Evaluation of imaging-based methods for facial aging detection

Summary: Introduction: Quantifying facial aging is essential in dermatology for studying age-related changes and assessing the effectiveness of skincare products. However, facial aging detection remains challenging due to the absence of standardized benchmarks and unified testing protocols, making it difficult to compare different methods fairly. In this study, we evaluate the performance of commonly used imaging-based facial aging detection methods, focusing on accuracy, stability, and sensitivity. By highlighting their strengths and limitations, this research aims to provide a comprehensive review of facial aging detection approaches to help researchers select the most suitable method for their studies. Methods: A dataset of 2,000 individuals was analyzed under standardized conditions using imaging systems (Visia CR 5.0, Antera 3D, EVE V). To compare the performance of the methods, we calculated correlations with age, consistency across repeated measurements, and detection of subtle changes post-intervention. Human assessments were used as the gold standard for measuring accuracy. Results: EVE V demonstrated the highest correlation with age, with results exceeding 0.82, outperforming Visia CR 5.0 (average 0.73) and Antera 3D (average 0.77). Compared to human assessments as the gold standard, the accuracy adjustment for EVE V averaged 0.75, while Visia CR 5.0 was 0.68, and Antera 3D was 0.63. Antera 3D showed superior sensitivity, detecting over 20% changes in localized skin features. In terms of stability, EVE V achieved the highest score at 0.93, followed by Visia CR 5.0 at 0.88, and Antera 3D at 0.80. Discussion and Conclusion: Antera 3D’s high sensitivity makes it ideal for analyzing localized skin features, while EVE V and Visia CR 5.0 excels in accuracy and stability, making it well-suited for research on age-related skin changes. These findings offer valuable insights for selecting the most appropriate imaging systems for clinical dermatology and efficacy testing. Fudi Wang¹, Baolin Chen², Zhiyang Li² 1. Chinese Academy of Sciences Shanghai Institute of Nutrition and Health, Shanghai, Shanghai, China. 2. Xiamen Meitueve Technology CO., Ltd, Xiamen, China. Clinical Research: Epidemiology and Observational Research