Answers are grounded in this paper and cite their sources.
Autologous facial fat grafting is widely used in aesthetic and reconstructive surgery to restore facial volume and improve facial appearance. Despite its popularity, evaluation of postoperative outcomes frequently relies mainly on subjective assessments by clinicians or patient-reported satisfaction. Advances in artificial intelligence (AI) provide new opportunities for objective and quantitative analysis of facial aesthetics. The present study aimed to explore differences in AI-derived aesthetic metrics between preoperative and postoperative facial photographs following facial fat transfer. Selected preoperative and postoperative frontal facial photographs of subjects undergoing facial fat transfer were analyzed using an AI-based aesthetic evaluation platform. Three automated indices were extracted: the Facial Aesthetic Index (FAI), Facial Youthfulness Index (FYI), and Skin Quality Index (SQI), each ranging from 0 to 100. Pre- and postoperative scores were compared using paired Wilcoxon signed-rank tests. Fifty female subjects between 18 to over 75 years old were included, with postoperative photographs obtained between 5 days and 7 years after the procedure. AI-based analysis demonstrated significant postoperative improvements across all evaluated indices. Median FAI increased from 81.0 (IQR 72.2–86.8) to 85.0 (IQR 75.2–89.8) (p = 0.005), FYI from 61.0 (IQR 53.2–72.8) to 66.5 (IQR 52.2–79.5) (p = 0.021), and SQI from 88.0 (IQR 82.2–91.8) to 91.0 (IQR 87.0–95.0) (p < 0.001). Effect size analysis demonstrated moderate improvements in FAI (r = 0.390) and FYI (r = 0.319), and a large effect for SQI (r = 0.511). Subgroup analysis suggested greater improvements among older subjects, although these differences were not statistically significant. AI-assisted facial analysis represents a promising quantitative approach for comparing preoperative and postoperative facial images following facial fat transfer. These exploratory findings demonstrate the feasibility of applying AI-derived metrics to retrospective image-based assessment. The integration of objective digital assessment tools may complement traditional evaluation methods and contribute to more standardized outcome reporting in aesthetic surgery. This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .
No takes yet. Share an insight, caveat, or question.
Alves et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: