文献速递口腔修复与种植

人工智能在二维X线片中进行牙种植体分类及种植体周病变识别的系统评价

Artificial intelligence for dental implant classification and peri-implant pathology identification in 2D radiographs: A systematic review.
PubMed 文献 · J Dent · 2024-12-15

本系统评价检索Medline、Embase和Cochrane数据库至2024年9月,纳入29项观察性研究及随机和对照临床试验,评估人工智能在二维X线片中对牙种植体分类和种植体周病变识别的性能。QUADAS-2评估显示10项研究高偏倚风险、15项不明确、仅4项低偏倚风险。作者认为基于人工智能的模型尤其在卷积神经网络方面表现出高准确率,但在广泛临床应用前仍需解决若干局限性,并建议探索联邦学习等更先进技术以提高泛化性和效率。

要点

  • QUADAS-2评估显示10项研究高偏倚风险、15项不明确、仅4项低偏倚风险。
  • 作者认为卷积神经网络等人工智能模型在种植体分类和种植体周病变检测中表现出高准确率,但广泛临床应用前仍需解决若干局限性。

核心结论

  • 基于人工智能的模型尤其是卷积神经网络在牙种植体分类和种植体周病变检测中表现出高准确率,但在广泛临床应用前必须解决若干局限性。
  • 作者建议探索联邦学习等更先进的人工智能技术以提高这些模型在临床实践中的泛化性和效率。

研究设计与样本

  • 系统评价检索Medline、Embase和Cochrane数据库至2024年9月,纳入观察性研究及随机和对照临床试验,检索限近7年发表的英文文献,由两名评价者独立进行文献选择和数据提取。
  • 共识别1465条记录,最终选择29篇参考文献进行定性分析,研究特征汇总于自设表格。
  • 采用QUADAS-2工具由两名操作者独立进行偏倚风险评估。

主要发现

  • 牙种植体分类的总体准确率范围为67%至99%。
  • QUADAS-2工具评估显示10项研究为高偏倚风险、15项为不明确偏倚风险,仅4项被归类为低偏倚风险。

关键数值与推荐

  • 牙种植体分类准确率范围为67%至99%。
  • QUADAS-2评估:高偏倚风险10项、不明确偏倚风险15项、低偏倚风险4项。

临床怎么用

  • 作者认为基于人工智能的模型能够帮助临床医生准确分类未知牙种植体,并实现种植体周炎的早期检测,从而改善患者结局并简化治疗计划。
  • 作者认为在广泛临床应用前必须解决若干局限性,并建议探索联邦学习等更先进的人工智能技术以提高模型的泛化性和效率。

局限性

  • QUADAS-2工具识别10项研究为高偏倚风险、15项为不明确偏倚风险,仅4项为低偏倚风险。
  • 作者指出在广泛临床应用前必须解决若干局限性。

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

OBJECTIVE: This systematic review aimed to summarize and evaluate the available information regarding the performance of artificial intelligence on dental implant classification and peri-implant pathology identification in 2D radiographs. DATA SOURCES: Electronic databases (Medline, Embase, and Cochrane) were searched up to September 2024 for relevant observational studies and both randomized and controlled clinical trials. The search was limited to studies published in English from the last 7 years. Two reviewers independently conducted both study selection and data extraction. Risk of bias assessment was also performed individually by both operators using the Quality Assessment Diagnostic Tool (QUADAS-2). STUDY SELECTION: Of the 1,465 records identified, 29 references were selected to perform qualitative analysis. The study characteristics were tabulated in a self-designed table. QUADAS-2 tool identified 10 and 15 studies to respectively have a high and an unclear risk of bias, while only four were categorized as low risk of bias. Overall, accuracy rates for dental implant classification ranged from 67 % to 99 %. Peri-implant pathology identification showed results with accuracy detection rates over 78,6 %. CONCLUSIONS: While AI-based models, particularly convolutional neural networks, have shown high accuracy in dental implant classification and peri-implant pathology detection, several limitations must be addressed before widespread clinical application. More advanced AI techniques, such as Federated Learning should be explored to improve the generalizability and efficiency of these models in clinical practice. CLINICAL SIGNIFICANCE: AI-based models offer can and clinicians to accurately classify unknown dental implants and enable early detection of peri-implantitis, improving patient outcomes and streamline treatment planning.

来源:J Dent,查看原文。版权归原作者所有。

引用

  1. Bonfanti-Gris M, Ruales E, Salido MP, et al. Artificial intelligence for dental implant classification and peri-implant pathology identification in 2D radiographs: A systematic review. J Dent. 2024. PMID: 39681182. doi:10.1016/j.jdent.2024.105533

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。