin cancer: knowledge, perceptions and practices of general practitioners in Victoria. Med. J. Aust. 161: 188-195 (1994).
• 18. Patwardhan S.V., Dai S., Dhawan A.P., Multi-spectral image analysis and classification of melanoma using fuzzy membership based partitions, Computerized Medical Imaging and Graphics, 29: 287-296 (2005).
• 19. Patwardhan S.V., Dhawan A.P., Relue P.A., Classification of melanoma using tree structured wavelet transforms, Computer Methods and Programs in Biomedicine, 72:223-239 (2003).
• 20. Chang T., Kuo C.C.J., Texture Analysis and Classification with Tree-Structured Wavelet Transform, IEEE Transactions on Image Processing, 2: 429-441 (1993).
• 21. Kadiyala M., DeBrunner V., Effect of wavelet bases in texture classification using a tree structured wavelet transform, 33 Asilomar Conference on Signals, Systems, and Computers, 2: 1292-1296 (1999).
• 22. Mallat S.G., A Theory for Multiresolution Signal Decomposition: The Wavelet Representation, IEEE Transactions on pattern analysis and machine intelligence, 11: 674-693 (1989).
• 23. Wang J.W., Chen C.H., Chien W.M., Tsai CM., Texture classification using non-separable two-dimensional wavelets, Patt.Rec. Left., 19:1225-1234 (1998).
• 24. Kovacevic J., Vatterli M., Nonseparable Multidimensional Perfect Reconstruction Filter Banks and Wavelet Bases for Rn, IEEE Trans. Inf. Theor., 38: 533-555 (1992).
• 25. Mojsilovic A., Popovic M.V., Rackov D.M., On the selection of an optimal wavelet basis for texture characterization, IEEE Transactions on Image Processing, 9: 2043-2050 (2000).
• 26. An Analysis of Wavelet Characteristics in Image Compression, SPIE Conference on Wavelets: Applications in Signal and Image Processing (2003).
• 27. Porter R., Canagarajah N., A Robust Automatic Clustering Scheme for Image Segmentation Using Wavelets, IEEE Transactions on Image Processing 5: 662-665 (1996).
• 28. Daubechies I., Ten Lectures on Wavelets, S.I.A.M., Philadelphia, 1992.
• 29. Numerical Recipes in C. The art of scientific computing, PWN 1999, pp. 591-606.
• 30. Receiver operating characteristic (ROC) analysis: Basic principles and applications in radiology, European Journal of Radiology, 27: 88-94 (1998).
• 31. http://zti.if.uj.edu.pl/~merkwirth/entool.htm