Multimodal deep learning for midpalatal suture assessment in maxillary expansion

Accurate midpalatal suture maturation assessment is critical for orthodontic treatment planning, yet current manual staging methods exhibit substantial inter-examiner variability (kappa values 0.3-0.8), compromising treatment decision reliability. This study developed and validated DeepMSM, an automated multimodal deep learning framework integrating cone-beam computed tomography with clinical indicators for standardized midpalatal suture staging. We retrospectively analyzed cone-beam computed tomography and lateral cephalometric radiographs from 200 orthodontic patients aged 7-36 years. The DeepMSM framework integrated multimodal images with clinical variables including age, gender, cervical vertebral maturation stage, and mandibular third molar stage using attention-based fusion strategies. DeepMSM achieved 93.75% accuracy and 93.81% F1-score, substantially outperforming single-modality approaches (47.50%-71.25% accuracy) and dual-modality models (73.75-81.25% accuracy). The system demonstrated excellent performance in distinguishing critical stages C and D with F1-scores of 92%-93%, representing the decision point between conventional expansion and surgical intervention. All clinical parameters showed significant correlations with midpalatal suture maturation (p<0.05). DeepMSM, a novel multimodal midpalatal suture maturation assessment system, achieved a high accuracy of 93.75%, demonstrating the potential to reduce diagnostic variability and improve treatment reliability. This automated framework particularly benefits less experienced clinicians in making critical treatment decisions for maxillary expansion therapy.