Temporomandibular joint assessment in MRI images using artificial intelligence tools: where are we now? A systematic review
Bibliographic record
Abstract
OBJECTIVES: To summarize the current evidence on the performance of artificial intelligence (AI) algorithms for the temporomandibular joint (TMJ) disc assessment and TMJ internal derangement diagnosis in magnetic resonance imaging (MRI) images. METHODS: Studies were gathered by searching 5 electronic databases and partial grey literature up to May 27, 2024. Studies in humans using AI algorithms to detect or diagnose internal derangements in MRI images were included. The methodological quality of the studies was evaluated using the Quality Assessment Tool for Diagnostic of Accuracy Studies-2 (QUADAS-2) and a proposed checklist for dental AI studies. RESULTS: Thirteen studies were included in this systematic review. Most of the studies assessed disc position. One study assessed disc perforation. A high heterogeneity related to the patient selection domain was found between the studies. The studies used a variety of AI approaches and performance metrics with CNN-based models being the most used. A high performance of AI models compared to humans was reported with accuracy ranging from 70% to 99%. CONCLUSIONS: The integration of AI, particularly deep learning, in TMJ MRI, shows promising results as a diagnostic-assistance tool to segment TMJ structures and classify disc position. Further studies exploring more diverse and multicentre data will improve the validity and generalizability of the models before being implemented in clinical practice.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.031 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.006 | 0.005 |
| Bibliometrics | 0.010 | 0.009 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".