Skip to main content
. 2020 Nov 15;17(22):8447. doi: 10.3390/ijerph17228447

Table 1.

Accuracy, precision, recall, and mean average precision (mAP) for both the teeth detection model and inflammation detection model.

Training * Testing * Accuracy Precision Recall mAP
Teeth Detection Model Teeth 107 27 100% 100% 51.85% 100%
Inflammation Detection Model Inflamed 226 79 78.46% 87.14% 35.05% 57.44%
Non-Inflamed 416 83 75.79% 88.91% 48.47% 78.94%
Overall Total 642 162 77.12% 88.02% 41.75% 68.19%

* Number of bounding boxes/annotations.