Detection and classification of mandibular fractures in panoramic radiography using artificial intelligence

This study evaluated the performance of the YOLOv5 deep learning model in detecting different mandibular fracture types in panoramic images.

The dataset of panoramic radiographs with mandibular fractures was divided into training, validation, and testing sets, with 60%, 20%, and 20% of the images, respectively. An equal number of control images without fractures were also distributed among the datasets. The YOLOv5 algorithm was trained to detect six mandibular fracture types based on the anatomical location including symphysis, body, angle, ramus, condylar neck, and condylar head. Performance metrics of accuracy, precision, sensitivity (recall), specificity, dice coefficient (F1 score), and area under the curve (AUC) were calculated for each class.

A total of 498 panoramic images containing 673 fractures were collected. The accuracy was highest in detecting body (96.21%) and symphysis (95.87%), and was lowest in angle (90.51%) fractures. The highest and lowest precision values were observed in detecting symphysis (95.45%) and condylar head (63.16%) fractures, respectively. The sensitivity was highest in the body (96.67%) fractures and was lowest in the condylar head (80.00%) and condylar neck (81.25%) fractures. The highest specificity was noted in symphysis (98.96%), body (96.08%), and ramus (96.04%) fractures, respectively. The dice coefficient and AUC were highest in detecting body fractures (0.921 and 0.942, respectively), and were lowest in detecting condylar head fractures (0.706 and 0.812, respectively).

The trained algorithm achieved promising results in detecting most fracture types, particularly in body and symphysis regions indicating machine learning potential as a diagnostic aid for clinicians.