Characterization of dental pathologies using digital panoramic X-ray images based on texture analysis

Area of Science:

• Dentistry
• Medical Imaging
• Computer Science

Background:

• Dental caries and jaw cysts are common pathologies requiring accurate radiographic diagnosis.
• Panoramic radiography (Orthopantomography/OPG) is widely used but image noise can hinder detection.
• Computer-aided image processing offers potential for enhanced detection and characterization of dental anomalies.

Purpose of the Study:

• To develop and evaluate novel image processing algorithms for detecting dental caries and jaw cysts in panoramic dental images.
• To improve the accuracy and efficiency of diagnosing these common dental pathologies.

Main Methods:

• A novel hybridized negative transformation approach for dental caries detection.
• Statistical texture analysis using Gray Level Co-occurrence Matrix (GLCM) for jaw cyst segmentation.
• Texture features (energy, entropy, homogeneity, contrast, correlation) were extracted for segmentation.

Main Results:

• Both developed algorithms demonstrated satisfactory results in detecting dental caries and segmenting cysts.
• The image processing methods correlated well with diagnoses made by maxillofacial radiologists.
• The texture analysis effectively segmented regions based on texture content, outperforming intensity-based methods for cysts.

Conclusions:

• Computer-aided image processing algorithms can significantly aid in the detection and characterization of dental caries and jaw cysts.
• Hybrid negative transformation and GLCM-based texture analysis are effective tools for analyzing dental panoramic images.
• These advanced image processing techniques show promise for improving diagnostic accuracy in dentistry.