Full text

Turn on search term navigation

© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

Abstract

Background and Objectives: 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. Methods: 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. Results: 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%. Conclusions: 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.

Details

Title
Deep Learning-Assisted Diagnostic System: Implant Brand Detection Using Improved IB-YOLOv10 in Periapical Radiographs
Author
Yuan-Jin, Lin 1   VIAFID ORCID Logo  ; Shih-Lun, Chen 2   VIAFID ORCID Logo  ; Ya-Cheng, Lu 2 ; Xu-Ming, Lin 2 ; Yi-Cheng, Mao 3 ; Ming-Yi, Chen 4 ; Chao-Shun, Yang 5 ; Tsung-Yi, Chen 6   VIAFID ORCID Logo  ; Kuo-Chen, Li 7   VIAFID ORCID Logo  ; Wei-Chen, Tu 8   VIAFID ORCID Logo  ; Abu Patricia Angela R. 9   VIAFID ORCID Logo  ; Chen Chiung-An 5   VIAFID ORCID Logo 

 Department of Program on Semiconductor Manufacturing Technology (PSMT), Academy of Innovative Semiconductor and Sustainable Manufacturing (AISSM), National Cheng Kung University, Tainan City 701401, Taiwan; [email protected] 
 Department of Electronic Engineering, Chung Yuan Christian University, Taoyuan City 320317, Taiwan; [email protected] (S.-L.C.); [email protected] (Y.-C.L.); [email protected] (X.-M.L.) 
 Department of Operative Dentistry, Taoyuan Chang Gung Memorial Hospital, Taoyuan City 33305, Taiwan; [email protected] 
 Department of Family Dentistry, Taoyuan Chang Gung Memorial Hospital, Taoyuan City 33305, Taiwan; [email protected] 
 Department of Electrical Engineering, Ming Chi University of Technology, New Taipei City 243303, Taiwan; [email protected] 
 Department of Electronic Engineering, Feng Chia University, Taichung City 40724, Taiwan; [email protected] 
 Department of Information Management, Chung Yuan Christian University, Taoyuan City 320317, Taiwan 
 Department of Electrical Engineering, National Cheng Kung University, Tainan City 701401, Taiwan; [email protected] 
 Ateneo Laboratory for Intelligent Visual Environments, Department of Information Systems and Computer Science, Ateneo de Manila University, Quezon City 1108, Philippines; [email protected] 
First page
1194
Publication year
2025
Publication date
2025
Publisher
MDPI AG
e-ISSN
20754418
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3211938224
Copyright
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.