Motion-Robust Dental MRI for Imaging of Paediatric Dental Trauma
Zihan Ning, Rubens Spin-Neto, Jonathan Davies, Saoirse O’Toole, Kathleen E Colford, Sarah McElroy, Alena Uus, Sara Neves Silva, Owen Addison, Jo V HajnalAbstract
Objectives
Dental MRI provides soft-tissue contrast without ionising-radiation, but is susceptible to motion, particularly in paediatric imaging. Independent mandibular motion limits conventional single-rigid-model correction, while tailored strategies remain unexplored for dental MRI. We developed an automated, region-adaptive motion-corrected reconstruction method tailored to dental MRI.
Methods
The proposed method automatically defines the maxillary- and mandibular landmarks, performs region-specific joint motion-corrected reconstruction, and fuses the motion-corrected regions into a single motion-free image. The method has broadly sequence applicability without using external motion-free reference, navigator, or prospective tracking. It was validated with three multi-contrast 3D sequences at 0.55T in adult controlled-motion experiments and paediatric scans. Image quality was assessed using normalised gradient square (NGS) and blinded radiologist scoring. Uncorrected (No-MoCo), full field-of-view single-rigid-model correction (MoCo-fullFOV), and fused region-adaptive correction (MoCo-fused) were compared. Cross-correlation between maxillary and mandibular motion traces classified shared and independent mandibular motion pattern.
Results
Eight healthy adults and 11 paediatric patients, including 10 with traumatic dental injuries and one with delayed dental development, completed 42 acquisitions. Across all acquisitions, MoCo-fused improved NGS compared with No-MoCo (P<.0001) and MoCo-fullFOV (P=.0004). In mandibular-involved motion cases (n = 23), MoCo-fullFOV did not significantly improve image quality, whereas MoCo-fused improved both NGS and radiologist scores compared with No-MoCo. Lower cross-correlation between maxillary and mandibular motion traces was associated with greater NGS improvement for MoCo-fused over MoCo-fullFOV (Spearman r = −0.66, P<.0001). Paediatric examples showed improved visualisation of pulp signal and inflammatory change after motion correction. The method is open-sourced at https://github.com/ZihanNing/dental_MRI_motion_correction.git.
Conclusions
Automated region-adaptive motion-corrected dental MRI improved image quality, particularly with mandibular motion.