Comparison of trueness and repeatability of facial prosthesis design using a 3D morphable model approach, traditional computer-aided design methods, and conventional manual sculpting techniques

Abstract

Statement of problem

Manually sculpting a wax pattern of a facial prosthesis is a time-, skill-, and resource-intensive process. Computer-aided design (CAD) methods have been proposed as a substitute for manual sculpting, but these techniques can still require high technical or artistic abilities. Three-dimensional morphable models (3DMMs) could semi-automate facial prosthesis CAD. Systematic comparisons of different design approaches are needed.

Purpose

The purpose of this study was to compare the trueness and repeatability of replacing facial features with 3 methods of facial prosthesis design involving 3DMM, traditional CAD, and conventional manual sculpting techniques.

Material and methods

Fifteen participants without facial defects were scanned with a structured light scanner. The facial meshes were manipulated to generate artificial orbital, nasal, or combined defects. Three methods of facial prosthesis design were compared for the 15 participants and repeated to produce 5 of each design for 2 participants. For the 3DMM approach, the Leeds face model informed the designs in a statistically meaningful way. For the traditional CAD methods, designs were created by using mirroring techniques or from a nose model database. For the conventional manual sculpting techniques, wax patterns were manually created on 3D printed full face baseplates. For analysis, the unedited facial feature was the standard. The unsigned distance was calculated from each of the several thousand vertices on the unedited facial feature to the closest point on the external surface of the prosthesis prototype. The mean absolute error was calculated, and a Friedman test was performed (α=.05).

Results

The median mean absolute error was 1.13 mm for the 3DMM group, 1.54 mm for the traditional CAD group, and 1.49 mm for the manual sculpting group, with no statistically significant differences among groups (P=.549). Boxplots showed substantial differences in the distribution of mean absolute error among groups, with the 3DMM group showing the greatest consistency. The 3DMM approach produced repeat designs with the lowest coefficient of variation.

Conclusions

The 3DMM approach shows potential as a semi-automated method of CAD. Further clinical research is planned to explore the 3DMM approach in a feasibility trial.