Deep Learning-Assisted Diagnostic System: Implant Brand Detection Using Improved IB-YOLOv10 in Periapical Radiographs
<b>Background and Objectives</b>: Implant brand identification is critical in modern dental clinical diagnostics. With the increasing variety of implant brands and the difficulty of accurate identification in periapical radiographs, there is a growing demand for automated solutions. This...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/10/1194 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849711861922004992 |
|---|---|
| author | Yuan-Jin Lin Shih-Lun Chen Ya-Cheng Lu Xu-Ming Lin Yi-Cheng Mao Ming-Yi Chen Chao-Shun Yang Tsung-Yi Chen Kuo-Chen Li Wei-Chen Tu Patricia Angela R. Abu Chiung-An Chen |
| author_facet | Yuan-Jin Lin Shih-Lun Chen Ya-Cheng Lu Xu-Ming Lin Yi-Cheng Mao Ming-Yi Chen Chao-Shun Yang Tsung-Yi Chen Kuo-Chen Li Wei-Chen Tu Patricia Angela R. Abu Chiung-An Chen |
| author_sort | Yuan-Jin Lin |
| collection | DOAJ |
| description | <b>Background and Objectives</b>: Implant brand identification is critical in modern dental clinical diagnostics. With the increasing variety of implant brands and the difficulty of accurate identification in periapical radiographs, there is a growing demand for automated solutions. This study aims to leverage deep learning techniques to assist in dental implant classification, providing dentists with an efficient and reliable tool for implant brand detection. <b>Methods</b>: We proposed an innovative implant brand feature extraction method with multiple image enhancement techniques to improve implant visibility and classification accuracy. Additionally, we introduced a PA resolution enhancement technique that utilizes Dark Channel Prior and Lanczos interpolation for image resolution upscaling. <b>Results</b>: We evaluated the performance differences among various YOLO models for implant brand detection. Additionally, we analyzed the impact of implant brand feature extraction and PA resolution enhancement techniques on YOLO’s detection accuracy. Our results show that IB-YOLOv10 achieves a 17.8% accuracy improvement when incorporating these enhancement techniques compared to IB-YOLOv10 without enhancements. In real-world clinical applications, IB-YOLOv10 can classify implant brands in just 6.47 ms per PA, significantly reducing diagnostic time. Compared to existing studies, our model improves implant detection accuracy by 2.3%, achieving an overall classification accuracy of 94.5%. <b>Conclusions</b>: The findings of this study demonstrate that IB-YOLOv10 effectively reduces the diagnostic burden on dentists while providing a fast and reliable implant brand detection solution, improves clinical efficiency, and establishes a robust deep learning approach for automated implant detection in PA. |
| format | Article |
| id | doaj-art-1582b2543cf74aedb5d8fa321f2fac6d |
| institution | DOAJ |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-1582b2543cf74aedb5d8fa321f2fac6d2025-08-20T03:14:31ZengMDPI AGDiagnostics2075-44182025-05-011510119410.3390/diagnostics15101194Deep Learning-Assisted Diagnostic System: Implant Brand Detection Using Improved IB-YOLOv10 in Periapical RadiographsYuan-Jin Lin0Shih-Lun Chen1Ya-Cheng Lu2Xu-Ming Lin3Yi-Cheng Mao4Ming-Yi Chen5Chao-Shun Yang6Tsung-Yi Chen7Kuo-Chen Li8Wei-Chen Tu9Patricia Angela R. Abu10Chiung-An Chen11Department of Program on Semiconductor Manufacturing Technology (PSMT), Academy of Innovative Semiconductor and Sustainable Manufacturing (AISSM), National Cheng Kung University, Tainan City 701401, TaiwanDepartment of Electronic Engineering, Chung Yuan Christian University, Taoyuan City 320317, TaiwanDepartment of Electronic Engineering, Chung Yuan Christian University, Taoyuan City 320317, TaiwanDepartment of Electronic Engineering, Chung Yuan Christian University, Taoyuan City 320317, TaiwanDepartment of Operative Dentistry, Taoyuan Chang Gung Memorial Hospital, Taoyuan City 33305, TaiwanDepartment of Family Dentistry, Taoyuan Chang Gung Memorial Hospital, Taoyuan City 33305, TaiwanDepartment of Electrical Engineering, Ming Chi University of Technology, New Taipei City 243303, TaiwanDepartment of Electronic Engineering, Feng Chia University, Taichung City 40724, TaiwanDepartment of Information Management, Chung Yuan Christian University, Taoyuan City 320317, TaiwanDepartment of Electrical Engineering, National Cheng Kung University, Tainan City 701401, TaiwanAteneo Laboratory for Intelligent Visual Environments, Department of Information Systems and Computer Science, Ateneo de Manila University, Quezon City 1108, PhilippinesDepartment of Electrical Engineering, Ming Chi University of Technology, New Taipei City 243303, Taiwan<b>Background and Objectives</b>: Implant brand identification is critical in modern dental clinical diagnostics. With the increasing variety of implant brands and the difficulty of accurate identification in periapical radiographs, there is a growing demand for automated solutions. This study aims to leverage deep learning techniques to assist in dental implant classification, providing dentists with an efficient and reliable tool for implant brand detection. <b>Methods</b>: We proposed an innovative implant brand feature extraction method with multiple image enhancement techniques to improve implant visibility and classification accuracy. Additionally, we introduced a PA resolution enhancement technique that utilizes Dark Channel Prior and Lanczos interpolation for image resolution upscaling. <b>Results</b>: We evaluated the performance differences among various YOLO models for implant brand detection. Additionally, we analyzed the impact of implant brand feature extraction and PA resolution enhancement techniques on YOLO’s detection accuracy. Our results show that IB-YOLOv10 achieves a 17.8% accuracy improvement when incorporating these enhancement techniques compared to IB-YOLOv10 without enhancements. In real-world clinical applications, IB-YOLOv10 can classify implant brands in just 6.47 ms per PA, significantly reducing diagnostic time. Compared to existing studies, our model improves implant detection accuracy by 2.3%, achieving an overall classification accuracy of 94.5%. <b>Conclusions</b>: The findings of this study demonstrate that IB-YOLOv10 effectively reduces the diagnostic burden on dentists while providing a fast and reliable implant brand detection solution, improves clinical efficiency, and establishes a robust deep learning approach for automated implant detection in PA.https://www.mdpi.com/2075-4418/15/10/1194clinical decision support systemsimplant brandimage enhancementdental medical diagnosisperiapical radiographsyou only look once |
| spellingShingle | Yuan-Jin Lin Shih-Lun Chen Ya-Cheng Lu Xu-Ming Lin Yi-Cheng Mao Ming-Yi Chen Chao-Shun Yang Tsung-Yi Chen Kuo-Chen Li Wei-Chen Tu Patricia Angela R. Abu Chiung-An Chen Deep Learning-Assisted Diagnostic System: Implant Brand Detection Using Improved IB-YOLOv10 in Periapical Radiographs Diagnostics clinical decision support systems implant brand image enhancement dental medical diagnosis periapical radiographs you only look once |
| title | Deep Learning-Assisted Diagnostic System: Implant Brand Detection Using Improved IB-YOLOv10 in Periapical Radiographs |
| title_full | Deep Learning-Assisted Diagnostic System: Implant Brand Detection Using Improved IB-YOLOv10 in Periapical Radiographs |
| title_fullStr | Deep Learning-Assisted Diagnostic System: Implant Brand Detection Using Improved IB-YOLOv10 in Periapical Radiographs |
| title_full_unstemmed | Deep Learning-Assisted Diagnostic System: Implant Brand Detection Using Improved IB-YOLOv10 in Periapical Radiographs |
| title_short | Deep Learning-Assisted Diagnostic System: Implant Brand Detection Using Improved IB-YOLOv10 in Periapical Radiographs |
| title_sort | deep learning assisted diagnostic system implant brand detection using improved ib yolov10 in periapical radiographs |
| topic | clinical decision support systems implant brand image enhancement dental medical diagnosis periapical radiographs you only look once |
| url | https://www.mdpi.com/2075-4418/15/10/1194 |
| work_keys_str_mv | AT yuanjinlin deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT shihlunchen deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT yachenglu deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT xuminglin deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT yichengmao deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT mingyichen deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT chaoshunyang deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT tsungyichen deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT kuochenli deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT weichentu deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT patriciaangelarabu deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs AT chiunganchen deeplearningassisteddiagnosticsystemimplantbranddetectionusingimprovedibyolov10inperiapicalradiographs |