Image Analysis and Diagnosis of Skin Diseases - A Review

Abstract

Background: Skin disease image analysis has drawn extensive attention from researchers, which can help doctors efficiently diagnose skin disease from medical images. Existing reviews have focused only on the specific task of skin disease diagnosis based on a single medical image type.

Discussion: This paper presents the latest and comprehensive review of image analysis methods in skin diseases, and summarizes over 350 contributions to the field, most of which appeared in the last three years. We first sort out representative publicly available skin datasets and summarize their characteristics. Thereafter, aiming at the typical problems exposed by datasets, we organize the image preprocessing and data enhancement part. Further, we review the single tasks of skin disease image analysis in the literature, such as classification, detection or segmentation, and analyze the improvement direction of their corresponding methods. Additionally, popular multi-task models based on structure and loss function are also investigated.

Conclusions: Challenges involved from the aspects of the dataset and model structure have been discussed.

Keywords: Computer-aided diagnosis; classification; deep learning; multi-task; segmentation; skin disease.