Optimized Multi-Scale Detection and Numbering of Teeth in Panoramic Radiographs Using DentifyNet
Manual tooth detection and numbering in panoramic radiographs are time-consuming and prone to human errors, negatively impacting diagnostic accuracy and treatment outcomes. These challenges necessitate robust automated solutions to improve efficiency and precision in dental imaging. This study intro...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10935326/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849389380946362368 |
|---|---|
| author | Salih Taha Alperen Ozcelik Huseyin Uzen Abdulkadir Sengur Muammer Turkoglu Adalet Celebi Nebras M. Sobahi |
| author_facet | Salih Taha Alperen Ozcelik Huseyin Uzen Abdulkadir Sengur Muammer Turkoglu Adalet Celebi Nebras M. Sobahi |
| author_sort | Salih Taha Alperen Ozcelik |
| collection | DOAJ |
| description | Manual tooth detection and numbering in panoramic radiographs are time-consuming and prone to human errors, negatively impacting diagnostic accuracy and treatment outcomes. These challenges necessitate robust automated solutions to improve efficiency and precision in dental imaging. This study introduces DentifyNet, a novel deep learning architecture designed for automatic tooth detection and numbering in panoramic radiography images. DentifyNet integrates a customized Faster R-CNN framework with Feature Pyramid Networks (FPN), flexible anchor structures, and RoI Align to enhance detection precision. The model was trained and evaluated on 468 panoramic radiographs annotated by dental experts using the FDI numbering system. Experimental results demonstrate that DentifyNet achieved state-of-the-art performance with an Intersection over Union (IoU) of 86.42%, precision of 97.52%, recall of 97.49%, F1-score of 97.51%, and accuracy of 97.50%. The architecture effectively detects challenging cases, such as adjacent similar teeth and missing teeth. These findings suggest that DentifyNet surpasses standard Faster R-CNN architectures, offering a reliable solution for automated tooth detection and numbering. Future research will focus on utilizing broader datasets and architectural advancements to address current limitations and expand clinical applications. |
| format | Article |
| id | doaj-art-5edd5068c65d46fda160db1639d383ec |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-5edd5068c65d46fda160db1639d383ec2025-08-20T03:41:59ZengIEEEIEEE Access2169-35362025-01-0113523535236810.1109/ACCESS.2025.355322810935326Optimized Multi-Scale Detection and Numbering of Teeth in Panoramic Radiographs Using DentifyNetSalih Taha Alperen Ozcelik0https://orcid.org/0000-0002-7929-7542Huseyin Uzen1Abdulkadir Sengur2https://orcid.org/0000-0003-1614-2639Muammer Turkoglu3https://orcid.org/0000-0002-2377-4979Adalet Celebi4https://orcid.org/0000-0003-2471-1942Nebras M. Sobahi5https://orcid.org/0000-0001-5788-5629Department of Electrical and Electronics Engineering, Faculty of Engineering, Bingöl University, Bingöl, TürkiyeDepartment of Computer Engineering, Faculty of Engineering, Bingöl University, Bingöl, TürkiyeDepartment of Electrical and Electronics Engineering, Faculty of Technology, Fırat University, Elâziğ, TürkiyeDepartment of Software Engineering, Samsun University, Samsun, TürkiyeOral and Maxillofacial Surgery Department, Faculty of Dentistry, Mersin University, Mersin, TürkiyeDepartment of Electrical and Electronics Engineering, Faculty of Engineering, King Abdulaziz University, Jeddah, Saudi ArabiaManual tooth detection and numbering in panoramic radiographs are time-consuming and prone to human errors, negatively impacting diagnostic accuracy and treatment outcomes. These challenges necessitate robust automated solutions to improve efficiency and precision in dental imaging. This study introduces DentifyNet, a novel deep learning architecture designed for automatic tooth detection and numbering in panoramic radiography images. DentifyNet integrates a customized Faster R-CNN framework with Feature Pyramid Networks (FPN), flexible anchor structures, and RoI Align to enhance detection precision. The model was trained and evaluated on 468 panoramic radiographs annotated by dental experts using the FDI numbering system. Experimental results demonstrate that DentifyNet achieved state-of-the-art performance with an Intersection over Union (IoU) of 86.42%, precision of 97.52%, recall of 97.49%, F1-score of 97.51%, and accuracy of 97.50%. The architecture effectively detects challenging cases, such as adjacent similar teeth and missing teeth. These findings suggest that DentifyNet surpasses standard Faster R-CNN architectures, offering a reliable solution for automated tooth detection and numbering. Future research will focus on utilizing broader datasets and architectural advancements to address current limitations and expand clinical applications.https://ieeexplore.ieee.org/document/10935326/Computer-aided diagnosticsconvolutional neural networkstooth detectiontooth numberingpanoramic radiography |
| spellingShingle | Salih Taha Alperen Ozcelik Huseyin Uzen Abdulkadir Sengur Muammer Turkoglu Adalet Celebi Nebras M. Sobahi Optimized Multi-Scale Detection and Numbering of Teeth in Panoramic Radiographs Using DentifyNet IEEE Access Computer-aided diagnostics convolutional neural networks tooth detection tooth numbering panoramic radiography |
| title | Optimized Multi-Scale Detection and Numbering of Teeth in Panoramic Radiographs Using DentifyNet |
| title_full | Optimized Multi-Scale Detection and Numbering of Teeth in Panoramic Radiographs Using DentifyNet |
| title_fullStr | Optimized Multi-Scale Detection and Numbering of Teeth in Panoramic Radiographs Using DentifyNet |
| title_full_unstemmed | Optimized Multi-Scale Detection and Numbering of Teeth in Panoramic Radiographs Using DentifyNet |
| title_short | Optimized Multi-Scale Detection and Numbering of Teeth in Panoramic Radiographs Using DentifyNet |
| title_sort | optimized multi scale detection and numbering of teeth in panoramic radiographs using dentifynet |
| topic | Computer-aided diagnostics convolutional neural networks tooth detection tooth numbering panoramic radiography |
| url | https://ieeexplore.ieee.org/document/10935326/ |
| work_keys_str_mv | AT salihtahaalperenozcelik optimizedmultiscaledetectionandnumberingofteethinpanoramicradiographsusingdentifynet AT huseyinuzen optimizedmultiscaledetectionandnumberingofteethinpanoramicradiographsusingdentifynet AT abdulkadirsengur optimizedmultiscaledetectionandnumberingofteethinpanoramicradiographsusingdentifynet AT muammerturkoglu optimizedmultiscaledetectionandnumberingofteethinpanoramicradiographsusingdentifynet AT adaletcelebi optimizedmultiscaledetectionandnumberingofteethinpanoramicradiographsusingdentifynet AT nebrasmsobahi optimizedmultiscaledetectionandnumberingofteethinpanoramicradiographsusingdentifynet |