An annotation tool for dermoscopic image segmentation

Abstract

Dermoscopy is a non-invasive diagnostic technique for the in vivo observation of pigmented skin lesions, and it is currently one of the most important imaging techniques for melanoma diagnosis. Since the diagnostic accuracy of dermoscopy significantly depends on the experience of the dermatologists, and the visual interpretation and examination of this kind of images is time consuming, several computer-aided diagnosis systems of digital dermoscopic images have been introduced. However, a reliable ground truth database of manually segmented images is necessary for the development and validation of automatic segmentation and classification methods. As the ground truth database have to be created by expert dermatologists, there is a need for the development of annotation tools that can support the manual segmentation of dermoscopic images, and this way make this task easier and practicable for dermatologists. In this paper we present an annotation tool for manual segmentation of dermoscopic images. This tool allows building up a ground truth database with the manual segmentations both of pigmented skin lesions and of other regions of interest, whose recognition is essential for the development of computer-aided diagnosis systems.