Development a computer-aided diagnosis system for dental caries detection applying radiographic images

Area of Science:

• Dentistry
• Medical Imaging
• Artificial Intelligence

Background:

• Delayed diagnosis of dental caries leads to severe complications, including tooth loss.
• Manual interpretation of radiographic images for caries detection is error-prone due to human factors.
• Automated diagnostic tools are essential for accurate and efficient dental caries detection.

Purpose of the Study:

• To develop an intelligent computer-aided diagnosis (CAD) system for detecting dental caries in radiographic images.
• To enhance diagnostic accuracy and efficiency in clinical dental practice.

Main Methods:

• Utilized advanced image processing and machine learning techniques for analyzing radiographic images.
• Applied preprocessing for artifact removal and image enhancement.
• Employed Sauvola thresholding and Canny edge detection for tooth segmentation.
• Extracted texture and chaotic indices for feature extraction.
• Used Non-dominated Sorting Genetic Algorithm II (NSGA II) for feature selection.
• Evaluated performance using 10-fold cross-validation and Support Vector Machine (SVM) classifier.

Main Results:

• The developed CAD system effectively distinguished between healthy and decayed teeth.
• The Support Vector Machine (SVM) classifier achieved a highest accuracy of 93.33% in caries detection.
• The system demonstrated robustness and precision in identifying dental decay.

Conclusions:

• The intelligent CAD system offers a reliable and precise tool for dental caries detection.
• This technology has the potential to significantly improve diagnostic reliability in modern clinical settings.
• Automated caries detection can aid dentists in timely and effective treatment planning.