Unsupervised border detection of skin lesion images

As a result of the advances in skin imaging technology and the development of suitable image processing/computer vision algorithms, during the last decade, there has been a significant increase of interest in the computer-aided diagnosis of skin cancer. Automated border extraction is one of the most important steps in this procedure since the accuracy of the subsequent steps crucially depends on the accuracy of this very first step. In this paper, we present an unsupervised approach to border detection in skin lesion (tumor) images based on a modified version of the JSEG algorithm [Y. Deng et al., (2001)]. The segmentation results are visually examined by an expert dermatologist and are found to be highly accurate.