Root Canal Segmentation in CBCT Images by 3D U-Net with Global and Local Combination Loss

Accurate root canal segmentation provides an important assistance for root canal therapy. The existing research such as level set method have made effective progress in tooth and root canal segmentation. In the current situation, however, doctors are required to specify an initial area for the target root canal manually. In this paper, we propose a fully automatic and high precision root canal segmentation method based on deep learning and hybrid level set constraints. We set up the global image encoder and local region decoder for global localization and local segmentation, and then combine the contour information generated by level set. Through using CLAHE algorithm and a combination loss based on dice loss, we solve the class imbalance problem and improved recognition ability. More accurate and faster root canal segmentation is implemented under the framework of multi-task learning and evaluated by experiments on 78 Cone Beam CT images. The experimental results show that the proposed 3D U-Net had higher segmentation performance than state of the art algorithms. The average dice similarity coefficient (DSC) is 0.952.