Characterization and pattern recognition of color images of dermatological ulcers: a pilot study

Abstract

We present color image processing methods for the char\-ac\-te\-ri\-za\-tion of images of dermatological lesions for the purpose of content-based image retrieval (CBIR) and computer-aided di\-ag\-no\-sis. The intended application is to segment the images and perform classification and analysis of the tissue composition of skin lesions or ulcers, in terms of granulation (red), fibrin (yel\-low), necrotic (black), callous (white), and mixed tissue composition. The images were analyzed and classified by an expert dermatologist following the red-yellow-black-white model. Automatic segmentation was performed by means of clustering using Gauss\-ian mixture modeling, and its performance was evaluated by deriving the Jaccard coefficient between the automatically and manually segmented images. Statistical texture features were derived from cooccurrence matrices of RGB, HSI, L$^*$a$^*$b$^*$, and L$^*$u$^*$v$^*$ color components. A retrieval engine was implemented using the k-nearest-neighbor classifier and the Euclidean, Man\-hat\-tan, and Chebyshev distance metrics. Classification was performed by means of a metaclassifier using logistic regression. The average Jaccard coefficient after the segmentation step between the automatically and manually segmented images was 0.560, with a standard deviation of 0.220. The performance in CBIR was mea\-sured in terms of precision of retrieval, with average values of up to 0.617 obtained with the Chebyshev distance. The metaclassifier yielded an average area under the receiver operating char\-ac\-ter\-is\-tic curve of 0.772.

Keywords

• Color image processing
• color medical images
• color texture
• content-based image retrieval
• computer-aided diagnosis
• image segmentation
• dermatological ulcers
• tissue composition analysis