Statistical Techniques Applied to the Automatic Diagnosis of Dermoscopic Images

Abstract

An image based system implementing a well-known diagnostic method is disclosed for the automatic detection of melanomas as support to clinicians. The software procedure is able to recognize automatically the skin lesion within the digital image, measure morphological and chromatic feature, carry out a suitable classification for the detection of structural dermoscopic criteria provided by the 7-Point Check. Statistical techniques are introduced and adopted for border detection, feature extraction and classification as well as the resulting diagnostic score are described with reference to a large image set of pigmented lesions.