Deep Segmentation of the Mandibular Canal: A New 3D Annotated Dataset of CBCT Volumes

Inferior Alveolar Nerve (IAN) canal detection has been the focus of multiple recent works in dentistry and maxillofacial imaging. Deep learning-based techniques have reached interesting results this research field, although small size 3D datasets strongly limited performance these algorithms. Researchers forced to build their own private datasets, thus precluding any opportunity for reproducing fairly comparing proposals. This work describes a novel, large, publicly available mandibular Cone Beam Computed Tomography (CBCT) dataset, with 2D manual annotations, provided by expert clinicians. Leveraging dataset employing deep learning techniques, we are able improve state art on segmentation. The source code which allows exactly reproduce all reported experiments is released as an open-source project, along article.