Table 2.
Guide of recommended designs for 3D CNN implementations in various forensic topics.
| Area of Forensic Research | Proposed Method | Metrics |
|---|---|---|
| Biological age determination | Regression model by 3D deep CNN | MAE, MSE |
| Sex determination | Deep 3D CNN—conv.layers and outputs class probabilities for both targets | CM such as precision, recall and F1 score |
| 3D cephalometric analysis | Object detection model on 3D CNN that auto.estimates cephalom.measurements | MAE, MSE |
| Face prediction from skull | model on Generative Adversarial Network that synthesize soft/hard tissues | slice-wise Frechet Inception Distance |
| Facial growth prediction | Based on methods stated above 1 | another 1 |
1 Method and metrics are not proposed from the current state of knowledge for Facial growth prediction and need further consideration upon clinical experience from 3D CNN applications.