Neutrosophic‑Enhanced Cephalometric Analysis with Improved Diagnostic Accuracy for  Egyptian Population

Nagham Ahmed Abdelmegeed; Amal F. Abdel-Gawad; Mohamed Alaa Fahmy El-Ghamry

Authors

Nagham Ahmed Abdelmegeed Computer Science Department, Faculty of Computers and Artificial Intelligence -Sohag University, Egypt;
Amal F. Abdel-Gawad Decision Support Department, Faculty of Computers and Informatics, Zagazig University, Zagazig;
Mohamed Alaa Fahmy El-Ghamry Department of computer science, faculty of computers and informatics Zagazig University, Egypt;

Keywords:

Cephalometric analysis; Neutrosophic logic; Medical imaging; Orthodontic diagnosis; Decision-support systems; Egyptian population; Automated landmark detection; Artificial intelligence.

Abstract

Cephalometric analysis is a fundamental diagnostic tool in orthodontics and craniofacial
research, yet its accuracy is frequently limited by uncertainties in landmark detection and
population-specific anatomical variations. This study introduces the NeutrosophicEnhanced Cephalometric Analysis (N-ECA) software, designed to address these
limitations by integrating neutrosophic logic with automated cephalometric evaluation.
The proposed approach applies neutrosophic preprocessing, landmark detection, and
angular measurement, followed by diagnostic classification using a neutrosophic
decision-support framework.
The system was validated on a dataset of 120 lateral cephalometric radiographs of
Egyptian patients (aged 12–25 years), achieving improved accuracy (96.9%) compared to
traditional methods such as Downs (87%) and commercial platforms (85%). Statistical
analysis confirmed the improvement was significant (p < 0.05). Results confirm that NECA effectively reduces errors caused by anatomical diversity, radiographic noise, and
operator subjectivity.
This research highlights the potential of neutrosophic frameworks in enhancing
orthodontic diagnostics, offering a culturally adapted, reproducible, and clinically reliable
tool for cephalometric analysis.

DOI: 10.5281/zenodo.17069339