Osteoporosis detection using AI and Panoramic radiographs

A Comprehensive Study on Feature Types for Osteoporosis Classification in Dental Panoramic Radiographs

Authors: Mohammad A. Alzubaidi and Mwaffaq Otoom
Department of Computer Engineering, Yarmouk University, Irbid 21163, Jordan

---

Summary
This study explores how AI-based feature extraction from dental panoramic radiographs can assist in the early detection of osteoporosis — a condition characterized by decreased bone density and fracture risk. Using 575 radiographs (267 osteoporotic and 308 normal), the researchers compared 13 types of image features, such as Gabor filters, Haar wavelets, and steerable filters, combined with SOM/LVQ and SVM models.
The best-performing approach (SOM/LVQ with Gabor features) achieved 92.6% accuracy, 97.1% sensiti... The authors conclude that dental panoramic radiographs, routinely acquired in clinics, could become a low-cost AI-assisted screening tool for identifying early signs of osteoporosis — especially useful in populations where DEXA scans are not readily available.

DOI: https://doi.org/10.1016/j.cmpb.2019.105301

---

Key Words

AI in Dentistry, Panoramic Radiography, Osteoporosis, Bone Density, Gabor Filter, SOM, LVQ, Image Processing, Machine Learning, Medical Imaging

---

Extracted Data

• Year: 2019
• Modality: Panoramic radiography
• Dataset: 575 radiographs (267 osteoporotic / 308 normal)
• Network Architecture: SOM/LVQ and SVM models
• Feature Types: 13 (Gabor filters, Haar wavelets, steerable filters, etc.)
• Metrics: Accuracy = 92.6%; Sensitivity = 97.1%; Specificity = 86.4%
• Task: Classification (osteoporotic vs. normal bone density)
• Project Objective: To evaluate different feature types for AI-based osteoporosis classification using dental panoramic radiographs

---

Clinical Relevance

• Clinical importance: Panoramic radiographs are common in routine dental care and may offer a low-cost alternative for early osteoporosis screening when DEXA is not accessible.
• Scientific contribution: This study demonstrated that texture-based features, especially Gabor filters combined with SOM/LVQ, can accurately identify low bone density patterns in the mandible.
• Practical impact: AI analysis of dental radiographs can expand dentists’ role in systemic health monitoring and support preventive medicine through routine imaging.

---

Related Video

▶️ Watch on YouTube