YOLOv8 Model Detects and Classifies TMJ Disc Displacement on Open-Mouth MRI

A YOLOv8 model achieved precision 0.983, recall 0.988, F1 0.987 for classifying TMJ disc displacement with vs without reduction on open-mouth MRI (n=237 patients).

• The model was trained on 280, validated on 71, and tested on 88 proton-density-weighted MRI images from 237 patients with TMJ disc displacement.
• The task combined automated TMJ localization and classification into disc displacement with reduction (DDwR) vs without reduction (DDwoR).
• Internal validation only; no external or prospective testing was reported.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.