Segmenting the Inferior Alveolar Canal in CBCTs Volumes: The ToothFairy Challenge
| Tipo de publicação: | Artigo |
| Citação: | In recent years, several algorithms have been developed for the segmentation of the Inferior Alveolar Canal (IAC) in Cone-Beam Computed Tomography (CBCT) scans. However, the availability of public datasets in this domain is limited, resulting in a lack of |
| Journal: | IEEE Transactions on Medical Imaging |
| Volume: | Volume 44, Issue : 4, Arpil 2025 |
| Ano: | 2025 |
| Mês: | April |
| Páginas: | 1890-1906 |
| ISSN: | https://pubmed.ncbi.nlm.nih.gov/ |
| URL: | https://ieeexplore.ieee.org/do... |
| DOI: | https://doi.org/10.1109/TMI.2024.3523096 |
| Resumo: | In recent years, several algorithms have been developed for the segmentation of the Inferior Alveolar Canal (IAC) in Cone-Beam Computed Tomography (CBCT) scans. However, the availability of public datasets in this domain is limited, resulting in a lack of comparative evaluation studies on a common benchmark. To address this scientific gap and encourage deep learning research in the field, the ToothFairy challenge was organized within the MICCAI 2023 conference. In this context, a public dataset was released to also serve as a benchmark for future research. The dataset comprises 443 CBCT scans, with voxel-level annotations of the IAC available for 153 of them, making it the largest publicly available dataset of its kind. The participants of the challenge were tasked with developing an algorithm to accurately identify the IAC using the 2D and 3D-annotated scans. This paper presents the details of the challenge and the contributions made by the most promising methods proposed by the participants. It represents the first comprehensive comparative evaluation of IAC segmentation methods on a common benchmark dataset, providing insights into the current state-of-the-art algorithms and outlining future research directions. Furthermore, to ensure reproducibility and promote future developments, an open-source repository that collects the implementations of the best submissions was released. |
| Palavras-chave: | 3D Network , 3D U-Net Author Keywords Segmentation , algorithms, Annotation Process , Annotations , Benchmark testing , Challenge Participants , Common Benchmark , computed tomography MeSH Terms Cone-Beam Computed Tomography , Cone-beam Computed Tomography Images , Cone-beam Computed Tomography Volume , Data Augmentation , Deep Learning, Deep Neural Network, Dice Loss , Dice Similarity Coefficient , Domain Dataset , EEE Keywords Three-dimensional displays , Final Ranking , Focal Loss , Humans, image segmentation, Imaging, Inferior Alveolar Canal , Inferior Alveolar Nerve , Intersection Over Union , Irrigation , Mandible , Mandibular Canal , Medical Experts , Mental Foramen , Neural Network, Panoramic Radiographs , Private Dataset , Proposals Index Terms Inferior Alveolar , Public Datasets , semi-supervised learning, Sparse Labeling , Statistical Shape Model , Surgery , Teeth , Three-Dimensional , tooth , training, Training Data , Training Set , X-ray imaging |
| Autores | |
| Adicionado por: | [] |
| Total mark: | 0 |
|
Anexos
|
|
|
|
|
Notas
|
|
|
|
|
|
Tópicos
|
|
|
|
|
