Development and verification of a convolutional neural network-based model for automatic mandibular canal localization on multicenter CBCT images
Abstract Objectives Development and verification of a convolutional neural network (CNN)-based deep learning (DL) model for mandibular canal (MC) localization on multicenter cone beam computed tomography (CBCT) images. Methods In this study, a total 1056 CBCT scans in multiple centers were collected...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | BMC Oral Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12903-025-06724-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849225864678473728 |
|---|---|
| author | Xiao Pan Chengtao Wang Xuhui Luo Qi Dong Haiyang Sun Wentao Zhang Hongyan Qu Runzhi Deng Zitong Lin |
| author_facet | Xiao Pan Chengtao Wang Xuhui Luo Qi Dong Haiyang Sun Wentao Zhang Hongyan Qu Runzhi Deng Zitong Lin |
| author_sort | Xiao Pan |
| collection | DOAJ |
| description | Abstract Objectives Development and verification of a convolutional neural network (CNN)-based deep learning (DL) model for mandibular canal (MC) localization on multicenter cone beam computed tomography (CBCT) images. Methods In this study, a total 1056 CBCT scans in multiple centers were collected. Of these, 836 CBCT scans of one manufacturer were used for development of CNN model (training set: validation set: internal testing set = 640:360:36) and an external testing dataset of 220 CBCT scans from other four manufacturers were tested. The convolution module was built using a stack of Conv + InstanceNorm + LeakyReLU. Average symmetric surface distance (ASSD) and symmetric mean curve distance (SMCD) were used for quantitative evaluation of this model for both internal testing data and partial external testing data. Visual scoring (1–5 points) were performed to evaluate the accuracy and generalizability of MC localization for all external testing data. The differences of ASSD, SMCD and visual scores among the four manufacturers were compared for external testing dataset. The time of manual and automatic MC localization were recorded. Results For the internal testing dataset, the average ASSD and SMCD was 0.486 mm and 0.298 mm respectively. For the external testing dataset, 86.8% CBCT scans’ visual scores ≥ 4 points; the average ASSD and SMCD of 40 CBCT scans with visual scores ≥ 4 points were 0.438 mm and 0.185 mm respectively; there were significant differences among the four manufacturers for ASSD, SMCD and visual scores (p < 0.05). And the time for bilateral automatic MC localization was 8.52s (± 0.97s). Conclusions In this study, a CNN model was developed for automatic MC localization, and external testing of large sample on multicenter CBCT images showed its excellent clinical application potential. |
| format | Article |
| id | doaj-art-b8e49e08fcc5430daa2b6ddbb1414089 |
| institution | Kabale University |
| issn | 1472-6831 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Oral Health |
| spelling | doaj-art-b8e49e08fcc5430daa2b6ddbb14140892025-08-24T11:54:46ZengBMCBMC Oral Health1472-68312025-08-0125111110.1186/s12903-025-06724-6Development and verification of a convolutional neural network-based model for automatic mandibular canal localization on multicenter CBCT imagesXiao Pan0Chengtao Wang1Xuhui Luo2Qi Dong3Haiyang Sun4Wentao Zhang5Hongyan Qu6Runzhi Deng7Zitong Lin8Department of Dentomaxillofacial Radiology, Nanjing Stomatological Hospital, Affiliated Hospital of Medical School, Institute of Stomatology, Nanjing UniversityDepartment of Dentomaxillofacial Radiology, Nanjing Stomatological Hospital, Affiliated Hospital of Medical School, Institute of Stomatology, Nanjing UniversityDepartment of Dentomaxillofacial Radiology, Nanjing Stomatological Hospital, Affiliated Hospital of Medical School, Institute of Stomatology, Nanjing UniversityDepartment of Dentomaxillofacial Radiology, Nanjing Stomatological Hospital, Affiliated Hospital of Medical School, Institute of Stomatology, Nanjing UniversitySchool of Computer and Software, Nanjing Vocational University of Industry TechnologyShanghai Bondent Technology Co., LtdShanghai Bondent Technology Co., LtdDepartment of General Dentistry, Nanjing Stomatological Hospital, Affiliated Hospital of Medical School, Institute of Stomatology, Nanjing UniversityDepartment of Dentomaxillofacial Radiology, Nanjing Stomatological Hospital, Affiliated Hospital of Medical School, Institute of Stomatology, Nanjing UniversityAbstract Objectives Development and verification of a convolutional neural network (CNN)-based deep learning (DL) model for mandibular canal (MC) localization on multicenter cone beam computed tomography (CBCT) images. Methods In this study, a total 1056 CBCT scans in multiple centers were collected. Of these, 836 CBCT scans of one manufacturer were used for development of CNN model (training set: validation set: internal testing set = 640:360:36) and an external testing dataset of 220 CBCT scans from other four manufacturers were tested. The convolution module was built using a stack of Conv + InstanceNorm + LeakyReLU. Average symmetric surface distance (ASSD) and symmetric mean curve distance (SMCD) were used for quantitative evaluation of this model for both internal testing data and partial external testing data. Visual scoring (1–5 points) were performed to evaluate the accuracy and generalizability of MC localization for all external testing data. The differences of ASSD, SMCD and visual scores among the four manufacturers were compared for external testing dataset. The time of manual and automatic MC localization were recorded. Results For the internal testing dataset, the average ASSD and SMCD was 0.486 mm and 0.298 mm respectively. For the external testing dataset, 86.8% CBCT scans’ visual scores ≥ 4 points; the average ASSD and SMCD of 40 CBCT scans with visual scores ≥ 4 points were 0.438 mm and 0.185 mm respectively; there were significant differences among the four manufacturers for ASSD, SMCD and visual scores (p < 0.05). And the time for bilateral automatic MC localization was 8.52s (± 0.97s). Conclusions In this study, a CNN model was developed for automatic MC localization, and external testing of large sample on multicenter CBCT images showed its excellent clinical application potential.https://doi.org/10.1186/s12903-025-06724-6Cone beam computed tomographyMandibular canalConvolutional neural networkLocalization |
| spellingShingle | Xiao Pan Chengtao Wang Xuhui Luo Qi Dong Haiyang Sun Wentao Zhang Hongyan Qu Runzhi Deng Zitong Lin Development and verification of a convolutional neural network-based model for automatic mandibular canal localization on multicenter CBCT images BMC Oral Health Cone beam computed tomography Mandibular canal Convolutional neural network Localization |
| title | Development and verification of a convolutional neural network-based model for automatic mandibular canal localization on multicenter CBCT images |
| title_full | Development and verification of a convolutional neural network-based model for automatic mandibular canal localization on multicenter CBCT images |
| title_fullStr | Development and verification of a convolutional neural network-based model for automatic mandibular canal localization on multicenter CBCT images |
| title_full_unstemmed | Development and verification of a convolutional neural network-based model for automatic mandibular canal localization on multicenter CBCT images |
| title_short | Development and verification of a convolutional neural network-based model for automatic mandibular canal localization on multicenter CBCT images |
| title_sort | development and verification of a convolutional neural network based model for automatic mandibular canal localization on multicenter cbct images |
| topic | Cone beam computed tomography Mandibular canal Convolutional neural network Localization |
| url | https://doi.org/10.1186/s12903-025-06724-6 |
| work_keys_str_mv | AT xiaopan developmentandverificationofaconvolutionalneuralnetworkbasedmodelforautomaticmandibularcanallocalizationonmulticentercbctimages AT chengtaowang developmentandverificationofaconvolutionalneuralnetworkbasedmodelforautomaticmandibularcanallocalizationonmulticentercbctimages AT xuhuiluo developmentandverificationofaconvolutionalneuralnetworkbasedmodelforautomaticmandibularcanallocalizationonmulticentercbctimages AT qidong developmentandverificationofaconvolutionalneuralnetworkbasedmodelforautomaticmandibularcanallocalizationonmulticentercbctimages AT haiyangsun developmentandverificationofaconvolutionalneuralnetworkbasedmodelforautomaticmandibularcanallocalizationonmulticentercbctimages AT wentaozhang developmentandverificationofaconvolutionalneuralnetworkbasedmodelforautomaticmandibularcanallocalizationonmulticentercbctimages AT hongyanqu developmentandverificationofaconvolutionalneuralnetworkbasedmodelforautomaticmandibularcanallocalizationonmulticentercbctimages AT runzhideng developmentandverificationofaconvolutionalneuralnetworkbasedmodelforautomaticmandibularcanallocalizationonmulticentercbctimages AT zitonglin developmentandverificationofaconvolutionalneuralnetworkbasedmodelforautomaticmandibularcanallocalizationonmulticentercbctimages |