Detection of Various Dental Conditions on Dental Panoramic Radiography Using Faster R-CNN

Shih Lun Chen, Tsung Yi Chen, Yi Cheng Mao, Szu Yin Lin*, Ya Yun Huang, Chiung An Chen, Yuan Jin Lin, Mian Heng Chuang, Patricia Angela R. Abu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

The dental panoramic radiograph (DPR) is a pivotal diagnostic tool in dentistry. However, despite the growing prevalence of artificial intelligence (AI) across various medical domains, manual methods remain the prevailing means of interpreting DPR images. This study aims to introduce an advanced identification system for detecting seven dental conditions in DPR images by utilizing Faster R-CNN. The primary objectives are to enhance dentists' efficiency and evaluate the performance of various CNN models as foundational training networks. This study contributes significantly to the field in several notable ways. Firstly, including a Butterworth filter in the training process yielded an approximately 7% enhancement in judgment accuracy. Secondly, the proposed enhancement technology tailored to different dental symptoms effectively bolstered the training model's accuracy. Consequently, all dental conditions attained an accuracy rate exceeding 95% in CNN analysis. These accuracy enhancements ranged from 1.34% to 13.24% compared to existing recognition technologies. Thirdly, this study pioneers the application of Faster R-CNN for identifying dental conditions, achieving an impressive accuracy rate of 94.18%. The outcomes of this study mark a substantial advancement compared to prior research and offer dentists a more efficient and convenient means of pre-diagnosing dental conditions.

Original languageEnglish
Pages (from-to)127388-127401
Number of pages14
JournalIEEE Access
Volume11
DOIs
StatePublished - 2023

Keywords

  • CNN
  • Dental panoramic radiograph
  • Faster R-CNN
  • database augmentation
  • image enhancement
  • image segmentation

Fingerprint

Dive into the research topics of 'Detection of Various Dental Conditions on Dental Panoramic Radiography Using Faster R-CNN'. Together they form a unique fingerprint.

Cite this