Automatic detection of midfacial fractures in facial bone CT images using deep learning-based object detection models

Daiki Morita; Ayako Kawarazaki; Mazen Soufi; Yoshito Otake; Yoshinobu Sato; Toshiaki Numajiri

doi:10.1016/j.jormas.2024.101914

Automatic detection of midfacial fractures in facial bone CT images using deep learning-based object detection models

J Stomatol Oral Maxillofac Surg. 2024 May 13:101914. doi: 10.1016/j.jormas.2024.101914. Online ahead of print.

Authors

Daiki Morita¹, Ayako Kawarazaki², Mazen Soufi³, Yoshito Otake³, Yoshinobu Sato³, Toshiaki Numajiri²

Affiliations

¹ Department of Plastic and Reconstructive Surgery, Kyoto Prefectural University of Medicine, Kyoto, Japan; Department of Plastic and Reconstructive Surgery, Tokai University School of Medicine, Kanagawa, Japan. Electronic address: d-morita@koto.kpu-m.ac.jp.
² Department of Plastic and Reconstructive Surgery, Kyoto Prefectural University of Medicine, Kyoto, Japan.
³ Division of Information Science, Nara Institute of Science and Technology, Nara, Japan.

PMID: 38750725
DOI: 10.1016/j.jormas.2024.101914

Abstract

Background: Midfacial fractures are among the most frequent facial fractures. Surgery is recommended within 2 weeks of injury, but this time frame is often extended because the fracture is missed on diagnostic imaging in the busy emergency medicine setting. Using deep learning technology, which has progressed markedly in various fields, we attempted to develop a system for the automatic detection of midfacial fractures. The purpose of this study was to use this system to diagnose fractures accurately and rapidly, with the intention of benefiting both patients and emergency room physicians.

Methods: One hundred computed tomography images that included midfacial fractures (e.g., maxillary, zygomatic, nasal, and orbital fractures) were prepared. In each axial image, the fracture area was surrounded by a rectangular region to create the annotation data. Eighty images were randomly classified as the training dataset (3736 slices) and 20 as the validation dataset (883 slices). Training and validation were performed using Single Shot MultiBox Detector (SSD) and version 8 of You Only Look Once (YOLOv8), which are object detection algorithms.

Results: The performance indicators for SSD and YOLOv8 were respectively: precision, 0.872 and 0.871; recall, 0.823 and 0.775; F1 score, 0.846 and 0.82; average precision, 0.899 and 0.769.

Conclusions: The use of deep learning techniques allowed the automatic detection of midfacial fractures with good accuracy and high speed. The system developed in this study is promising for automated detection of midfacial fractures and may provide a quick and accurate solution for emergency medical care and other settings.

Keywords: Automatic detection; Deep learning; Facial fracture; Midfacial fracture.