AI-Assisted Detection of Interproximal, Occlusal, and Secondary Caries on Bite-Wing Radiographs: A Single-Shot Deep Learning Approach.

Tooth decay is a common oral disease worldwide, but errors in diagnosis can often be made in dental clinics, which can lead to a delay in treatment. This study aims to use artificial intelligence (AI) for the automated detection and localization of secondary, occlusal, and interproximal (D1, D2, D3)...

Full description

Bibliographic Details
Published in:Journal of Digital Imaging Vol. 37; no. 6; pp. 3146 - 3160
Main Authors: Karakuş, Rabia, Öziç, Muhammet Üsame, Tassoker, Melek
Format: diagnostic images research tables/charts Journal Article
Published: Springer Nature Dec2024
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=182283957&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 182283957
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        08971889
        DOQ
      jtl: Journal of Digital Imaging
      issn: 08971889
      maglogo: N
    pubinfo:
      dt: Dec2024
      vid: 37
      iid: 6
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        182283957
        182283957
        182283957
        10.1007/s10278-024-01113-x
        182283957
      ppf: 3146
      ppct: 14
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: AI-Assisted Detection of Interproximal, Occlusal, and Secondary Caries on Bite-Wing Radiographs: A Single-Shot Deep Learning Approach.
      aug:
        au:
          Karakuş, Rabia
          Öziç, Muhammet Üsame
          Tassoker, Melek
        affil: https://ror.org/013s3zh21 Faculty of Dentistry, Department of Oral and Maxillofacial Radiology, Necmettin Erbakan University, Konya, Turkey
      sug:
        subj:
          Dental Caries Radiography
          Deep Learning
          Radiographic Image Interpretation, Computer-Assisted
          Automation
          Radiography, Bitewing
          Decision Support Systems, Clinical
          Human
          Artificial Intelligence
          Reliability and Validity Evaluation
          Diagnostic Errors Prevention and Control
      ab: Tooth decay is a common oral disease worldwide, but errors in diagnosis can often be made in dental clinics, which can lead to a delay in treatment. This study aims to use artificial intelligence (AI) for the automated detection and localization of secondary, occlusal, and interproximal (D1, D2, D3) caries types on bite-wing radiographs. The eight hundred and sixty bite-wing radiographs were collected from the School of Dentistry database. Pre-processing and data augmentation operations were performed. Interproximal (D1, D2, D3), secondary, and occlusal caries on bite-wing radiographs were annotated by two oral radiologists. The data were split into 80% for training, 10% for validation, and 10% for testing. The AI-based training process was conducted using the YOLOv8 algorithm. A clinical decision support system interface was designed using the Python PyQT5 library, allowing for the use of dental caries detection without the need for complex programming procedures. In the test images, the average precision, average sensitivity, and average F1 score values for secondary, occlusal, and interproximal caries were obtained as 0.977, 0.932, and 0.954, respectively. The AI-based dental caries detection system yielded highly successful results in the test, receiving full approval from dentists for clinical use. YOLOv8 has the potential to increase sensitivity and reliability while reducing the burden on dentists and can prevent diagnostic errors in dental clinics.
      pubtype: Academic Journal
      doctype:
        diagnostic images
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N