Enhancing furcation involvement classification on panoramic radiographs with vision transformers
Abstract Background The severity of furcation involvement (FI) directly affected tooth prognosis and influenced treatment approaches. However, assessing, diagnosing, and treating molars with FI was complicated by anatomical and morphological variations. Cone-beam computed tomography (CBCT) enhanced...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Oral Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12903-025-05431-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571240432271360 |
|---|---|
| author | Xuan Zhang Enting Guo Xu Liu Hong Zhao Jie Yang Wen Li Wenlei Wu Weibin Sun |
| author_facet | Xuan Zhang Enting Guo Xu Liu Hong Zhao Jie Yang Wen Li Wenlei Wu Weibin Sun |
| author_sort | Xuan Zhang |
| collection | DOAJ |
| description | Abstract Background The severity of furcation involvement (FI) directly affected tooth prognosis and influenced treatment approaches. However, assessing, diagnosing, and treating molars with FI was complicated by anatomical and morphological variations. Cone-beam computed tomography (CBCT) enhanced diagnostic accuracy for detecting FI and measuring furcation defects. Despite its advantages, the high cost and radiation dose associated with CBCT equipment limited its widespread use. The aim of this study was to evaluate the performance of the Vision Transformer (ViT) in comparison with several commonly used traditional deep learning (DL) models for classifying molars with or without FI on panoramic radiographs. Methods A total of 1,568 tooth images obtained from 506 panoramic radiographs were used to construct the database and evaluate the models. This study developed and assessed a ViT model for classifying FI from panoramic radiographs, and compared its performance with traditional models, including Multi-Layer Perceptron (MLP), Visual Geometry Group (VGG)Net, and GoogLeNet. Results Among the evaluated models, the ViT model outperformed all others, achieving the highest precision (0.98), recall (0.92), and F1 score (0.95), along with the lowest cross-entropy loss (0.27) and the highest accuracy (92%). ViT also recorded the highest area under the curve (AUC) (98%), outperforming the other models with statistically significant differences (p < 0.05), confirming its enhanced classification capability. The gradient-weighted class activation mapping (Grad-CAM) analysis on the ViT model revealed the key areas of the images that the model focused on during predictions. Conclusion DL algorithms can automatically classify FI using readily accessible panoramic images. These findings demonstrate that ViT outperforms the tested traditional models, highlighting the potential of transformer-based approaches to significantly advance image classification. This approach is also expected to reduce both the radiation dose and the financial burden on patients while simultaneously improving diagnostic precision. |
| format | Article |
| id | doaj-art-6cb30051e9b445a7b3483bbaff23b812 |
| institution | Kabale University |
| issn | 1472-6831 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Oral Health |
| spelling | doaj-art-6cb30051e9b445a7b3483bbaff23b8122025-02-02T12:45:14ZengBMCBMC Oral Health1472-68312025-01-0125111410.1186/s12903-025-05431-6Enhancing furcation involvement classification on panoramic radiographs with vision transformersXuan Zhang0Enting Guo1Xu Liu2Hong Zhao3Jie Yang4Wen Li5Wenlei Wu6Weibin Sun7Department of Periodontics, Affiliated Hospital of Medical School, Nanjing Stomatological Hospital, Research Institute of Stomatology, Nanjing UniversityDivision of Computer Science, University of AizuDepartment of Periodontics, Affiliated Hospital of Medical School, Nanjing Stomatological Hospital, Research Institute of Stomatology, Nanjing UniversityThe School of Computer Science and Technology, North University of ChinaDepartment of Periodontics, Affiliated Hospital of Medical School, Nanjing Stomatological Hospital, Research Institute of Stomatology, Nanjing UniversityDepartment of Endodontics, Affiliated Hospital of Medical School, Nanjing Stomatological Hospital, Research Institute of Stomatology, Nanjing UniversityDepartment of Periodontics, Affiliated Hospital of Medical School, Nanjing Stomatological Hospital, Research Institute of Stomatology, Nanjing UniversityDepartment of Periodontics, Affiliated Hospital of Medical School, Nanjing Stomatological Hospital, Research Institute of Stomatology, Nanjing UniversityAbstract Background The severity of furcation involvement (FI) directly affected tooth prognosis and influenced treatment approaches. However, assessing, diagnosing, and treating molars with FI was complicated by anatomical and morphological variations. Cone-beam computed tomography (CBCT) enhanced diagnostic accuracy for detecting FI and measuring furcation defects. Despite its advantages, the high cost and radiation dose associated with CBCT equipment limited its widespread use. The aim of this study was to evaluate the performance of the Vision Transformer (ViT) in comparison with several commonly used traditional deep learning (DL) models for classifying molars with or without FI on panoramic radiographs. Methods A total of 1,568 tooth images obtained from 506 panoramic radiographs were used to construct the database and evaluate the models. This study developed and assessed a ViT model for classifying FI from panoramic radiographs, and compared its performance with traditional models, including Multi-Layer Perceptron (MLP), Visual Geometry Group (VGG)Net, and GoogLeNet. Results Among the evaluated models, the ViT model outperformed all others, achieving the highest precision (0.98), recall (0.92), and F1 score (0.95), along with the lowest cross-entropy loss (0.27) and the highest accuracy (92%). ViT also recorded the highest area under the curve (AUC) (98%), outperforming the other models with statistically significant differences (p < 0.05), confirming its enhanced classification capability. The gradient-weighted class activation mapping (Grad-CAM) analysis on the ViT model revealed the key areas of the images that the model focused on during predictions. Conclusion DL algorithms can automatically classify FI using readily accessible panoramic images. These findings demonstrate that ViT outperforms the tested traditional models, highlighting the potential of transformer-based approaches to significantly advance image classification. This approach is also expected to reduce both the radiation dose and the financial burden on patients while simultaneously improving diagnostic precision.https://doi.org/10.1186/s12903-025-05431-6Vision transformerFurcation involvementDeep learningPanoramic radiograph |
| spellingShingle | Xuan Zhang Enting Guo Xu Liu Hong Zhao Jie Yang Wen Li Wenlei Wu Weibin Sun Enhancing furcation involvement classification on panoramic radiographs with vision transformers BMC Oral Health Vision transformer Furcation involvement Deep learning Panoramic radiograph |
| title | Enhancing furcation involvement classification on panoramic radiographs with vision transformers |
| title_full | Enhancing furcation involvement classification on panoramic radiographs with vision transformers |
| title_fullStr | Enhancing furcation involvement classification on panoramic radiographs with vision transformers |
| title_full_unstemmed | Enhancing furcation involvement classification on panoramic radiographs with vision transformers |
| title_short | Enhancing furcation involvement classification on panoramic radiographs with vision transformers |
| title_sort | enhancing furcation involvement classification on panoramic radiographs with vision transformers |
| topic | Vision transformer Furcation involvement Deep learning Panoramic radiograph |
| url | https://doi.org/10.1186/s12903-025-05431-6 |
| work_keys_str_mv | AT xuanzhang enhancingfurcationinvolvementclassificationonpanoramicradiographswithvisiontransformers AT entingguo enhancingfurcationinvolvementclassificationonpanoramicradiographswithvisiontransformers AT xuliu enhancingfurcationinvolvementclassificationonpanoramicradiographswithvisiontransformers AT hongzhao enhancingfurcationinvolvementclassificationonpanoramicradiographswithvisiontransformers AT jieyang enhancingfurcationinvolvementclassificationonpanoramicradiographswithvisiontransformers AT wenli enhancingfurcationinvolvementclassificationonpanoramicradiographswithvisiontransformers AT wenleiwu enhancingfurcationinvolvementclassificationonpanoramicradiographswithvisiontransformers AT weibinsun enhancingfurcationinvolvementclassificationonpanoramicradiographswithvisiontransformers |