Automated Detection and Classification of Ponticulus Posticus from Digital Lateral Cephalograms- An Artifical Intelligence Based Retrospective Study
Keywords:
Artificial Intelligence, Ponticulus Posticus, Lateral Cephalogram, Machine Learning, TechnologyAbstract
Context: Ponticulus Posticus (PP) is a clinically significant anatomical variant of vertebrae that may compress the vertebral artery and contribute to cervicogenic headaches. Traditional radiographic assessment of PP is often subjective and inconsistent. This study explores the application of artificial intelligence (AI) for detection and classification of PP from digital lateral cephalograms.
Aim: To evaluate the accuracy of AI in detecting and classifying Ponticulus Posticus from digital lateral cephalograms.
Settings and Design: An artificial intelligence based retrospective study.
Methods and materials: A total of 1052 digital lateral cephalograms were selected, analyzed, and grouped as complete PP, partial PP, or absence of PP. Machine learning models in Orange® software, including Logistic Regression, Neural Network, and Naïve Bayes, were used for detection and classification.
Results: Logistic Regression achieved an accuracy of 98.5%, 98%, and 97.4% in the detection and classification of complete PP, partial PP, and absence of PP, respectively, outperforming Neural network and Naïve Bayes. Logistic Regression also demonstrated higher AUC, F1 score, precision, and recall. ROC curve analysis confirmed its superior classification ability across all PP categories.
Conclusions: AI, particularly Logistic Regression algorithm, is a reliable and promising tool for detecting and classifying Ponticulus Posticus in digital lateral cephalograms. Further validation using larger and more diverse datasets is recommended to enhance diagnostic precision.
Downloads
Metrics
References
Cho YJ. Radiological analysis of ponticulus posticus in Koreans. Yonsei Med J 2009; 50(1):45–9.
Govindraju P, Kumar TSM. Prevalence of ponticulus posticus of the first cervical vertebra: a digital radiographic study. J Indian Acad Oral Med Radiol 2017; 29(2):95–9.
Suazo GI, Schilling J, Schilling A. Ponticulus posticus on the posterior arch of atlas: prevalence analysis in asymptomatic patients. Int J Morphol 2010;28(1):317–22.
Chitroda PK, Katti G, Sreedevi E, Mandlik J, Pawar R, Shetty S. Ponticulus posticus on the posterior arch of atlas: prevalence analysis in symptomatic and asymptomatic patients of Gulbarga population. J Clin Diagn Res 2013; 7(12):3044–7.
Diallo R, Edalo C, Awe O. Machine learning evaluation of imbalanced health data: a comparative analysis of balanced accuracy, MCC, and F1 score. In: Arai K, editor. Proceedings of the Future of Information and Communication Conference (FICC) 2024. Cham: Springer; 2024. p. 283–312.
Macri M, Rendina F, Marini M, Papi P, Pompa G. Prevalence of ponticulus posticus and migraine in 220 orthodontic patients: a cross-sectional study. Biology (Basel) 2023; 12(3):471.
Tassoker M, Kok H, Ozcan S. Investigation of the relationship between sella turcica bridge and ponticulus posticus: a lateral cephalometric study. Int J Morphol 2017; 35(2):337–44.
Elliott RE, Tanweer O. The prevalence of the ponticulus posticus (arcuate foramen) and its importance in the Goel-Harms procedure: meta-analysis and review of the literature. World neurosurg 2014; 82(1-2):e335-43.
Data mining fruitful And fun. (1996). Accessed: July 09, 2025: https://orangedatamining.com/.
Xu X, Zhu Y, Ding X, Yin M, Mo W, Ma J. Research Progress of Ponticulus Posticus: A Narrative Literature Review. Front Surg 2022; 9:834551. doi: 10.3389/fsurg.2022.834551.
Shahidi S, Hasani M, Khozaei M. Evaluating the relation between the elongated styloid process and the ponticulus posticus using cone-beam computed tomography. Folia Morphologica 2022; 81(1):196-202.
Sharma V, Chaudhary D, Mitra R. Prevalence of ponticulus posticus in Indian orthodontic patients. Dentomaxillofac Radiol 2010; 39(5):277-83.
Singh R. Logistic regression-based detection of sella turcica bridging on cephalograms. Dentomaxillofac Radiol 2022; 51(2):20210235.
Singh P, Gupta V, Sharma S. Neural network classification of temporomandibular joint disorders on MRI images. J Oral Rehabil 2021; 48(7):826–33.
Kumar N, Verma S, Rai A. Naive Bayes algorithm for screening osteoporosis on panoramic radiographs. Oral Radiol 2020; 36(4):365–72.
Jeevitha S J, Kumar L, Yadalam PK, kumar Yadalam P. Artificial intelligence: a reliable tool to detect the elongation of the styloid process. Cureus 2023; 15(11):e94541.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
