Validation of three-dimensional facial imaging captured with smartphone-based photogrammetry application in comparison to stereophotogrammetry system
Bibliographic record
Abstract
Statement of problem: The development of facial scanners has improved capabilities to create three-dimensional (3D) virtual patients for accurate facial and smile analysis. However, most of these scanners are expensive, stationary and involve a significant clinical footprint. The use of the Apple iPhone and its integrated "TrueDepth" near-infrared (NIR) scanner combined with an image processing application (app) offers the potential to capture and analyze the unique 3D nature of the face; the accuracy and reliability of which are yet to be established for use in clinical dentistry. Purpose: This study was designed to validate both the trueness and precision of the iPhone 11 Pro smartphone TrueDepth NIR scanner in conjunction with the Bellus3D Face app in capturing 3D facial images in a sample of adult participants in comparison to the conventional 3dMDface stereophotogrammetry system. Material and methods: Twenty-nine adult participants were prospectively recruited. Eighteen soft tissue landmarks were marked on each participant's face before imaging. 3D facial images were captured using a 3dMDface system and the Apple iPhone TrueDepth NIR scanner combined with the Bellus3D Face app respectively. The best fit of each experimental model to the 3dMD scan was analyzed using Geomagic Control X software. The root mean square (RMS) was used to measure the "trueness" as the absolute deviation of each TrueDepth scan from the reference 3dMD image. Individual facial landmark deviations were also assessed to evaluate the reliability in different craniofacial regions. The "precision" of the smartphone was tested by taking 10 consecutive scans of the same subject and comparing those to the reference scan. Intra-observer and inter-observer reliabilities were assessed using the intra-class correlation coefficient (ICC). Results: Relative to the 3dMDface system, the mean RMS difference of the iPhone/Bellus3D app was 0.86 ± 0.31 mm. 97% of all the landmarks were within 2 mm of error compared with the reference data. The ICC for intra-observer reproducibility or precision of the iPhone/Bellus3D app was 0.96, which was classified as excellent. The ICC for inter-observer reliability was 0.84, which was classified as good. Conclusions: These results suggest that 3D facial images acquired with this system, the iPhone TrueDepth NIR camera in conjunction with the Bellus3D Face app, are clinically accurate and reliable. Judicious use is advised in clinical situations that require high degrees of detail due to a lack of image resolution and a longer acquisition time. Generally, this system possesses the potential to serve as a practical alternative to conventional stereophotogrammetry systems for use in a clinical setting due to its accessibility and relative ease of use and further research is planned to appraise its updated clinical use.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".