An automatic procedure that grades some facial skin structural signs: agreements and validation with clinical assessments made by dermatologists

Abstract

To confirm the robustness and validity of an automatic scoring system, algorithm-based, that grades the severity of nine facial signs through "selfies" smartphones pictures taken by European Caucasian women through dermatological assessments. 157 Caucasian women from three countries (France, Germany, Spain), of different ages (20-75years), took one "selfie" image by the frontal camera of their smartphones whereas local dermatologists photographed them with the back camera of the same smartphone. The same nine facial signs of these subjects were initially graded by these local dermatologists, using referential Skin Aging Atlases. All 314 "selfies" images were then further automatically analyzed by the algorithm. The severity of facial signs (wrinkles, pigmentation, ptosis, skin folds etc.) were statistically compared to the assessments made by the three dermatologists, taken as ground truth. Highly significant coefficients of correlation (P<0.001) were found in the three cohorts between the grades provided by the system and those from dermatologists in live. The back camera - of a better resolution than the frontal one - seems affording slightly more significant correlations. However, although significantly correlated, the signs of vascular disorders and cheek skin pores present some disparities that are likely linked to the technical diversity of smartphones or self-shootings, leading to lower coefficients of correlations. This automatic scoring system offers a promising approach in the harmonization of Dermatological assessments of skin facial signs and their changes with age or the follow up of anti-aging treatments.