Active learning-assisted deep learning for automated maxillary sinus segmentation in dental cone-beam computed tomography.
6 affiliations
- 1College of Dentistry, National Yang-Ming University, Taipei, Taiwan.
- 2Department of Prosthodontics, Shin Kong Wu Ho-Su Memorial Hospital, Taipei, Taiwan.
- 3Department of Mechanical Engineering, Chinese Culture University, Taipei, Taiwan.
- 4Faculty of Dentistry, Chulalongkorn University, Bangkok, Thailand.
- 5School of Dentistry, Tohoku University, Sendai, Japan.
- 6Department of Stomatology, Taipei Veterans General Hospital, Taipei, Taiwan.
Abstract
Background/purpose
Accurate automated segmentation of the maxillary sinus in cone-beam computed tomography (CBCT) scans is crucial for dental implant planning, sinus lift procedures, and pathological assessment, yet there remains a notable lack of publicly available models and datasets for this task. This study developed and evaluated a deep learning model for automated maxillary sinus segmentation using an active learning approach to minimize annotation effort while achieving high accuracy.Materials and methods
We utilized 249 CBCT scans from the publicly available CTooth+ and STS-Tooth datasets. Ground truth annotations were generated through semi-automated segmentation in 3D Slicer with validation by five expert dentists. An active learning strategy was employed using the nnU-Net 3D full-resolution architecture trained with five-fold cross-validation. Performance was evaluated using Dice similarity coefficient (Dice).Results
The model achieved a mean Dice of 0.985 (standard deviation (SD): 0.026, median: 0.992) and mean intersection over union (IoU) of 0.972 (SD: 0.044) across 249 cases. Performance remained stable across varying sinus volumes, with only rare outliers (minimum Dice: 0.712) corresponding to unusual anatomical presentations or image artifacts.Conclusion
This study demonstrates that automated maxillary sinus segmentation using nnU-Net with active learning can achieve highly accurate and consistent results on diverse CBCT scans. The approach shows strong potential for clinical integration to enhance efficiency in dental treatment planning and supports the advancement of dental radiology driven by artificial intelligence (AI) through utilization of publicly available datasets.
Related
- Automated segmentation and clinical characterization of layered plaque in intracoronary optical coherence tomography
- Artificial Intelligence‐Assisted Automated Optical Coherence Tomography Analysis for Percutaneous Coronary Intervention Planning: From Plaque Analysis to Precision Lesion Preparation and Stent Optimization
- Automated quantitative computed tomography grading of lumbar facet joint degeneration: influence of segmentation errors on instance-level clinical assessment.
- Federated knowledge-guided 3D Transformer learning for bone tumor segmentation from partially annotated computed tomography data
- A robust lightweight deep learning network with deformable convolutions for efficient segmentation of optical coherence tomography images
BibTeX
@article{chen2026active,
title = {{Active learning-assisted deep learning for automated maxillary sinus segmentation in dental cone-beam computed tomography.}},
author = {Hsuan Chen and Khoa Dang Nguyen and Chih-Ling Chang and Hong Thi-Phuong Doan and Ya-Chu Chang and Thantrira Porntaveetus and Guang Hong and Wen-Liang Lo and Ding-Han Wang and Ming-Lun Hsu},
journal = {Journal of dental sciences},
year = {2026},
month = oct,
doi = {10.1016/j.jds.2025.07.3523},
url = {https://europepmc.org/article/MED/42924217},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Active learning-assisted deep learning for automated maxillary sinus segmentation in dental cone-beam computed tomography.
AU - Hsuan Chen
AU - Khoa Dang Nguyen
AU - Chih-Ling Chang
AU - Hong Thi-Phuong Doan
AU - Ya-Chu Chang
AU - Thantrira Porntaveetus
AU - Guang Hong
AU - Wen-Liang Lo
AU - Ding-Han Wang
AU - Ming-Lun Hsu
PY - 2026
DA - 2026/10/01
JO - Journal of dental sciences
DO - 10.1016/j.jds.2025.07.3523
UR - https://europepmc.org/article/MED/42924217
AB - Background/purpose Accurate automated segmentation of the maxillary sinus in cone-beam computed tomography (CBCT) scans is crucial for dental implant planning, sinus lift procedures, and pathological assessment, yet there remains a notable lack of publicly available models and datasets for this task. This study developed and evaluated a deep learning model for automated maxillary sinus segmentation using an active learning approach to minimize annotation effort while achieving high accuracy.Materials and methods We utilized 249 CBCT scans from the publicly available CTooth+ and STS-Tooth datasets. Ground truth annotations were generated through semi-automated segmentation in 3D Slicer with validation by five expert dentists. An active learning strategy was employed using the nnU-Net 3D full-resolution architecture trained with five-fold cross-validation. Performance was evaluated using Dice similarity coefficient (Dice).Results The model achieved a mean Dice of 0.985 (standard deviation (SD): 0.026, median: 0.992) and mean intersection over union (IoU) of 0.972 (SD: 0.044) across 249 cases. Performance remained stable across varying sinus volumes, with only rare outliers (minimum Dice: 0.712) corresponding to unusual anatomical presentations or image artifacts.Conclusion This study demonstrates that automated maxillary sinus segmentation using nnU-Net with active learning can achieve highly accurate and consistent results on diverse CBCT scans. The approach shows strong potential for clinical integration to enhance efficiency in dental treatment planning and supports the advancement of dental radiology driven by artificial intelligence (AI) through utilization of publicly available datasets.
SN - 1991-7902
SN - 2213-8862
ER -