A new procedure, free from human assessment that automatically grades some facial skin structural signs. Comparison with assessments by experts, using referential atlases of skin ageing

Abstract

OBJECTIVE: To develop an automatic system that grades the severity of facial signs through 'selfies' pictures taken by women of different ages and ethnics. METHODS: 1140 women from three ethnics (African-American, Asian, Caucasian), of different ages (18-80 years old), took 'selfies' by high resolution smartphones cameras under different conditions of lighting or facial expressions. A dedicated software, was developed, based on a Convolutional Neural Network (CNN) that integrates training data from referential Skin Aging Atlases. The latter allows to an immediate quantification of the severity of nine facial signs according to the ethnicity declared by the subject. These automatic grading were confronted to those assessed by 12 trained experts and dermatologists either on 'selfies' pictures or in live conditions on a smaller cohort of women. RESULTS: The system appears weakly influenced by lighting conditions or facial expressions (coefficients of variations ranging 10-13% for most signs) and leads to global agreements with experts' assessments, even showing a better reproducibility on some facial signs. CONCLUSION: This automatic scoring system, still in development, seems offering a new quantitative approach in the quantified description of facial signs, independent from human vision, in many applications, being individual, cosmetic oriented or dermatological with regard to the follow-up of medical anti-ageing corrective strategies. a des valeurs comparables de celles des experts, voire même de meilleure reproductibilit e dans certains cas. CONCLUSION: Ce syst eme de scorage automatique, encore en d eveloppement, semble offrir une nouvelle approche dans la description quantitative de signes du visage, ind ependante de l'oeil humain, dans de nombreuses applications, comme la personnalisation, a vis ee cosm etique ou dermatologique, dans le suivi de certaines strat egies m edicales de l'antivieillissement cutan e.

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

“…The results of this multi centric study organized in three European countries, under the supervisions of three local dermatologists, globally confirm the robustness of the dedicated algorithm versus an on‐live ground truth. These results globally confirmed those previously found by expert’s assessments on pictures and “selfies” . A few points have however to be commented and discussed.…”

“…However, analyzing the respective correlations (in the three countries, Tables IV-VI) between their own grading's and those provided by the automatic system, led to non-significant slightly lower values (r decreased by about 0.06 in average) to those obtained by an automatic grading. A comparable result was obtained with regard slightly diverging assessments between experts [14]. In brief, the automatic system seems offering a slightly better accuracy than the one given by an unavoidable individual subjectivity of the human vision.…”

“…The latter were taken by 1140 women of three different ethnics and ages, under variable conditions (lighting, distance, facial expressions etc.). This first study showed that smartphones of an optical memory below 3 Megapixels led to less reproducible results. Comparisons with expert’s assessments, who graded the various severities using referential skin aging atlases , were shown in significant agreement in most cases.…”

A new procedure, free from human assessment, that automatically grades some facial skin signs in men from selfie pictures. Application to changes induced by a severe aerial chronic urban pollution

“…Because of low contrast with their skin complexion, the criterion of vascular disorders could not be addressed in African subjects. The same issue previously occurred in the system dedicated to women of different ethnic origins .…”

“…This step was performed through the use of Skin Aging Atlases devoted to men of different ancestries and ages [24][25][26][27][28]. Hence, similar to the one used on women [1,2], a new automatic grading system was therefore created, trained and validated on selfie images obtained in the first experiment from three cohorts of differently aged Asian, African, and Caucasian men (Study 1). As a use case (Study 2), this new automatic grading system was then challenged to record the possible changes in facial signs on Chinese men exposed to very different aerial urban pollutions [22,23].…”