Automatic detection of the third molar and mandibular canal on panoramic radiographs based on deep learning.

Journal: Journal of stomatology, oral and maxillofacial surgery
PMID:

Abstract

PURPOSE: This study aims to develop a deep learning framework for the automatic detection of the position relationship between the mandibular third molar (M3) and the mandibular canal (MC) on panoramic radiographs (PRs), to assist doctors in assessing and planning appropriate surgical interventions.

Authors

  • Xinle Fang
    School of Information Science and Engineering, Shandong University, Qingdao, China.
  • Shengben Zhang
    Department of Implantology, School and Hospital of Stomatology, Cheeloo College of Medicine, Shandong University, Jinan, China.
  • Zhiyuan Wei
    School of Information Science and Engineering, Shandong University, Qingdao, China.
  • Kaixin Wang
    School of Information Science and Engineering, Shandong University, Qingdao, China.
  • Guanghui Yang
    School of Physical Education, Yanshan University, Qinhuangdao, Hebei 066004, China.
  • Chengliang Li
    School of Information Science and Engineering, Shandong University, Qingdao, China.
  • Min Han
    National Laboratory of Solid State Microstructures, College of Engineering and Applied Sciences, Nanjing University, 22 Hankou Road, Nanjing 210093, P. R. China.
  • Mi Du
    Department of Implantology, School and Hospital of Stomatology, Cheeloo College of Medicine, Shandong University, Jinan, China; Shandong Key Laboratory of Oral Tissue Regeneration, Jinan, China; Shandong Engineering Laboratory for Dental Materials and Oral Tissue Regeneration, Jinan, China; Shandong Provincial Clinical Research Center for Oral Diseases, Jinan, China. Electronic address: mi.du@sdu.edu.cn.