Randomized Dynamic Generation of Selected Melanocytic Skin Lesion Features
In this paper, the methodology of generating images of melanocytic skin lesions is briefly outlined. The developed methodology proceeds essentially in two steps. In the first one, semantic description of skin lesions of anonymous patients is carefully analyzed to catch important features (symptoms) and to mine their logical values. Then, data gained in this step are used to control a specific simulation process, in which the simulated lesion’s image is randomly put together from a priori pre-defined fragments (textures). In this way, a single textual vector representing a distinct lesion, can produce a collection of several images of a given category. The quality of simulated images, verified by an independent expert was found to be quite satisfactory.
KeywordsSimulated Image Semantic Description Source Database Melanocytic Lesion Blue Nevus
Unable to display preview. Download preview PDF.
- 1.1. Alberty R.A., Silbey R.J. (1992) Physical Chemistry. J. Wiley & Sons, Inc., New York, pp. 426–430.Google Scholar
- 2.2. Braun-Falco O., Stolz W., Bilek P., Merkle T., Landthaler M. (1990) Das dermatoskop. Eine Vereinfachung der Auflichtmikroskopie von pigmentierten Hautveranderungen. Hautarzt 40, 131–136.Google Scholar
- 3.3. Bajcar S., Grzegorczyk L. (2000) The Atlas of Diagnostics of Melanocitic Lesions. Jagiellonian University Editorial Office, Cracow (Poland).Google Scholar
- 4.4. Gołąb J., Jakóbisiak M., Lasek W. (2004) Immunology. Polish Scientific Publishers PWN, Warsaw (Poland).Google Scholar
- 6.6. Hippe Z.S., Piatek L. (2005) From research on the database of simulated medical images. Proc. of the Conferene Databases for Science and Technology, Gdańsk (Poland), 225–230.Google Scholar
- 7.7. Kulikowski J.L. (2005) The foundations of the structural description of distracted databases of expert knowledge. Proc. of the Conference Databases for Science and Technology, Gdańsk (Poland), 29–38.Google Scholar
- 8.8. http://www.boutell.com/gd/.Google Scholar