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 are discussed.

Deep learning models across the range of skin disease

“…AI first entered dermatology in the context of Stanford’s landmark deep learning model for skin cancer detection in Nature in 2017 3 . Since then, new models have evolved beyond skin cancer alone—promising significant growth potential for the highly prevalent chronic inflammatory skin diseases, which affect 20–25% of the population wordwide 4 – 6 . With an array of promising diagnostic models inching closer to the bedside, questions arise for providers and regulators as to how these models should be evaluated and adopted.…”

SkinLiTE: Lightweight Supervised Contrastive Learning Model for Enhanced Skin Lesion Detection and Disease Typification in Dermoscopic Images

“…Meanwhile, Vatiwutipong, Vachmanus, Noraset and Tuarob [4] expanded the scope to cosmetic dermatology, demonstrating AI's role in areas ranging 2 from product development to treatment prediction. Research challenges in the context of skin disease diagnosis include image preprocessing, and the improvement of methods for tasks like classification, detection, segmentation, multi-task modeling, and dataset characterization [5]. Several studies collectively explored the integration of advanced imaging and machine learning technologies in the medical field, especially in oncology and early disease diagnosis [6][7][8].…”