Wang Wenna, Flament Frederic, Wang Hequn, Ye Chengda, Jiang Ruowei, Houghton Jeff, Liu Wei
L'Oréal Research and Innovation, Shanghai, China.
L'Oréal Research and Innovation, Clichy, France.
Int J Cosmet Sci. 2025 Feb;47(1):113-122. doi: 10.1111/ics.13016. Epub 2024 Sep 1.
The objective of this study is to assess the correspondence, in live conditions, between clinical gradings of facial aging signs by three dermatologists and those afforded by an automatic AI-based algorithm that analyses smartphones' selfie images of Chinese subjects.
In total, 125 Chinese subjects of both genders, aged 18-62y, took a selfie using their own smartphones and were immediately viewed by three dermatologists. The latter graded the severity of 15 facial signs in women and 9 in men, using the standardized values afforded by a Skin Aging Atlas referential dedicated to Asian skin. The data issued by both methodologies were then statistically compared.
The absolute gradings of the automatic system were found highly correlated with clinical assessments, with lower values in most cases. In women, large differences in absolute values were found on the gradings for size of isolated spot, cheek fold, spread macules, and texture of mouth contour women. Analysis of the Mean Absolute Errors (M.A.E) revealed that these rarely exceed 0.6 grading units in women and to a lesser extent in men.
The present study confirmed the value of the automatic system towards an extended use towards large human cohorts as a surrogate of clinical evaluations and allowed to detect the points where improvements must be brought to the system.
本研究的目的是评估在实际情况下，三位皮肤科医生对面部衰老迹象的临床分级与基于人工智能的自动算法对中国受试者智能手机自拍图像分析结果之间的一致性。
共有125名年龄在18 - 62岁之间的中国男女受试者，用自己的智能手机自拍，三位皮肤科医生立即查看这些照片。皮肤科医生使用专门针对亚洲皮肤的皮肤老化图谱参考标准值，对女性的15种面部特征和男性的9种面部特征的严重程度进行分级。然后对两种方法得出的数据进行统计学比较。
发现自动系统的绝对分级与临床评估高度相关，大多数情况下数值较低。在女性中，孤立斑点大小、脸颊褶皱、散在斑和口周轮廓质地的分级在绝对值上存在较大差异。平均绝对误差（M.A.E）分析表明，这些误差在女性中很少超过0.6个分级单位，在男性中程度较轻。
本研究证实了自动系统作为临床评估替代方法在大规模人群中广泛应用的价值，并指出了该系统需要改进的地方。
