EUVIMEDEUVIMED entdecken
Randomisierte kontrollierte Studie

Deep learning for osteoarthritis classification in temporomandibular joint

Won Jung iD, Kyung-Eun Lee iD, Bong-Jik Suh iD, Hyun Seok iD, Dae-Woo Lee iD

Oral Diseases · 2023-04 · 29 (3) · 1050-1059

DOI: 10.1111/odi.14056 ↗

Kurz gefasst

Randomisierte kontrollierte Studie in der Zeitschrift Oral Diseases, 2021-11. Verfasst von Won Jung und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral Medicine, School of Dentistry, Jeonbuk National University, Jeonju, Korea. Hauptthemen laut MEDLINE: Deep Learning, Osteoarthritis, Temporomandibular Joint Disorders. Die Arbeit wurde bisher 66-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Biomedical Research Institute, Korean Government (MSIT), Novartis Institutes for BioMedical Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

This study aimed to develop a diagnostic support tool using pretrained models for classifying panoramic images of the temporomandibular joint (TMJ) into normal and osteoarthritis (OA) cases. Subjects and Methods A total of 858 panoramic images of the TMJ (395 normal and 463 TMJ‐OA) were obtained from 518 individuals from January 2015 to December 2018. The data were randomly divided into training, validation, and testing sets (6:2:2). We used pretrained Resnet152 and EfficientNet‐B7 as transfer learning models. The accuracy, specificity, sensitivity, area under the curve, and gradient‐weighted class activation mapping (grad‐CAM) of both trained models were evaluated. The performances of the trained models were compared to that of dentists (both TMD specialists and general dentists).

Results

The classification accuracies of ResNet‐152 and EfficientNet‐B7 were 0.87 and 0.88, respectively. The trained models exhibited the highest accuracy in OA classification. In the grad‐CAM analysis, the trained models focused on specific areas in osteoarthritis images where erosion or osteophyte were observed.

Conclusions

The artificial intelligence model improved the diagnostic power of TMJ‐OA when trained with two‐dimensional panoramic condyle images and can be effectively applied by dentists as a screening diagnostic tool for TMJ‐OA.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningOsteoarthritisTemporomandibular Joint DisordersHumansArtificial IntelligenceTemporomandibular Joint

Stichwörter der Autor:innen

artificial intelligencecomputer-aidedconvolutional neural networkdiagnosisosteoarthritistemporomandibular joint

Autor:innen und Institutionen

  • Department of Oral Medicine, School of Dentistry, Jeonbuk National University, Jeonju, Korea.
  • Research Institute of Clinical Medicine of Jeonbuk National University-Biomedical Research and Institute of Jeonbuk National University Hospital, Jeonju, South Korea.
  • Department of Oral and Maxillofacial Surgery, School of Dentistry, Jeonbuk National University, Jeonju, Korea.
  • Department of Pediatric Dentistry, School of Dentistry, Jeonbuk National University, Jeonju, Korea.

ORCID-Profile: Won Jung, Kyung-Eun Lee, Bong-Jik Suh, Hyun Seok, Dae-Woo Lee

Förderung

  • Biomedical Research Institute
  • Korean Government (MSIT)
  • Novartis Institutes for BioMedical Research

Zitieren

APA

Jung, W., Lee, K. E., Suh, B. J., Seok, H., & Lee, D. W. (2023). Deep learning for osteoarthritis classification in temporomandibular joint. Oral Diseases, 29(3), 1050-1059. https://doi.org/10.1111/odi.14056

Vancouver

Jung W, Lee KE, Suh BJ, Seok H, Lee DW. Deep learning for osteoarthritis classification in temporomandibular joint. Oral Diseases. 2023;29(3):1050-1059. doi:10.1111/odi.14056

BibTeX
@article{Jung2023,
  author = {Jung, Won and Lee, Kyung-Eun and Suh, Bong-Jik and Seok, Hyun and Lee, Dae-Woo},
  title = {Deep learning for osteoarthritis classification in temporomandibular joint},
  journal = {Oral Diseases},
  year = {2023},
  volume = {29},
  number = {3},
  pages = {1050--1059},
  doi = {10.1111/odi.14056}
}
Kostenlos starten →