Back to 2024 Abstracts
Facial Skeleton Aging Pattern: Ai-assisted Statistical Shape Modeling And Volumetric Analysis In The White Population
Sara Hussein, MD, Jess Rames, M.D., Alexandre Pazelli, M.D., Abdallah Abushehab,, M.D, Victoria Sears, M.S., Adam Wentworth, M.S, Jonathan Morris, M.D, Basel Sharaf, M.D., D.D.S;
Mayo Clinic, Rochester, MN, USA
PURPOSE: Facial skeleton aging is reported across the medical literature and is the corner stone of tailoring the facial rejuvenation procedures. However, there is paucity of quantitative data analysis. Recently, Artificial Intelligence (AI) has been well integrated in radiological assessment of the patients scans. In this study, we report our findings using SSM 3D models to describe the pattern of facial skeleton aging representing male and female cohorts.
METHODS: Retrospective analysis was conducted using Mayo Data base from (2011 to 2023), CTA scans representing white ethnicity were included, slice less than 1mm. Patients with trauma or any history of orthodontic treatment were excluded. AI-assisted segmentation, and SSM in (Mimics Innovation 25e, 3D modelling software) were performed to generate 3D models. Ai scripts and some manual modifications were used. Our cohort was divided into 2 age groups (20:39) and (60:79) years old. All the findings represented in heat maps were statistically significant and represented as mean or Standard deviation (CI= 95%).
RESULTS: A sample of 100 patients, n=95 was eligible for analysis, The young and elder cohorts represented 44% and 47.9% females, respectively. The mean age of the 2 groups is 30.1 and 67.4 years old. The average BMI for both were 29.4. No Statistical significance of the BMI on our analysis. Female SSMs showed higher bone resorption (mean=1.6, CI=95%) in the upper face, mainly the orbital region.
CONCLUSION: Quantification and volumetric analysis of the facial skeleton aging using technological advancement is reliable and may assist in advancing Patient-centered aesthetic care.
Back to 2024 Abstracts
