Dataset¶

The ToothFairy2 Dataset is divided into a training and a test set.

The training set, ToothFairy2 Dataset, is publicly available under a CC BY-SA license here. Please note that a sign-up will be required to download it. Any publication using our data must explicitly reference this challenge and cite [1, 2, 3]. 

The test set will not be publicly released and will remain private even after the end of the challenge.

Both training and test data have a voxel spacing of 0.3mm isotropic.

[1] Bolelli, F., Lumetti, L., van Nistelrooij, N. et al. Multi-structure segmentation in CBCT volumes: The ToothFairy2 challenge. Medical Image Analysis, 104095. https://doi.org/10.1016/j.media.2026.104095

[2] Bolelli, F., Marchesini, K., van Nistelrooij, N., Lumetti, L., Pipoli, V., Ficarra, E., Vinayahalingam, S., & Grana, C. (2025). Segmenting Maxillofacial Structures in CBCT Volumes. In: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

[3] Lumetti, L., Pipoli, V., Bolelli, F., Ficarra, E., & Grana, C. (2024). Enhancing Patch-Based Learning for the Segmentation of the Mandibular Canal. IEEE Access.  https://doi.org/10.1109/ACCESS.2024.3408629