Medical images classification for skin cancer diagnosis based on combined texture and fractal analysis

Fractal and texture analysis are computer techniques which can discriminate between the shapes of benign and malignant tumors. The goal of present paper is to describe a method and an algorithm for automatic detection of malignancy of skin lesions which is based on both local fractal features (local fractal dimension) and texture features which derives from the medium co-occurrence matrices (contrast, energy, entropy, homogeneity). The global application was tested on a set of medical images obtained with a dermoscope and a digital camera, all from cases with known diagnostic. The experimental results confirm the efficiency of the proposed method.