ToothFairy: A Cone-Beam Computed Tomography Segmentation Challenge

This is the first edition of the ToothFairy challenge organized by the University of Modena and Reggio Emilia with the collaboration of Radboud University Medical Center. The challenge is hosted by grand-challenge and is part of MICCAI2023.

Cone Beam Computed Tomography (CBCT) has become increasingly important for treatment planning and diagnosis in implant dentistry and maxillofacial surgery. The three-dimensional information acquired with CBCT can be crucial to plan a vast number of surgical interventions with the aim of preserving noble anatomical structures such as the Inferior Alveolar Canal (IAC), an osseous structure of the mandible which contains the homonymous nerve (Inferior Alveolar Nerve, IAN), artery, and vein. Identifying the canal ensures its preservation in cases of impacted third molar extraction, implant positioning or removal of cystic lesions by preventing damages to dental or neural structures that would significantly reduce the quality of life.

Deep learning models can support medical personnel in surgical planning procedures by providing a voxel-level segmentation of the IAN, which is more accurate than bi-dimensional annotations commonly used in daily clinical practice. Unfortunately, the small extent of available 3D maxillofacial datasets has strongly limited the performance of deep learning-based techniques. On the other hand, a huge amount of sparsely 2D-annotated data is produced daily in the maxillofacial practice. The incomplete detection of nerve positioning is often sufficient to facilitate a positive outcome of surgical intervention, but it is not an accurate anatomical representation. Nevertheless, 2D annotations fail to identify a considerable amount of inner information about the IAN position and the bone structure. Additionally, deep learning approaches frame the presence of dense 3D annotations as a crucial factor. Still, the availability of such annotations is strongly limited by the huge amount of time required. The challenge we propose aims at pushing the development of deep learning frameworks to segment the inferior alveolar nerve by incrementally extending the amount of publicly available 3D-annotated CBCT scans.