Classification of melanoma using tree structured wavelet transforms Sachin V. Patwardhan a , Atam P. Dhawan a, *, Patricia A. Relue b a Department of Electrical and Computer Engineering, New Jersey Institute of Technology, University Heights, Newark, NJ 07102, USA b Department of Bioengineering, The University of Toledo, Toledo, OH 43606, USA Received 18 June 2002; received in revised form 19 November 2002; accepted 25 November 2002 Abstract This paper presents a wavelet transform based tree structure model developed and evaluated for the classification of skin lesion images into melanoma and dysplastic nevus. The tree structure model utilizes a semantic representation of the spatial-frequency information contained in the skin lesion images including textural information. Results show that the presented method is effective in discriminating melanoma from dysplastic nevus. The results are also compared with those obtained using another method of developing tree structures utilizing the maximum channel energy criteria with a fixed energy ratio threshold. # 2002 Elsevier Science Ireland Ltd. All rights reserved. Keywords: Melanoma; Dysplastic nevus; Tree structured wavelet transform; Nevoscope 1. Introduction The rising rate of skin cancer is a growing concern worldwide [1]. Skin cancer is the most common form of cancer in the human population [2]. Mass screening for melanoma and other cutaneous malignancies has been advocated for early detection and effective treatment [3]. Though the gold standard for the diagnosis of skin cancer would still be the biopsy examination, the lesion for biopsy can be selected utilizing the computer- aided analysis for improving the sensitivity and specificity of skin cancer detection. Thus, the development of a non-invasive imaging and ana- lysis method could be beneficial in the early detection of cutaneous melanoma. Malignant melanoma [4] is the most lethal skin cancer in which melanocytes in the epidermis undergo malignant transformation. The two phases in the growth of melanoma are the super- ficial spreading phase, during which the lesion increases in size within the epidermis, and the vertical growth phase when the cells begin to move into the dermis [5]. The level of the spread of melanoma within the epidermis and then the dermis is determined as the Clark level, which indicates the stage (i.e. the severity) of the spread of melanoma [6]. Dermatologists use the ABCD rule (Asymme- try, Border, Colors, and Dermoscopic structures) * Corresponding author. Tel.:  /1-973-596-3524; fax:  /1- 973-596-5680; http://www.njit.edu/ece/dhawan. Computer Methods and Programs in Biomedicine 72 (2003) 223  /239 www.elsevier.com/locate/cmpb 0169-2607/03/$ - see front matter # 2002 Elsevier Science Ireland Ltd. All rights reserved. doi:10.1016/S0169-2607(02)00147-5