An Artificial Intelligence System for Staging the Spheno‐Occipital Synchondrosis
Orthodontics & Craniofacial Research · 2025
DOI: 10.1111/ocr.70018 ↗At a glance
Journal article in Orthodontics & Craniofacial Research, 2025. Written by Omid Halimi Milani and 8 co-authors. Institution: Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, Illinois, USA. Major MEDLINE topics: Cone-Beam Computed Tomography, Sphenoid Bone, Deep Learning, Occipital Bone. Cited 1 times so far (Crossref); 28 references. The full text is freely available (open access, CC BY 4.0). Funded by: American Association of Orthodontists Foundation.
Abstract (original language)
Objective
The aim of this study was to develop, test and validate automated interpretable deep learning algorithms for the assessment and classification of the spheno‐occipital synchondrosis (SOS) fusion stages from a cone beam computed tomography (CBCT). Study Design The sample consisted of 723 CBCT scans of orthodontic patients from private practices in the midwestern United States. The SOS fusion stages were classified by two orthodontists and an oral and maxillofacial radiologist. The advanced deep learning models employed consisted of ResNet, EfficientNet and ConvNeXt. Additionally, a new attention‐based model, ConvNeXt + Conv Attention, was developed to enhance classification accuracy by integrating attention mechanisms for capturing subtle medical imaging features. Laslty, YOLOv11 was integrated for fully‐automated region detection and segmentation.
Results
ConvNeXt + Conv Attention outperformed the other models and achieved a 88.94% accuracy with manual cropping and 82.49% accuracy in a fully automated workflow.
Conclusion
This study introduces a novel artificial intelligence‐based pipeline that reliably automates the classification of the SOS fusion stages using advanced deep learning models, with the highest accuracy achieved by ConvNext + Conv Attention. These models enhance the efficiency, scalability and consistency of SOS staging while minimising manual intervention from the clinician, underscoring the potential for AI‐driven solutions in orthodontics and clinical workflows.
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, Illinois, USA.
- Department of Orthodontics, College of Dentistry, University of Illinois Chicago, Chicago, Illinois, USA.
- Department of Periodontics, College of Dentistry, University of Illinois Chicago, Chicago, Illinois, USA.
- Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Kutahya Health Sciences University, Kutahya, Turkey.
- Department of Orthodontics, Faculty of Dentistry, Tanta University, Tanta, Egypt.
ORCID profiles: Veerasathpurush Allareddy, Rashid Ansari, Mohammed H Elnagar
Funding
- American Association of Orthodontists Foundation
Cite
APA
Milani, O. H., Mills, L., Nikho, A., Tliba, M., Ayyildiz, H., Allareddy, V., Ansari, R., Cetin, A. E., & Elnagar, M. H. (2025). An Artificial Intelligence System for Staging the Spheno‐Occipital Synchondrosis. Orthodontics & Craniofacial Research. https://doi.org/10.1111/ocr.70018
Vancouver
Milani OH, Mills L, Nikho A, Tliba M, Ayyildiz H, Allareddy V, et al. An Artificial Intelligence System for Staging the Spheno‐Occipital Synchondrosis. Orthodontics & Craniofacial Research. 2025. doi:10.1111/ocr.70018
BibTeX
@article{Milani2025,
author = {Milani, Omid Halimi and Mills, Lauren and Nikho, Amanda and Tliba, Marouane and Ayyildiz, Halil and Allareddy, Veerasathpurush and Ansari, Rashid and Cetin, Ahmet Enis and Elnagar, Mohammed H},
title = {An Artificial Intelligence System for Staging the Spheno‐Occipital Synchondrosis},
journal = {Orthodontics & Craniofacial Research},
year = {2025},
doi = {10.1111/ocr.70018}
}
EUVIMED