A deep learning-based smartphone platform for cutaneous lupus erythematosus classification assistance: Simplifying the diagnosis of complicated diseases

To the Editor: Cutaneous lupus erythematosus (CLE) can be divided into different subtypes including acute cutaneous LE, subcutaneous LE, and discoid LE. These subtypes of CLE are easily confused with other skin diseases,1 which leads to inappropriate or delayed treatment. Convolutional neural networks (CNNs) have shown great power for automatic analysis of clinical images.2 However, data concerning CLE are limited.3 Here, we report our development of a smartphone-based platform to assist CLE diagnosis and classification.