A deep-learning algorithm to classify skin lesions from mpox virus infection
The Gevaert lab spearheaded by visiting scholar Dr. Alexander Thieme has developed a model that is able to distinguish mpox skin lesions from other skin lesions. We assembled a dataset of 139,198 skin lesion images comprising of non-mpox images from eight dermatological repositories and mpox images from the scientific literature, news articles, social media and a prospective cohort of the Stanford University Medical Center. We show that robust sensitivity and specificity in the prospective cohort. We also developed a web-based app by which the MPXV-CNN can be accessed for patient guidance called PoxApp. You can read more about it here.