- Published
- 2021-03-30
- Venue
- Journal of Dental Research, vol. 100, no. 9, pp. 943-949
- Cited by
- 189
- Open access
- Yes, hybrid
- DOI
- 10.1177/00220345211005338
- PubMed
- 33783247
Abstract
Accurate segmentation of the jaw (i.e., mandible and maxilla) and the teeth in cone beam computed tomography (CBCT) scans is essential for orthodontic diagnosis and treatment planning. Although various (semi)automated methods have been proposed to segment the jaw or the teeth, there is still a lack of fully automated segmentation methods that can simultaneously segment both anatomic structures in CBCT scans (i.e., multiclass segmentation). In this study, we aimed to train and validate a mixed-scale dense (MS-D) convolutional neural network for multiclass segmentation of the jaw, the teeth, and the background in CBCT scans. Thirty CBCT scans were obtained from patients who had undergone orthodontic treatment. Gold standard segmentation labels were manually created by 4 dentists. As a benchmark, we also evaluated MS-D networks that segmented the jaw or the teeth (i.e., binary segmentation). All segmented CBCT scans were converted to virtual 3-dimensional (3D) models. The segmentation performance of all trained MS-D networks was assessed by the Dice similarity coefficient and surface deviation. The CBCT scans segmented by the MS-D network demonstrated a large overlap with the gold standard segmentations (Dice similarity coefficient: 0.934 ± 0.019, jaw; 0.945 ± 0.021, teeth). The MS-D network-based 3D models of the jaw and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models (0.390 ± 0.093 mm, jaw; 0.204 ± 0.061 mm, teeth). The MS-D network took approximately 25 s to segment 1 CBCT scan, whereas manual segmentation took about 5 h. This study showed that multiclass segmentation of jaw and teeth was accurate and its performance was comparable to binary segmentation. The MS-D network trained for multiclass segmentation would therefore make patient-specific orthodontic treatment more feasible by strongly reducing the time required to segment multiple anatomic structures in CBCT scans.
Cite this paper
Formatted from the source metadata, not typed by hand. For a whole reference list, use the citation generator or ask your assistant through Find Research.
- APA 7
Wang, H., Minnema, J., Batenburg, K. J., Forouzanfar, T., Hu, F., & Wu, G. (2021). Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning. Journal of Dental Research, 100(9), 943–949. https://doi.org/10.1177/00220345211005338
- MLA 9
Wang, H., et al. "Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning." Journal of Dental Research, vol. 100, no. 9, 2021, pp. 943–949, https://doi.org/10.1177/00220345211005338.
- Chicago
Wang, H., Jordi Minnema, Kees Joost Batenburg, Tymour Forouzanfar, Fengjun Hu, and Guangming Wu. "Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning." Journal of Dental Research 100, no. 9 (2021): 943–949. https://doi.org/10.1177/00220345211005338.
- GOST
Wang H., Minnema J., Batenburg K. J. [и др.] Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning // Journal of Dental Research. — 2021. — Vol. 100, № 9. — P. 943–949. — URL: https://doi.org/10.1177/00220345211005338
- BibTeX
@article{wang2021multiclass, title = {{Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning}}, author = {H. Wang and Jordi Minnema and Kees Joost Batenburg and Tymour Forouzanfar and Fengjun Hu and Guangming Wu}, journal = {Journal of Dental Research}, year = {2021}, volume = {100}, number = {9}, pages = {943--949}, doi = {10.1177/00220345211005338}, url = {https://doi.org/10.1177/00220345211005338} }- RIS
TY - JOUR AU - Wang, H. AU - Minnema, Jordi AU - Batenburg, Kees Joost AU - Forouzanfar, Tymour AU - Hu, Fengjun AU - Wu, Guangming TI - Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning JO - Journal of Dental Research VL - 100 IS - 9 SP - 943 EP - 949 PY - 2021 DA - 2021/03/30 DO - 10.1177/00220345211005338 UR - https://doi.org/10.1177/00220345211005338 ER -
Ask Claude about this paper
Add Find Research to Claude or ChatGPT and ask in plain language. The assistant reads this record, finds the papers around it and cites only what it actually found:
- “Summarize doi:10.1177/00220345211005338 and list its main limitations.”
- “Find newer studies that test the same question, with free PDFs.”
- “Cite this and five related papers in APA for my literature review.”
Setup takes about a minute: add the connector, then start the free trial.
Record from OpenAlex; open-access location from Unpaywall and the indexes. Find Research links only to legal copies.