Multi-spectral image analysis and classification of melanoma using fuzzy membership based partitions
Document Type
Article
Publication Date
6-1-2005
Abstract
The sensitivity and specificity of melanoma diagnosis can be improved by adding the lesion depth and structure information obtained from the multi-spectral, trans-illumination images to the surface characteristic information obtained from the epi-illumination images. Wavelet transform based bi-modal channel energy features obtained from the images are used in the analysis. Methods using both crisp and fuzzy membership based partitioning of the feature space are evaluated. For this purpose, the ADWAT classification method that uses crisp partitioning is extended to handle multi-spectral image data. Also, multi-dimensional fuzzy membership functions with Gaussian and Bell profiles are proposed for classification. Results show that the fuzzy membership functions with Bell profile are more effective than the extended ADWAT method in discriminating melanoma from dysplastic nevus. © 2005 Elsevier Ltd. All rights reserved.
Identifier
18844452915 (Scopus)
Publication Title
Computerized Medical Imaging and Graphics
External Full Text Location
https://doi.org/10.1016/j.compmedimag.2004.11.001
ISSN
08956111
PubMed ID
15890256
First Page
287
Last Page
296
Issue
4
Volume
29
Recommended Citation
Patwardhan, Sachin V.; Dai, Shuangshuang; and Dhawan, Atam P., "Multi-spectral image analysis and classification of melanoma using fuzzy membership based partitions" (2005). Faculty Publications. 19689.
https://digitalcommons.njit.edu/fac_pubs/19689
