Detecting anteriorly displaced temporomandibular joint discs using super-resolution magnetic resonance imaging: a multi-center study

Yang Li; Wen Li; Li Wang; Xinrui Wang; Shiyu Gao; Yunyang Liao; Yihan Ji; Lisong Lin; Yiming Liu; Jiang Chen

doi:10.3389/fphys.2023.1272814

Detecting anteriorly displaced temporomandibular joint discs using super-resolution magnetic resonance imaging: a multi-center study

Front Physiol. 2024 Jan 5:14:1272814. doi: 10.3389/fphys.2023.1272814. eCollection 2023.

Authors

Yang Li^#^{1

2

3}, Wen Li^#^{1

2

3

4}, Li Wang³, Xinrui Wang⁵, Shiyu Gao⁶, Yunyang Liao⁴, Yihan Ji⁴, Lisong Lin⁴, Yiming Liu³, Jiang Chen^{1

2}

Affiliations

¹ School and Hospital of Stomatology, Fujian Medical University, Fuzhou, China.
² Fujian Key Laboratory of Oral Diseases, School and Hospital of Stomatology, Fujian Medical University, Fuzhou, China.
³ Department of Oral and Maxillofacial Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
⁴ Department of Oral and Maxillofacial Surgery, The First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
⁵ Department of Oral and Maxillofacial Surgery, Shenzhen Stomatology Hospital, Shenzhen, China.
⁶ School of Mathematics and Statistics, Huazhong University of Science and Technology, Wuhan, China.

^# Contributed equally.

Abstract

Background: Magnetic resonance imaging (MRI) plays a crucial role in diagnosing anterior disc displacement (ADD) of the temporomandibular joint (TMJ). The primary objective of this study is to enhance diagnostic accuracy in two common disease subtypes of ADD of the TMJ on MRI, namely, ADD with reduction (ADDWR) and ADD without reduction (ADDWoR). To achieve this, we propose the development of transfer learning (TL) based on Convolutional Neural Network (CNN) models, which will aid in accurately identifying and distinguishing these subtypes. Methods: A total of 668 TMJ MRI scans were obtained from two medical centers. High-resolution (HR) MRI images were subjected to enhancement through a deep TL, generating super-resolution (SR) images. Naive Bayes (NB) and Logistic Regression (LR) models were applied, and performance was evaluated using receiver operating characteristic (ROC) curves. The model's outcomes in the test cohort were compared with diagnoses made by two clinicians. Results: The NB model utilizing SR reconstruction with 400 × 400 pixel images demonstrated superior performance in the validation cohort, exhibiting an area under the ROC curve (AUC) of 0.834 (95% CI: 0.763-0.904) and an accuracy rate of 0.768. Both LR and NB models, with 200 × 200 and 400 × 400 pixel images after SR reconstruction, outperformed the clinicians' diagnoses. Conclusion: The ResNet152 model's commendable AUC in detecting ADD highlights its potential application for pre-treatment assessment and improved diagnostic accuracy in clinical settings.

Keywords: MRI; anterior disc displacement; super-resolution; temporomandibular joint; transfer learning.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This study was supported by the Fujian Medical University Starting Fund (2019QH1099), the Medical Innovation Program of Fujian Health and Family Planning Commission (No.2021CXA035), the National Natural Science Foundation of China (U1904145) and the Fujian Provincial Science and Technology Innovation Joint Fund (2019Y9128).