Skin lesion classification using relative color features
- 18 October 2007
- journal article
- Published by Wiley in Skin Research and Technology
- Vol. 14 (1), 53-64
- https://doi.org/10.1111/j.1600-0846.2007.00261.x
Abstract
Background/purpose: Clinically, it is difficult to differentiate the early stage of malignant melanoma and certain benign skin lesions due to similarity in appearance. Our research uses image analysis of clinical skin images and relative color‐based pattern recognition techniques to enhance the images and improve differentiation of these lesions. Methods: First, the relative color images were created from digitized photographic images. Then, they were segmented into objects and morphologically filtered. Next, the relative color features were extracted from the objects to form two different feature spaces; a lesion feature space and an object feature space. The two feature spaces serve as two data models to be analyzed to determine the best features. Finally, we used a statistical analysis model of relative color features, which better classifies the various types of skin lesions. Results/conclusions: The best features found for differentiation of melanoma and benign skin lesions from this study are area, mean in the red and blue bands, standard deviation in the red and green bands, skewness in the green band, and entropy in the red band. With the relative color feature algorithm developed, the best results were obtained with a multi‐layer perceptron neural network model. This showed an overall classification success of 79%, with 70% of the benign lesions successfully classified, and 86% of malignant melanoma successfully classified.Keywords
This publication has 13 references indexed in Scilit:
- Cancer Statistics, 2007CA: A Cancer Journal for Clinicians, 2007
- The Performance of SolarScanArchives of Dermatology, 2005
- Accuracy of Computer Diagnosis of MelanomaArchives of Dermatology, 2003
- Clinical and dermatoscopic diagnosis of small pigmented skin lesions.2002
- Automatic differentiation of melanoma from melanocytic nevi with multispectral digital dermoscopy: A feasibility studyJournal of the American Academy of Dermatology, 2001
- Rapid Increase in Diagnosis of Cutaneous Melanoma in Situ in Sweden, 1968-1992Cancer Detection Prevention, 1998
- Unsupervised color image segmentation: with application to skin tumor bordersIEEE Engineering in Medicine and Biology Magazine, 1996
- Neural network diagnosis of malignant melanoma from color imagesIEEE Transactions on Biomedical Engineering, 1994
- A scaled conjugate gradient algorithm for fast supervised learningNeural Networks, 1993
- An automatic color segmentation algorithm with application to identification of skin tumor bordersComputerized Medical Imaging and Graphics, 1992