Multi-label classification of temporomandibular joint osteoarthritic changes on CBCT: An anatomically guided artificial intelligence framework.
Authors
Affiliations (5)
Affiliations (5)
- Herman Ostrow School of Dentistry, University of Southern California, Los Angeles, CA, USA.
- Computer Science, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA.
- Oral and Maxillofacial Radiology, Herman Ostrow School of Dentistry, University of Southern California, Los Angeles, CA, USA.
- Clinical Dentistry of Orofacial Pain, Herman Ostrow School of Dentistry, University of Southern California, Los Angeles, CA, USA.
- Orofacial Pain and Oral Medicine Clinic, Herman Ostrow School of Dentistry, University of Southern California, Los Angeles, CA, USA.
Abstract
To develop and evaluate an anatomically guided artificial intelligence framework for joint-level detection and multi-label characterization of temporomandibular joint (TMJ) osteoarthritic changes on cone-beam computed tomography (CBCT). CBCT examinations from 71 patients (142 TMJs) were assessed independently by two expert readers for erosion, osteophyte formation, subchondral sclerosis, subchondral cysts, joint-space narrowing, and condylar flattening. Discordant cases underwent third-reader adjudication to establish the reference standard. A 3-dimensional ResNet18 model was trained using patient-level training, validation, and independent test partitions. Joint-level OA-associated features were evaluated. Complete TMJ region-of-interest (ROI) and segmentation-masked condyle inputs were compared. Condylar flattening was analyzed separately. Inter-reader agreement varied by feature, ranging from slight agreement for flattening (κ = -0.01) and joint-space narrowing (κ = 0.15) to substantial agreement for osteophyte formation (κ = 0.63). Automated condyle segmentation achieved a mean Dice similarity coefficient of 0.91 ± 0.042. The joint-level model achieved an area under the receiver operating characteristic curve (AUC) of 0.9325, with sensitivity of 0.8470 and specificity of 0.9081. Feature-level AUCs ranged from 0.6756 to 0.9515. Segmentation-masked condyle input yielded higher classification of erosion (AUC, 0.8685), osteophyte formation (0.9090), subchondral sclerosis (0.9134), and subchondral cysts (0.9515), whereas complete TMJ ROI input performed better for joint-space narrowing (0.8132). This framework extends CBCT assessment beyond binary detection of TMJ OA-associated changes by providing feature-level characterization. Anatomically guided masking showed higher AUCs for abnormalities intrinsic to the mandibular condyle, whereas joint-space narrowing performed better with broader joint context. These observations require confirmation in larger datasets.