ABCDE Rule for Multispectral Images of Nevi

General Info

Thesis by: Christoph Baur
Advisor: Professor Nassir Navab
Supervision by: Alexandru Duliu
Contact: Alexandru Duliu
Status: finished

Motivation

The ABCDE (asymmetry, border, colour, dimension, evolution) clinical rule was introduced for assisting the visual recognition of early melanoma. An automatic classification of skin leasion by means of this rule, would enable translation knowledge of expert physicians into a computer program.

Goals

This work will center around the implamentation of the ABCDE clinical rule for both RGB and Multispectral images of naevi in C++.

Part of this will be the development of a robust descriptor of Naevi (possible based of the ABCD rule - without E as in evolution) for the purpose of identification of naevi.

References

[1] R. J. Friedman, D. S. Rigel, and A. W. Kopf. Early detection of malignant melanoma: The role of physician examination and selfexamination of the skin. CA: A Cancer Journal for Clinicians, 35(3):130–151, 1985.

[2] Klaus D. Peter: original version of the naevi photo (Naevuszellnaevus.jpg)

[3] F. Nachbar, W. Stolz, T. Merkle, A. B. Cognetta, T. Vogt, M. Landthaler, P. Bilek, O. Braun-Falco, and G. Plewig. The ABCD rule of dermatoscopy: high prospective value in the diagnosis of doubtful melanocytic skin lesions. Journal of the American Academy of Dermatology, 30(4):551–559, 1994.

[4] S. Tomatis, M. Carrara, A. Bono, C. Bartoli, M. Lualdi, G. Tragni, A. Colombo, and R. Marchesini. Automated melanoma detection with a novel multispectral imaging system: results of a prospective study. Physics in medicine and biology, 50(8):1675, 2005.

[5] M. Yamaguchi, M. Mitsui, Y. Murakami, H. Fukuda, N. Ohyama, and Y. Kubota. Multispectral color imaging for dermatology: application in inflammatory and immunologic diseases. In Proceedings of the IS&T/SID 13th Color Imaging Conference, 2005.