Book Description
As a result of the advances in skin imaging technology and the development of suitable image processing techniques, during the last decade, there has been a significant increase of interest in the computer-aided diagnosis of skin cancer. Dermoscopy is a relatively recent, non-invasive skin imaging technique which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. This reduces screening errors, and provides greater differentiation between difficult lesions such as pigmented Spitz nevi and small, clinically equivocal lesions. However, it has been demonstrated that dermoscopy may actually lower the diagnostic accuracy in the hands of inexperienced dermatologists. Therefore, due to the lack of reproducibility and subjectivity of human interpretation, the development of computerized techniques is of utmost importance. In this thesis, several algorithms for the analysis of dermoscopy images have been developed. These include automatic border detection, low-level (shape, color, and texture) feature extraction, classification, and high-level (dermoscopic) feature extraction. Experimental results on a large and heterogeneous set of images demonstrate that the developed algorithms allow for fast and accurate classification of dermoscopy images.