EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

TAPSeg: An open-source deep learning tool for instance-level tooth and pulp segmentation in CBCT

Yi Zhang, Mingya Zhang, Jiaxue Ye, Xinyi Zhou, Zirui Qin, Suman Tong, Shuli Deng, Yuan Wang

Journal of Dentistry · 2026

DOI: 10.1016/j.jdent.2026.106643 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Dentistry, 2026. Verfasst von Yi Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Stomatology Hospital, School of Stomatology, Zhejiang University School of Medicine, Zhejiang Provincial Clinical Research Center for Oral Diseases, …. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Deep Learning, Tooth, Dental Pulp. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES: To develop an open-source one-tap CBCT automatic segmentation tool based on deep learning to perform integrated segmentation and reconstruction of teeth and pulp in the 3D Slicer software and verify its generalization ability on multiple datasets. METHODS: Three datasets were used for model training and evaluation. Tooth segmentation employed a three-stage V-Net collaborative framework (arch area positioning, single-tooth centroid detection, and single-tooth fine instance segmentation), while pulp segmentation used nnU-Net for 3D semantic segmentation. Model performance was assessed on independent external datasets, including immature permanent teeth with open apices, using Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), sensitivity, and precision. Fine-tuning and additional evaluations were performed for teeth with open apices. RESULTS: TAPSeg achieved robust performance across multiple test sets for tooth segmentation (n = 198) and pulp segmentation (n = 148), with DSCs ranging from 91.5%-94.2% and 91.0%-92.2%, and HD95 values of 0.700-1.449 mm and 0.704-1.008 mm for tooth and pulp segmentation, respectively, while maintaining high sensitivity and precision. For immature permanent teeth, hard-tissue segmentation achieved a DSC of 92.1% ± 6.5%. CONCLUSIONS: By integrating V-Net and nnU-Net, TAPSeg provides accurate, efficient, and generalizable tooth-pulp segmentation with one-click operation as a 3D Slicer plug-in, lowering the threshold for clinical use. CLINICAL RELEVANCE: TAPSeg enables clinicians to generate patient-specific 3D models from CBCT scans within minutes, supporting standardized quantification of root morphology and volume changes, follow-up of root development, regenerative endodontic procedures, and automated digital dental workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cone-Beam Computed TomographyDeep LearningToothDental PulpImage Processing, Computer-AssistedHumansImaging, Three-DimensionalSoftware

Stichwörter der Autor:innen

Computer-assisted image analysisCone-beam computed tomographyDeep learningOpen sourcePulp segmentationTooth segmentation

Autor:innen und Institutionen

  • Stomatology Hospital, School of Stomatology, Zhejiang University School of Medicine, Zhejiang Provincial Clinical Research Center for Oral Diseases, Zhejiang Key Laboratory of Oral Biomedical, Hangzhou, 310000, China.
  • School of Medical Information, Wannan Medical College, Wuhu, Anhui, 241002, China.
  • Stomatology Hospital, School of Stomatology, Zhejiang University School of Medicine, Zhejiang Provincial Clinical Research Center for Oral Diseases, Zhejiang Key Laboratory of Oral Biomedical, Hangzhou, 310000, China. E…

Zitieren

APA

Zhang, Y., Zhang, M., Ye, J., Zhou, X., Qin, Z., Tong, S., Deng, S., & Wang, Y. (2026). TAPSeg: An open-source deep learning tool for instance-level tooth and pulp segmentation in CBCT. Journal of Dentistry. https://doi.org/10.1016/j.jdent.2026.106643

Vancouver

Zhang Y, Zhang M, Ye J, Zhou X, Qin Z, Tong S, et al. TAPSeg: An open-source deep learning tool for instance-level tooth and pulp segmentation in CBCT. Journal of Dentistry. 2026. doi:10.1016/j.jdent.2026.106643

BibTeX
@article{Zhang2026,
  author = {Zhang, Yi and Zhang, Mingya and Ye, Jiaxue and Zhou, Xinyi and Qin, Zirui and Tong, Suman and Deng, Shuli and Wang, Yuan},
  title = {TAPSeg: An open-source deep learning tool for instance-level tooth and pulp segmentation in CBCT},
  journal = {Journal of Dentistry},
  year = {2026},
  doi = {10.1016/j.jdent.2026.106643}
}
Kostenlos starten →