EUVIMEDEUVIMED entdecken
Crossref

Individual Graph Representation Learning for Pediatric Tooth Segmentation From Dental CBCT

Yusheng Liu, Shu Zhang, Xiyi Wu, Tao Yang, Yuchen Pei, Huayan Guo, Yuxian Jiang, Zhien Feng, Wen Xiao, Yu-Ping Wang, Lisheng Wang

IEEE Transactions on Medical Imaging · 2025-03 · 44 (3) · 1432-1444

DOI: 10.1109/tmi.2024.3501365 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025-03. Verfasst von Yusheng Liu und 10 weiteren Autor:innen. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Tooth. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Nature Science Foundation of China, Shanghai Jiao Tong University Translation Medicine Awards Research, Innovation Foundation of Beijing Stomatological Hospital, Capital Medical University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Pediatric teeth exhibit significant changes in type and spatial distribution across different age groups. This variation makes pediatric teeth segmentation from cone-beam computed tomography (CBCT) more challenging than that in adult teeth. Existing methods mainly focus on adult teeth segmentation, which however cannot be adapted to spatial distribution of pediatric teeth with individual changes (SDPTIC) in different children, resulting in limited accuracy for segmenting pediatric teeth. Therefore, we introduce a novel topology structure-guided graph convolutional network (TSG-GCN) to generate dynamic graph representation of SDPTIC for improved pediatric teeth segmentation. Specifically, this network combines a 3D GCN-based decoder for teeth segmentation and a 2D decoder for dynamic adjacency matrix learning (DAML) to capture SDPTIC information for individual graph representation. 3D teeth labels are transformed into specially-designed 2D projection labels, which is accomplished by first decoupling 3D teeth labels into class-wise volumes for different teeth via one-hot encoding and then projecting them to generate instance-wise 2D projections. With such 2D labels, DAML can be trained to adaptively describe SDPTIC from CBCT with dynamic adjacency matrix, which is then incorporated into GCN for improving segmentation. To ensure inter-task consistency at the adjacency matrix level between the two decoders, a novel loss function is designed. It can address the issue with inconsistent prediction and unstable TSG-GCN convergence due to two heterogeneous decoders. The TSG-GCN approach is finally validated with both public and multi-center datasets. Experimental results demonstrate its effectiveness for pediatric teeth segmentation, with significant improvement over seven state-of-the-art methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cone-Beam Computed TomographyToothHumansChildImaging, Three-DimensionalChild, PreschoolAlgorithmsDeep LearningAdolescent

Förderung

  • National Nature Science Foundation of China
  • Shanghai Jiao Tong University Translation Medicine Awards Research
  • Innovation Foundation of Beijing Stomatological Hospital, Capital Medical University
  • Beijing Nova Program

Zitieren

APA

Liu, Y., Zhang, S., Wu, X., Yang, T., Pei, Y., Guo, H., Jiang, Y., Feng, Z., Xiao, W., Wang, Y. P., & Wang, L. (2025). Individual Graph Representation Learning for Pediatric Tooth Segmentation From Dental CBCT. IEEE Transactions on Medical Imaging, 44(3), 1432-1444. https://doi.org/10.1109/tmi.2024.3501365

Vancouver

Liu Y, Zhang S, Wu X, Yang T, Pei Y, Guo H, et al. Individual Graph Representation Learning for Pediatric Tooth Segmentation From Dental CBCT. IEEE Transactions on Medical Imaging. 2025;44(3):1432-1444. doi:10.1109/tmi.2024.3501365

BibTeX
@article{Liu2025,
  author = {Liu, Yusheng and Zhang, Shu and Wu, Xiyi and Yang, Tao and Pei, Yuchen and Guo, Huayan and Jiang, Yuxian and Feng, Zhien and Xiao, Wen and Wang, Yu-Ping and Wang, Lisheng},
  title = {Individual Graph Representation Learning for Pediatric Tooth Segmentation From Dental CBCT},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2025},
  volume = {44},
  number = {3},
  pages = {1432--1444},
  doi = {10.1109/tmi.2024.3501365}
}
Kostenlos starten →