文献速递口腔修复与种植

基于大规模多中心数据集的牙种植体系统识别

Identification of Dental Implant Systems Using a Large-Scale Multicenter Data Set.
PubMed 文献 · J Dent Res · 2023-04-21

本研究利用5所大学口腔医院和10家私人诊所的影像数据(37,442张根尖片和113,291张全景片,涵盖10个制造商25种种植体系统),评估深度学习(DL)识别分类牙种植体系统的效能,并与口腔专业人员比较。DL分类准确率为82.0%(95%CI 75.9%-87.0%),优于多数参与者(平均准确率23.5%±18.5%),且阅读分类时间(4.5分钟)少于种植专业医生(75.6±31.0分钟)和非专业医生(91.3±38.3分钟)。

要点

  • DL对25种牙种植体系统的分类准确率达82.0%(95%CI 75.9%-87.0%)。
  • DL准确率显著优于种植专业医生(平均43.3%±20.4%)和非专业医生(平均16.8%±9.0%)。
  • DL阅读分类时间仅4.5分钟,远少于专业医生(75.6±31.0分钟)和非专业医生(91.3±38.3分钟)。

核心结论

  • DL在多种牙种植体系统识别分类中取得可靠结果,分类准确率显著优于种植专业和非专业口腔医生。
  • DL可作为决策支持工具用于临床实践中牙种植体系统的识别和分类。

研究设计与样本

  • 研究采用大规模多中心数据集,数据来自5所大学口腔医院和10家私人诊所。
  • 数据集包含37,442张(24.8%)根尖片和113,291张(75.2%)全景片,涵盖10个制造商、25种牙种植体系统。
  • DL分类准确率使用预训练并修改的ResNet-50架构评估,并与口腔专业人员进行准确性和阅读时间比较(自报问卷)。

主要发现

  • DL分类准确率为82.0%(95%CI 75.9%-87.0%),优于大多数参与者(平均准确率23.5%±18.5%;95%CI 18.5%-32.3%)。
  • 种植专业医生平均准确率为43.3%±20.4%(95%CI 12.7%-56.2%),非专业医生平均准确率为16.8%±9.0%(95%CI 12.8%-20.9%)。
  • DL阅读分类时间倾向少于种植专业医生(75.6±31.0分钟;95%CI 13.1-78.4)和非专业医生(91.3±38.3分钟;95%CI 74.1-108.6),DL为4.5分钟。

临床怎么用

  • DL可作为决策支持辅助工具,用于临床实践中牙种植体系统的识别和分类。

局限性

  • 原文未述局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

This study aimed to evaluate the efficacy of deep learning (DL) for the identification and classification of various types of dental implant systems (DISs) using a large-scale multicenter data set. We also compared the classification accuracy of DL and dental professionals. The data set, which was collected from 5 college dental hospitals and 10 private dental clinics, contained 37,442 (24.8%) periapical and 113,291 (75.2%) panoramic radiographic images and consisted of a total of 10 manufacturers and 25 different types of DISs. The classification accuracy of DL was evaluated using a pretrained and modified ResNet-50 architecture, and comparison of accuracy performance and reading time between DL and dental professionals was conducted using a self-reported questionnaire. When comparing the accuracy performance for classification of DISs, DL (accuracy: 82.0%; 95% confidence interval [CI], 75.9%-87.0%) outperformed most of the participants (mean accuracy: 23.5% ± 18.5%; 95% CI, 18.5%-32.3%), including dentists specialized (mean accuracy: 43.3% ± 20.4%; 95% CI, 12.7%-56.2%) and not specialized (mean accuracy: 16.8% ± 9.0%; 95% CI, 12.8%-20.9%) in implantology. In addition, DL tends to require lesser reading and classification time (4.5 min) than dentists who specialized (75.6 ± 31.0 min; 95% CI, 13.1-78.4) and did not specialize (91.3 ± 38.3 min; 95% CI, 74.1-108.6) in implantology. DL achieved reliable outcomes in the identification and classification of various types of DISs, and the classification accuracy performance of DL was significantly superior to that of specialized or nonspecialized dental professionals. DL as a decision support aid can be successfully used for the identification and classification of DISs encountered in clinical practice.

来源:J Dent Res,查看原文。版权归原作者所有。

引用

  1. Park W, Schwendicke F, Krois J, et al. Identification of Dental Implant Systems Using a Large-Scale Multicenter Data Set. J Dent Res. 2023. PMID: 37085970. doi:10.1177/00220345231160750

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。