Share Email Print

Proceedings Paper

Wavelet and statistical analysis for melanoma classification
Author(s): Amit Nimunkar; Atam P. Dhawan; Patricia A. Relue; Sachin V. Patwardhan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The present work focuses on spatial/frequency analysis of epiluminesence images of dysplastic nevus and melanoma. A three-level wavelet decomposition was performed on skin-lesion images to obtain coefficients in the wavelet domain. A total of 34 features were obtained by computing ratios of the mean, variance, energy and entropy of the wavelet coefficients along with the mean and standard deviation of image intensity. An unpaired t-test for a normal distribution based features and the Wilcoxon rank-sum test for non-normal distribution based features were performed for selecting statistically correlated features. For our data set, the statistical analysis of features reduced the feature set from 34 to 5 features. For classification, the discriminant functions were computed in the feature space using the Mahanalobis distance. ROC curves were generated and evaluated for false positive fraction from 0.1 to 0.4. Most of the discrimination functions provided a true positive rate for melanoma of 93% with a false positive rate up to 21%.

Paper Details

Date Published: 9 May 2002
PDF: 8 pages
Proc. SPIE 4684, Medical Imaging 2002: Image Processing, (9 May 2002); doi: 10.1117/12.467098
Show Author Affiliations
Amit Nimunkar, Univ. of Wisconsin/Madison (United States)
Atam P. Dhawan, New Jersey Institute of Technology (United States)
Patricia A. Relue, Univ. of Toledo (United States)
Sachin V. Patwardhan, New Jersey Institute of Technology (United States)

Published in SPIE Proceedings Vol. 4684:
Medical Imaging 2002: Image Processing
Milan Sonka; J. Michael Fitzpatrick, Editor(s)

© SPIE. Terms of Use
Back to Top