Automatic SCOring of atopic dermatitis using deep learning (ASCORAD): a pilot study

Abstract

Atopic dermatitis (AD) is a chronic, itchy skin condition that affects 15–20% of children, but may occur at any age. It is estimated that 16.5 million U.S. adults (7.3%) have AD that initially began at >2 years of age, with nearly 40% affected by moderate or severe disease. Therefore, a quantitative measurement that could track the evolution of atopic dermatitis severity could be extremely useful in assessing therapeutic efficacy. Currently, SCORAD (SCOring Atopic Dermatitis) is the most frequently used measurement in clinical practice. However, SCORAD has the following disadvantages: (1) Time consuming: calculating SCORAD usually takes about 7–10 minutes per patient which poses a heavy burden on dermatologists; and (2) Inconsistency: due to the complexity of SCORAD calculation, even well-trained dermatologists could give different scores for the same case. In this study we introduce ASCORAD, an automatic version of the SCORAD, based on state-of-the-art convolutional neural networks that measure atopic dermatitis severity based on skin lesion images. Overall, we have demonstrated that ASCORAD may prove to be a rapid and objective alternative method for the automatic assessment of atopic dermatitis, achieving results comparable to human expert assessment while reducing inter-observer variability.