Computational methods for the image segmentation of pigmented skin lesions: A review

• The clinical requirement for the early diagnosis of malignant skin lesions from images is introduced and justified.
• An up-to-date review about the proposed techniques for the image segmentation of pigmented skin lesions is presented.
• Additionally, the tasks related to image acquisition and pre-processing are also taken into account.
• The techniques are introduced, classified, and some examples of their results, are illustrated and discussed.
• This review is of interest both for researchers and for health professionals.

Background and objectivesBecause skin cancer affects millions of people worldwide, computational methods for the segmentation of pigmented skin lesions in images have been developed in order to assist dermatologists in their diagnosis. This paper aims to present a review of the current methods, and outline a comparative analysis with regards to several of the fundamental steps of image processing, such as image acquisition, pre-processing and segmentation.MethodsTechniques that have been proposed to achieve these tasks were identified and reviewed. As to the image segmentation task, the techniques were classified according to their principle.ResultsThe techniques employed in each step are explained, and their strengths and weaknesses are identified. In addition, several of the reviewed techniques are applied to macroscopic and dermoscopy images in order to exemplify their results.ConclusionsThe image segmentation of skin lesions has been addressed successfully in many studies; however, there is a demand for new methodologies in order to improve the efficiency.