A Wide Spread of Algorithms for Automatic Segmentation of Dermoscopic Images

摘要

Currently, there is a great interest in the development of computer-aided diagnosis (CAD) systems for dermoscopic images. The segmentation step is one of the most important ones, since its accuracy determines the eventual success or failure of a CAD system. In this paper, different kinds of algorithms for the automatic segmentation of skin lesions in dermoscopic images were implemented and evaluated, namely automatic thresholding, k-means, mean-shift, region growing, gradient vector flow (GVF), and watershed. The segmentation methods were evaluated with three distinct metrics, using as ground truth a database of 50 images manually segmented by an expert dermatologist. Among the implemented segmentation approaches, the GVF snake method achieved the best segmentation performance.