A New and Validated Computed Tomography-Based Method for Measurement of Facial Fat Volume

Background A consensus on effectively measuring facial fat volume by computed tomography (CT) or magnetic resonance imaging is lacking. This study aimed to assess the validity and reproducibility of a new CT-based method for measuring facial fat volume. Methods Volume was measured using a new semiautomatic segmentation method. Two observers measured the volume of the fat layers in four soft tissue models constructed using the three-dimensional viewer software. These measurements were compared with previously reported standard volumes. Fat volume in the area of interest was measured from 16 hemifacial CT images by two independent observers. Based on the acquired data, inter-class correlation coefficients and Bland-Altman analyses were performed. Results The mean difference (ml) +/- SEM in comparison with the known volume was - 0.87 +/- 4.11 (observer MY) and 3.42 +/- 4.68 (observer HW), respectively. The fat volume of pork tissue (PFV) measured using MY (P = 0.846 > 0.05) and HW (P = 0.518 > 0.05) did not differ significantly from the standard volume. ICC calculations and Bland-Altman analysis indicated good agreement between inter- and intra-observer (ICC = 0.992 and 0.970 > 0.90, P<0.001). Conclusions This new volumetric analysis for facial fat using a semiautomatic segmentation technique on CT scans is an effective and reliable tool.