Tooth cavities detection based on digital image processing and artificial intelligence techniques

Area of Science:

• Dentistry
• Medical Image Processing
• Artificial Intelligence

Background:

• Dental caries result from sugar-fueled bacterial activity eroding tooth structure.
• Medical imaging aids in accurate diagnosis and treatment planning for oral healthcare.
• Automated systems can reduce clinician workload and diagnostic errors.

Purpose of the Study:

• To develop an automated system for detecting dental diseases using machine learning.
• To improve the speed and accuracy of diagnosing dental abnormalities like cavities.
• To reduce human error and clinician workload in dental diagnostics.

Main Methods:

• Preprocessing dental radiographs: noise reduction, greyscale conversion, filtering, resizing.
• Feature extraction using Wavelet analysis, Gray-Level Co-Occurrence Matrix (GLCM), and texture analysis.
• Training and evaluating Support Vector Machine (SVM) and Neural Network (NN) classifiers.

Main Results:

• The automated system achieved 80% accuracy with SVM and 77% with NN when combining all extracted features.
• The system successfully classifies dental X-ray images as normal or abnormal.
• Identification of specific abnormalities, such as dental caries, was demonstrated.

Conclusions:

• The proposed automated system offers faster and more reliable dental disease detection compared to conventional methods.
• This AI-driven approach can support clinical decision-making for dentists.
• The system has the potential to enhance the overall quality of patient care in dentistry.