Automatic segmentation of the mandible from computed tomography scans for 3D virtual surgical planning using the convolutional neural network

Abstract

Segmentation of mandibular bone in CT scans is crucial for 3D virtual surgical planning of craniofacial tumor resection and free flap reconstruction of the resection defect, in order to obtain a detailed surface representation of the bones. A major drawback of most existing mandibular segmentation methods is that they require a large amount of expert knowledge for manual or partially automatic segmentation. In fact, due to the lack of experienced doctors and experts, high quality expert knowledge is hard to achieve in practice. Furthermore, segmentation of mandibles in CT scans is influenced seriously by metal artifacts and large variations in their shape and size among individuals. In order to address these challenges we propose an automatic mandible segmentation approach in CT scans, which considers the continuum of anatomical structures through different planes. The approach adopts the architecture of the U-Net and then combines the resulting 2D segmentations from three orthogonal planes into a 3D segmentation. We implement such a segmentation approach on two head and neck datasets and then evaluate the performance. Experimental results show that our proposed approach for mandible segmentation in CT scans exhibits high accuracy.