Melanocytic globules detection in skin lesion images

Abstract

In this paper a method is presented for detection of melanin globules often present in melanocytic skin lesions images. The detection is done by performing image analysis similar to the one used in clinical evaluation. The method uses multi-stage image filtering to extract objects present in the dermoscopic image that match globule structure pattern. Classification of the found objects is made based on shape and size of globule structure. The classification is problematic task due to color and scale differences between dermatologic images and is related to differences between image acquisition equipment used in dermatoscopy. First we describe characteristic of globule structure needed for correct classification, along with method for calculating those characteristic. Next we presented a method for globules detection that is a part of computer-aided diagnostic process of melanocytic skin lesions. Evaluation of such lesions is a basis for early detection of malignant lesions.