Algorithmic analysis for dental caries detection using an adaptive neural network architecture.

Area of Science:

• Biomedical imaging
• Artificial Intelligence in Dentistry

Background:

• Dental caries detection is crucial for oral health.
• Existing methods require enhancement for accuracy and efficiency.

Purpose of the Study:

• To evaluate an AI model for accurate caries detection.
• To assess the performance of Adaptive Dragonfly algorithm and Neural Network classifier.

Main Methods:

• A two-phase methodology: feature extraction and classification.
• Utilized a database of 120 dental images, randomly split into sets.
• Employed the MPCA with Nonlinear Programming and Adaptive DA (MNP-ADA) model.

Main Results:

• The MNP-ADA model demonstrated superior performance compared to conventional models (PCA-ADA, LDA-ADA, ICA-ADA).
• Performance was evaluated using metrics like accuracy, sensitivity, specificity, and MCC.
• The proposed model achieved better results across all test types.

Conclusions:

• AI and Neural Network algorithms show significant potential for dental caries detection and diagnosis.
• The novel MNP-ADA model effectively distinguishes dental caries using image processing.