Imaging Sci Dent.
2024 Mar;54(1):81-91. 10.5624/isd.20230245.
Deep learning-based automatic segmentation of the mandibular canal on panoramic radiographs: A multi-device study
- Affiliations
-
- 1Department of Oral and Maxillofacial Radiology, School of Dentistry and Dental Research Institute, Seoul National University, Seoul, Korea
- 2Department of Oral Medicine, University of Dental Medicine, Mandalay, Myanmar
- 3Interdisciplinary Program in Bioengineering, Graduate School of Engineering, Seoul National University, Seoul, Korea
- 4Department of Applied Bioengineering, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, Korea
- 5Department of Oral and Maxillofacial Radiology, Seoul National University Dental Hospital, Seoul, Korea
- KMID: 2554281
- DOI: http://doi.org/10.5624/isd.20230245
Abstract
- Purpose
The objective of this study was to propose a deep-learning model for the detection of the mandibular canal on dental panoramic radiographs.
Materials and Methods
A total of 2,100 panoramic radiographs (PANs) were collected from 3 different machines: RAYSCAN Alpha (n=700, PAN A), OP-100 (n=700, PAN B), and CS8100 (n=700, PAN C). Initially, an oral and maxillofacial radiologist coarsely annotated the mandibular canals. For deep learning analysis, convolutional neural networks (CNNs) utilizing U-Net architecture were employed for automated canal segmentation. Seven independent networks were trained using training sets representing all possible combinations of the 3 groups. These networks were then assessed using a hold-out test dataset.
Results
Among the 7 networks evaluated, the network trained with all 3 available groups achieved an average precision of 90.6%, a recall of 87.4%, and a Dice similarity coefficient (DSC) of 88.9%. The 3 networks trained using each of the 3 possible 2-group combinations also demonstrated reliable performance for mandibular canal segmentation, as follows: 1) PAN A and B exhibited a mean DSC of 87.9%, 2) PAN A and C displayed a mean DSC of 87.8%, and 3) PAN B and C demonstrated a mean DSC of 88.4%.
Conclusion
This multi-device study indicated that the examined CNN-based deep learning approach can achieve excellent canal segmentation performance, with a DSC exceeding 88%. Furthermore, the study highlighted the importance of considering the characteristics of panoramic radiographs when developing a robust deep-learning network, rather than depending solely on the size of the dataset.
- Full Text Links
-
- Actions
-
Cited
- CITED
-
- Close
- Share
-
- Similar articles
-
- Comparison of Multi-Label U-Net and Mask R-CNN for panoramic radiograph segmentation to detect periodontitis
- Radiographic evaluation of the course and visibility of the mandibular canal
- Deep learning-based apical lesion segmentation from panoramic radiographs
- Assessment of the relationship between the mandibular third molar and the mandibular canal using panoramic radiograph and cone beam computed tomography
- Correlation of panoramic radiographs and cone beam computed tomography in the assessment of a superimposed relationship between the mandibular canal and impacted third molars
