Temporomandibular Joint Disorders Multi-Class Classification Using Deep Learning

Bhornsawan Thanathornwong; Treesukon Treebupachatsakul; Thitirat Teechot; Suvit Poomrittigul; Kritsasith Warin; Siriwan Suebnukarn

doi:10.3233/SHTI231261

Temporomandibular Joint Disorders Multi-Class Classification Using Deep Learning

Stud Health Technol Inform. 2024 Jan 25:310:1495-1496. doi: 10.3233/SHTI231261.

Authors

Bhornsawan Thanathornwong¹, Treesukon Treebupachatsakul², Thitirat Teechot², Suvit Poomrittigul³, Kritsasith Warin⁴, Siriwan Suebnukarn⁴

Affiliations

¹ Faculty of Dentistry, Srinakharinwirot University, Bangkok, Thailand.
² School of Engineering, King Mongkut's Institute of Technology, Bangkok, Thailand.
³ Faculty of Science and Technology, Pathumwan Institute of Technology, Bangkok, Thailand.
⁴ Faculty of Dentistry, Thammasat University, Bangkok, Thailand.

PMID: 38269713
DOI: 10.3233/SHTI231261

Abstract

Temporomandibular joint (TMJ) disorders have been misinterpreted by various normal TMJ features leading to treatment failure. This study assessed deep learning algorithms, DenseNet-121 and InceptionV3, for multi-class classification of TMJ normal variations and disorders in 1,710 panoramic radiographs. The overall accuracy of DenseNet-121 and InceptionV3 were 0.99 and 0.95, respectively. The AUC from 0.99 to 1.00, indicating high performance for TMJ disorders classification in panoramic radiographs.

Keywords: Temporomandibular joint disorders; classification; deep learning.

MeSH terms

Algorithms
Deep Learning*
Humans
Temporomandibular Joint Disorders* / diagnostic imaging