Assessment of deep convolutional neural network models for mandibular fracture detection in panoramic radiographs

• Published in: International journal of oral and maxillofacial surgery Vol. 51; no. 11; pp. 1488 - 1494
• Main Authors: Warin, K., Limprasert, W., Suebnukarn, S., Inglam, S., Jantana, P., Vicharueang, S.
• Format: Journal Article
• Language: English
• Published: Denmark Elsevier Inc 01-11-2022
• Subjects: artificial intelligence; deep learning; mandibular fractures; maxillofacial injuries; mandibular fractures; deep learning; artificial intelligence; maxillofacial injuries
• ISSN: 0901-5027; 1399-0020
• DOI: 10.1016/j.ijom.2022.03.056

The aim of this study was to develop automated models for the identification and detection of mandibular fractures in panoramic radiographs using convolutional neural network (CNN) algorithms. A total of 1710 panoramic radiograph images from the years 2016 to 2020, including 855 images containing mandibular fractures, were obtained retrospectively from the regional trauma centre. CNN-based classification models, DenseNet-169 and ResNet-50, were fabricated to identify fractures in the radiographic images. The CNN-based object detection models Faster R-CNN and YOLOv5 were trained to automate the placement of the bounding boxes to detect fractures in the radiographic images. The performance of the models was evaluated on a hold-out test set and also by comparison with residents in oral and maxillofacial surgery and oral and maxillofacial surgeons (experts) on a 100-image subset. The binary classification performance of the models achieved promising results with an area under the receiver operating characteristics curve (AUC), sensitivity, and specificity of 100%. The detection performance of the models achieved an AUC of approximately 90%. When compared with the accuracy of clinician observers, the identification performance of the models outperformed even an expert-level classification. In conclusion, CNN-based models identified mandibular fractures above expert-level performance. It is expected that these models will be used as an aid to improve clinician performance, with aided resident performance approximating that of expert level.