• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于 YOLO-V5 的深度学习方法在混合牙列的小儿全景片中进行牙齿检测和分割。

YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition.

机构信息

Department of Orthodontics, Faculty of Dentistry, Recep Tayyip Erdogan University, Rize, Turkey.

Pedodontics, Private Practice, Trabzon, Turkey.

出版信息

BMC Med Imaging. 2024 Jul 11;24(1):172. doi: 10.1186/s12880-024-01338-w.

DOI:10.1186/s12880-024-01338-w
PMID:38992601
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11238494/
Abstract

OBJECTIVES

In the interpretation of panoramic radiographs (PRs), the identification and numbering of teeth is an important part of the correct diagnosis. This study evaluates the effectiveness of YOLO-v5 in the automatic detection, segmentation, and numbering of deciduous and permanent teeth in mixed dentition pediatric patients based on PRs.

METHODS

A total of 3854 mixed pediatric patients PRs were labelled for deciduous and permanent teeth using the CranioCatch labeling program. The dataset was divided into three subsets: training (n = 3093, 80% of the total), validation (n = 387, 10% of the total) and test (n = 385, 10% of the total). An artificial intelligence (AI) algorithm using YOLO-v5 models were developed.

RESULTS

The sensitivity, precision, F-1 score, and mean average precision-0.5 (mAP-0.5) values were 0.99, 0.99, 0.99, and 0.98 respectively, to teeth detection. The sensitivity, precision, F-1 score, and mAP-0.5 values were 0.98, 0.98, 0.98, and 0.98, respectively, to teeth segmentation.

CONCLUSIONS

YOLO-v5 based models can have the potential to detect and enable the accurate segmentation of deciduous and permanent teeth using PRs of pediatric patients with mixed dentition.

摘要

目的

在全景放射影像（PR）解读中，牙齿的识别和编号是正确诊断的重要组成部分。本研究评估了 YOLO-v5 在基于 PR 对混合牙列儿童患者的乳牙和恒牙进行自动检测、分割和编号的有效性。

方法

使用 CranioCatch 标注程序对 3854 名混合儿科患者的 PR 进行了乳牙和恒牙的标注。数据集分为三个子集：训练集（n=3093，占总数的 80%）、验证集（n=387，占总数的 10%）和测试集（n=385，占总数的 10%）。开发了一种使用 YOLO-v5 模型的人工智能（AI）算法。

结果

牙齿检测的灵敏度、精度、F1 评分和平均精度-0.5（mAP-0.5）值分别为 0.99、0.99、0.99 和 0.98。牙齿分割的灵敏度、精度、F1 评分和 mAP-0.5 值分别为 0.98、0.98、0.98 和 0.98。

结论

基于 YOLO-v5 的模型有可能通过混合牙列儿童患者的 PR 检测并实现乳牙和恒牙的精确分割。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/a7f89d215264/12880_2024_1338_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/55d246fad8e2/12880_2024_1338_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/ff95984eafa5/12880_2024_1338_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/aa1e6e34ba7f/12880_2024_1338_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/61b6bae56982/12880_2024_1338_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/922023af1bd4/12880_2024_1338_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/a7f89d215264/12880_2024_1338_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/55d246fad8e2/12880_2024_1338_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/ff95984eafa5/12880_2024_1338_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/aa1e6e34ba7f/12880_2024_1338_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/61b6bae56982/12880_2024_1338_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/922023af1bd4/12880_2024_1338_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3800/11238494/a7f89d215264/12880_2024_1338_Fig6_HTML.jpg

相似文献

1
YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition.基于 YOLO-V5 的深度学习方法在混合牙列的小儿全景片中进行牙齿检测和分割。
BMC Med Imaging. 2024 Jul 11;24(1):172. doi: 10.1186/s12880-024-01338-w.
2
Artificial intelligence system for automatic deciduous tooth detection and numbering in panoramic radiographs.用于全景片上自动检测和编号乳牙的人工智能系统。
Dentomaxillofac Radiol. 2021 Sep 1;50(6):20200172. doi: 10.1259/dmfr.20200172. Epub 2021 Mar 4.
3
Proposing a CNN Method for Primary and Permanent Tooth Detection and Enumeration on Pediatric Dental Radiographs.提出一种基于卷积神经网络的儿童口腔 X 射线片中乳牙和恒牙检测与计数方法。
J Clin Pediatr Dent. 2022 Jul 1;46(4):293-298. doi: 10.22514/1053-4625-46.4.6.
4
Automated permanent tooth detection and numbering on panoramic radiograph using a deep learning approach.基于深度学习的全景片上恒牙自动检测和编号。
Oral Surg Oral Med Oral Pathol Oral Radiol. 2024 May;137(5):537-544. doi: 10.1016/j.oooo.2023.06.003. Epub 2023 Jun 8.
5
A novel collaborative learning model for mixed dentition and fillings segmentation in panoramic radiographs.全景片混合牙列和填充物分割的新型协同学习模型。
J Dent. 2024 Jan;140:104779. doi: 10.1016/j.jdent.2023.104779. Epub 2023 Nov 24.
6
An artifıcial ıntelligence approach to automatic tooth detection and numbering in panoramic radiographs.一种人工智能方法，用于在全景放射片中自动检测和编号牙齿。
BMC Med Imaging. 2021 Aug 13;21(1):124. doi: 10.1186/s12880-021-00656-7.
7
A Deep Learning Approach to Automatic Tooth Caries Segmentation in Panoramic Radiographs of Children in Primary Dentition, Mixed Dentition, and Permanent Dentition.一种用于乳牙列、混合牙列和恒牙列儿童全景X线片中龋齿自动分割的深度学习方法。
Children (Basel). 2024 Jun 5;11(6):690. doi: 10.3390/children11060690.
8
A dual-labeled dataset and fusion model for automatic teeth segmentation, numbering, and state assessment on panoramic radiographs.基于全景片的自动牙齿分割、编号和状态评估的双标记数据集和融合模型。
BMC Oral Health. 2024 Oct 9;24(1):1201. doi: 10.1186/s12903-024-04984-2.
9
Robust automated teeth identification from dental radiographs using deep learning.使用深度学习技术从口腔 X 光片中稳健地自动识别牙齿。
J Dent. 2023 Sep;136:104607. doi: 10.1016/j.jdent.2023.104607. Epub 2023 Jul 6.
10
Deep learning for automated detection and numbering of permanent teeth on panoramic images.基于深度学习的全景影像中恒牙自动检测与编号
Dentomaxillofac Radiol. 2022 Feb 1;51(2):20210296. doi: 10.1259/dmfr.20210296. Epub 2021 Oct 13.

引用本文的文献

1
Segmentation of airways and soft tissues on panoramic radiographs using artificial intelligence technology.利用人工智能技术对全景X光片上的气道和软组织进行分割。
BMC Oral Health. 2025 Jun 2;25(1):876. doi: 10.1186/s12903-025-06187-9.
2
Automatic mandibular third molar and mandibular canal relationship determination based on deep learning models for preoperative risk reduction.基于深度学习模型的下颌第三磨牙与下颌管关系自动判定以降低术前风险
Clin Oral Investig. 2025 Mar 25;29(4):203. doi: 10.1007/s00784-025-06285-6.
3
Segmentation of the nasopalatine canal and detection of canal furcation status with artificial intelligence on cone-beam computed tomography images.

本文引用的文献

1
Deep learning for tooth identification and numbering on dental radiography: a systematic review and meta-analysis.深度学习在口腔 X 光片上的牙齿识别和编号中的应用：系统评价和荟萃分析。
Dentomaxillofac Radiol. 2024 Jan 11;53(1):5-21. doi: 10.1093/dmfr/twad001.
2
A novel collaborative learning model for mixed dentition and fillings segmentation in panoramic radiographs.全景片混合牙列和填充物分割的新型协同学习模型。
J Dent. 2024 Jan;140:104779. doi: 10.1016/j.jdent.2023.104779. Epub 2023 Nov 24.
3
An artificial intelligence study: automatic description of anatomic landmarks on panoramic radiographs in the pediatric population.
锥形束计算机断层扫描图像上利用人工智能对鼻腭管进行分割并检测管分叉状态
Oral Radiol. 2025 Feb 28. doi: 10.1007/s11282-025-00812-7.
4
Evaluation of the Performance of a YOLOv10-Based Deep Learning Model for Tooth Detection and Numbering on Panoramic Radiographs of Patients in the Mixed Dentition Period.基于YOLOv10的深度学习模型在混合牙列期患者全景X线片上进行牙齿检测和编号的性能评估
Diagnostics (Basel). 2025 Feb 7;15(4):405. doi: 10.3390/diagnostics15040405.
一项人工智能研究：在儿科人群的全景片上自动描述解剖标志。
BMC Oral Health. 2023 Oct 17;23(1):764. doi: 10.1186/s12903-023-03532-8.
4
External root resorption and rapid maxillary expansion in the short-term: a CBCT comparative study between tooth-borne and bone-borne appliances, using 3D imaging digital technology.短期中外源性牙根吸收与上颌快速扩弓：基于三维成像数字技术的牙支抗与骨支抗装置的 CBCT 对比研究。
BMC Oral Health. 2023 Aug 12;23(1):558. doi: 10.1186/s12903-023-03280-9.
5
Deep Learning in Diagnosis of Dental Anomalies and Diseases: A Systematic Review.深度学习在牙体异常与疾病诊断中的应用：一项系统综述
Diagnostics (Basel). 2023 Jul 27;13(15):2512. doi: 10.3390/diagnostics13152512.
6
A fine-tuned YOLOv5 deep learning approach for real-time house number detection.一种用于实时门牌号检测的微调YOLOv5深度学习方法。
PeerJ Comput Sci. 2023 Jul 3;9:e1453. doi: 10.7717/peerj-cs.1453. eCollection 2023.
7
Robust automated teeth identification from dental radiographs using deep learning.使用深度学习技术从口腔 X 光片中稳健地自动识别牙齿。
J Dent. 2023 Sep;136:104607. doi: 10.1016/j.jdent.2023.104607. Epub 2023 Jul 6.
8
Children's dental panoramic radiographs dataset for caries segmentation and dental disease detection.儿童口腔全景放射数据集，用于龋齿分割和口腔疾病检测。
Sci Data. 2023 Jun 14;10(1):380. doi: 10.1038/s41597-023-02237-5.
9
Developing deep learning methods for classification of teeth in dental panoramic radiography.开发用于牙科全景射线照相中牙齿分类的深度学习方法。
Oral Surg Oral Med Oral Pathol Oral Radiol. 2024 Jul;138(1):118-127. doi: 10.1016/j.oooo.2023.02.021. Epub 2023 Mar 30.
10
Artificial Intelligence Its Uses and Application in Pediatric Dentistry: A Review.人工智能在儿童牙科中的应用及其用途：综述
Biomedicines. 2023 Mar 5;11(3):788. doi: 10.3390/biomedicines11030788.