Automatic segmentation of bone structures in CBCT images

Abstract

Modern surgeries are performed using transplants or implants based on surgical planning with CT images. The CT or CBCT images having bad initial quality greatly decrease the performance of the processing algorithms and affect the quality of the reconstructed 3D models. 3D reconstruction using Manual segmentation takes several hours of work and expertise, which significantly increases the overall cost and time of 3D CAD/CAM based surgical planning and production processes. In this paper, we introduce a procedure as a time- and cost-efficient solution for bone tissue segmentation. The idea of this process is an automated image processing algorithm based on edge detection, mathematical morphology and various image processing operations. Accuracy of the method has been compared to manual segmentation of 40 series. Results (precision 86–95%) show that the algorithm is fast and accurate so it is applicable for surgical planning.

Keywords

• cbct
• 3d surgical planning and construction
• cad/cam
• automated segmentation