Metal Artifact Reduction and Segmentation of Dental Computerized Tomography Images Using Least Square Support Vector...

Area of Science:

• Medical Imaging
• Computer-Aided Diagnosis
• Dental Technology

Background:

• Accurate segmentation and 3D visualization of teeth from dental CT images are crucial for diagnosing abnormalities and planning treatments like dental implants and orthodontics.
• Dental CT image segmentation presents challenges due to the unique structural characteristics of teeth.

Purpose of the Study:

• To develop an automatic method for segmenting teeth in dental CT images.
• To enhance the accuracy and efficiency of dental image analysis for clinical applications.

Main Methods:

• A multi-step approach involving preprocessing for metal artifact reduction using least square support vector machine.
• Tooth region candidate detection via integral intensity profile.
• Tooth region partitioning using the mean shift algorithm.
• Application of segmented slices for 3D teeth visualization.

Main Results:

• The proposed method demonstrated precise segmentation results on various sample slices across 14 cone-beam CT datasets.
• Significant improvements in segmentation accuracy were achieved: 83.24% sensitivity, 98.35% specificity, 72.77% precision, and 97.62% accuracy.
• A reduction in the segmentation error rate by 2.34% was observed.
• The method showed superior performance compared to existing approaches, particularly with the inclusion of metal artifact reduction.

Conclusions:

• The developed automatic segmentation method is effective for dental CT images.
• The approach offers improved accuracy and performance over existing methods, aiding in precise diagnosis and treatment planning.
• Metal artifact reduction in preprocessing further enhances segmentation accuracy.