Table 8 Comparative performance of the proposed FCM‑FRWS + MDOT (Fine segmentation) model against deep learning (U‑Net, ResNet, YOLO) and traditional machine learning (SVM) approaches in dental X‑ray segmentation.
Model | Avg. Acc. | Avg. Pre. | Avg. Spec. | Avg. Sen | Avg. Dice | Avg. Acc. |
|---|---|---|---|---|---|---|
FCM-FRWS + MDOT (Fine) | 91.62% | 90.89% | 91.26% | 91.78% | 90.74% | 90.74% |
U-Net | 87.30% | 85.20% | 85.60% | 88.00% | 85.50% | 88.20% |
ResNet-50/101 | 86.50% | 84.00% | 83.20% | 85.00% | 83.50% | 87.10% |
YOLOv3/v5/v8 | 83.00% | 82.10% | 81.50% | 84.00% | 81.00% | 85.00% |
SVM (with handcrafted features) | 76.00% | 75.00% | 74.00% | 78.00% | 73.50% | 76.50% |
