对咬翼x线片龋检测的评估:改进的深度学习模型与牙医性能的比较分析。

IF 3.2 3区 医学 Q1 DENTISTRY, ORAL SURGERY & MEDICINE
Baturalp Ayhan, Enes Ayan, Gökhan Karadağ, Yusuf Bayraktar
{"title":"对咬翼x线片龋检测的评估:改进的深度学习模型与牙医性能的比较分析。","authors":"Baturalp Ayhan, Enes Ayan, Gökhan Karadağ, Yusuf Bayraktar","doi":"10.1111/jerd.13470","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>The application of deep learning techniques for detecting caries in bitewing radiographs has gained significant attention in recent years. However, the comparative performance of various modern deep learning models and strategies to enhance their accuracy remains an area requiring further investigation.</p><p><strong>Methods: </strong>This study explored the capabilities of 11 widely used YOLO (You Only Look Once) object detection models to automatically identify enamel and dentin caries from bitewing radiographs. To further optimize detection performance, the YOLOv9c model's backbone architecture was refined, reducing both model size and computational requirements. The enhanced model was assessed alongside six dentists, using the same test dataset for direct comparison.</p><p><strong>Results: </strong>The proposed YOLOv9c model achieved the highest performance among the evaluated models, with recall, precision, specificity, F1-score, and Youden index values of 0.727, 0.651, 0.726, 0.687, and 0.453, respectively. Notably, the YOLOv9c model surpassed the performance of the dentists, as indicated by its recall and F1-score values.</p><p><strong>Conclusions: </strong>The proposed YOLOv9c model proved to be highly effective in detecting enamel and dentin caries, outperforming other models and even clinical evaluations by dentists in this study. Its high accuracy positions it as a valuable tool to augment dentists' diagnostic capabilities.</p><p><strong>Clinical significance: </strong>The results emphasize the potential of the YOLOv9c model to assist dentists in clinical settings, offering accurate and efficient support for caries detection and contributing to improved patient outcomes.</p>","PeriodicalId":15988,"journal":{"name":"Journal of Esthetic and Restorative Dentistry","volume":" ","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Evaluation of Caries Detection on Bitewing Radiographs: A Comparative Analysis of the Improved Deep Learning Model and Dentist Performance.\",\"authors\":\"Baturalp Ayhan, Enes Ayan, Gökhan Karadağ, Yusuf Bayraktar\",\"doi\":\"10.1111/jerd.13470\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>The application of deep learning techniques for detecting caries in bitewing radiographs has gained significant attention in recent years. However, the comparative performance of various modern deep learning models and strategies to enhance their accuracy remains an area requiring further investigation.</p><p><strong>Methods: </strong>This study explored the capabilities of 11 widely used YOLO (You Only Look Once) object detection models to automatically identify enamel and dentin caries from bitewing radiographs. To further optimize detection performance, the YOLOv9c model's backbone architecture was refined, reducing both model size and computational requirements. The enhanced model was assessed alongside six dentists, using the same test dataset for direct comparison.</p><p><strong>Results: </strong>The proposed YOLOv9c model achieved the highest performance among the evaluated models, with recall, precision, specificity, F1-score, and Youden index values of 0.727, 0.651, 0.726, 0.687, and 0.453, respectively. Notably, the YOLOv9c model surpassed the performance of the dentists, as indicated by its recall and F1-score values.</p><p><strong>Conclusions: </strong>The proposed YOLOv9c model proved to be highly effective in detecting enamel and dentin caries, outperforming other models and even clinical evaluations by dentists in this study. Its high accuracy positions it as a valuable tool to augment dentists' diagnostic capabilities.</p><p><strong>Clinical significance: </strong>The results emphasize the potential of the YOLOv9c model to assist dentists in clinical settings, offering accurate and efficient support for caries detection and contributing to improved patient outcomes.</p>\",\"PeriodicalId\":15988,\"journal\":{\"name\":\"Journal of Esthetic and Restorative Dentistry\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.2000,\"publicationDate\":\"2025-04-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Esthetic and Restorative Dentistry\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1111/jerd.13470\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"DENTISTRY, ORAL SURGERY & MEDICINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Esthetic and Restorative Dentistry","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/jerd.13470","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}
引用次数: 0

摘要

目的:近年来,深度学习技术在咬颌x线片龋齿检测中的应用得到了广泛的关注。然而,各种现代深度学习模型和策略的比较性能,以提高其准确性仍然是一个需要进一步研究的领域。方法:研究了11种常用的YOLO (You Only Look Once)目标检测模型在咬牙x线片中自动识别牙本质和牙釉质龋的能力。为了进一步优化检测性能,对YOLOv9c模型的主干架构进行了细化,减小了模型尺寸和计算需求。增强模型与六位牙医一起进行评估,使用相同的测试数据集进行直接比较。结果:提出的YOLOv9c模型在评价模型中表现最好,召回率为0.727,精密度为0.651,特异性为0.726,f1评分为0.687,约登指数值为0.453。值得注意的是,YOLOv9c模型的召回率和f1得分值超过了牙医的表现。结论:本研究所建立的YOLOv9c模型在牙釉质和牙本质龋的检测上具有较高的效率,优于其他模型,甚至优于牙医的临床评价。它的高精度定位它作为一个有价值的工具,以增加牙医的诊断能力。临床意义:结果强调了YOLOv9c模型在临床环境中协助牙医的潜力,为龋齿检测提供准确有效的支持,并有助于改善患者的预后。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Evaluation of Caries Detection on Bitewing Radiographs: A Comparative Analysis of the Improved Deep Learning Model and Dentist Performance.

Objectives: The application of deep learning techniques for detecting caries in bitewing radiographs has gained significant attention in recent years. However, the comparative performance of various modern deep learning models and strategies to enhance their accuracy remains an area requiring further investigation.

Methods: This study explored the capabilities of 11 widely used YOLO (You Only Look Once) object detection models to automatically identify enamel and dentin caries from bitewing radiographs. To further optimize detection performance, the YOLOv9c model's backbone architecture was refined, reducing both model size and computational requirements. The enhanced model was assessed alongside six dentists, using the same test dataset for direct comparison.

Results: The proposed YOLOv9c model achieved the highest performance among the evaluated models, with recall, precision, specificity, F1-score, and Youden index values of 0.727, 0.651, 0.726, 0.687, and 0.453, respectively. Notably, the YOLOv9c model surpassed the performance of the dentists, as indicated by its recall and F1-score values.

Conclusions: The proposed YOLOv9c model proved to be highly effective in detecting enamel and dentin caries, outperforming other models and even clinical evaluations by dentists in this study. Its high accuracy positions it as a valuable tool to augment dentists' diagnostic capabilities.

Clinical significance: The results emphasize the potential of the YOLOv9c model to assist dentists in clinical settings, offering accurate and efficient support for caries detection and contributing to improved patient outcomes.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Esthetic and Restorative Dentistry
Journal of Esthetic and Restorative Dentistry 医学-牙科与口腔外科
CiteScore
6.30
自引率
6.20%
发文量
124
审稿时长
>12 weeks
期刊介绍: The Journal of Esthetic and Restorative Dentistry (JERD) is the longest standing peer-reviewed journal devoted solely to advancing the knowledge and practice of esthetic dentistry. Its goal is to provide the very latest evidence-based information in the realm of contemporary interdisciplinary esthetic dentistry through high quality clinical papers, sound research reports and educational features. The range of topics covered in the journal includes: - Interdisciplinary esthetic concepts - Implants - Conservative adhesive restorations - Tooth Whitening - Prosthodontic materials and techniques - Dental materials - Orthodontic, periodontal and endodontic esthetics - Esthetics related research - Innovations in esthetics
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信