文献速递神经PET

18F-FDG PET 鉴别帕金森病与非典型帕金森综合征的准确性:系统评价与 Meta 分析

Accuracy of 18F-FDG PET Imaging in Differentiating Parkinson's Disease from Atypical Parkinsonian Syndromes: A Systematic Review and Meta-Analysis.
PubMed 文献 · Acad Radiol · 2024-08-24

该系统评价与 Meta 分析检索 PubMed、Embase 和 Web of Science 建库至 2024 年 6 月的研究,纳入 24 项研究、1508 例帕金森病患者和 1370 例非典型帕金森综合征患者,评估 18F-FDG PET 鉴别两者的准确性。放射科医生直接视觉判读诊断帕金森病的汇总敏感度 96%、特异度 90%、SROC-AUC 0.98;单变量算法支持的视觉判读为 93%、90%、0.96;机器学习为 87%、91%、0.95;深度学习为 97%、95%、0.98。结论认为 18F-FDG PET 鉴别准确性高,人工智能辅助自动分类表现良好,诊断准确性可与放射科医生相媲美,有望成为未来临床诊断的重要辅助手段。

要点

  • 18F-FDG PET 鉴别帕金森病与非典型帕金森综合征准确性高,放射科医生直接视觉判读 SROC-AUC 达 0.98。
  • 深度学习诊断帕金森病汇总敏感度 97%、特异度 95%、SROC-AUC 0.98,与放射科医生直接视觉判读相当。
  • 机器学习诊断帕金森病汇总敏感度 87%、特异度 91%、SROC-AUC 0.95。

核心结论

  • 18F-FDG PET 鉴别帕金森病与非典型帕金森综合征准确性高,其中人工智能辅助自动分类表现良好,诊断准确性可与放射科医生相媲美,有望成为未来临床诊断的重要辅助手段。

研究设计与样本

  • 系统评价与 Meta 分析,检索 PubMed、Embase 和 Web of Science 建库至 2024 年 6 月的研究。
  • 纳入 24 项使用 18F-FDG PET 鉴别帕金森病与非典型帕金森综合征的研究,共 1508 例帕金森病患者和 1370 例非典型帕金森综合征患者。
  • 采用 QUADAS-2 或 QUADAS-AI 工具评估纳入研究的偏倚风险,采用双变量随机效应模型计算汇总敏感度、特异度和 SROC 曲线下面积。

诊断标准与关键数值

  • 12 项研究依赖放射科医生视觉判读,直接视觉判读诊断帕金森病的汇总敏感度 96%(95%CI:91%,98%)、特异度 90%(95%CI:83%,95%)、SROC-AUC 0.98(95%CI:0.96,0.99)。
  • 单变量算法支持的视觉判读诊断帕金森病的汇总敏感度 93%(95%CI:90%,95%)、特异度 90%(95%CI:85%,94%)、SROC-AUC 0.96(95%CI:0.94,0.97)。
  • 12 项研究依赖人工智能分析 18F-FDG PET 数据,机器学习诊断帕金森病的汇总敏感度 87%(95%CI:82%,91%)、特异度 91%(95%CI:86%,94%)、SROC-AUC 0.95(95%CI:0.93,0.96)。
  • 深度学习诊断帕金森病的汇总敏感度 97%(95%CI:95%,98%)、特异度 95%(95%CI:89%,98%)、SROC-AUC 0.98(95%CI:0.96,0.99)。

临床应用与阅片要点

  • 原文结论认为 18F-FDG PET 鉴别帕金森病与非典型帕金森综合征准确性高,人工智能辅助自动分类表现良好,诊断准确性可与放射科医生相媲美,有望成为未来临床诊断的重要辅助手段。

局限性

  • 原文未报告局限性。

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)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVE: To quantitatively assess the accuracy of 18F-FDG PET in differentiating Parkinson's Disease (PD) from Atypical Parkinsonian Syndromes (APSs).

METHODS: PubMed, Embase, and Web of Science databases were searched to identify studies published from the inception of the databases up to June 2024 that used 18F-FDG PET imaging for the differential diagnosis of PD and APSs. The risk of bias in the included studies was assessed using the QUADAS-2 or QUADAS-AI tool. Bivariate random-effects models were used to calculate the pooled sensitivity, specificity, and the area under the curves (AUC) of summary receiver operating characteristic (SROC).

RESULTS: 24 studies met the inclusion criteria, involving a total of 1508 PD patients and 1370 APSs patients. 12 studies relied on visual interpretation by radiologists, of which the pooled sensitivity, specificity, and SROC-AUC for direct visual interpretation in diagnosing PD were 96% (95%CI: 91%, 98%), 90% (95%CI: 83%, 95%), and 0.98 (95%CI: 0.96, 0.99), respectively; the pooled sensitivity, specificity, and SROC-AUC for visual interpretation supported by univariate algorithms in diagnosing PD were 93% (95%CI: 90%, 95%), 90% (95%CI: 85%, 94%), and 0.96 (95%CI: 0.94, 0.97), respectively. 12 studies relied on artificial intelligence (AI) to analyze 18F-FDG PET imaging data. The pooled sensitivity, specificity, and SROC-AUC of machine learning (ML) for diagnosing PD were 87% (95%CI: 82%, 91%), 91% (95%CI: 86%, 94%), and 0.95 (95%CI: 0.93, 0.96), respectively. The pooled sensitivity, specificity, and SROC-AUC of deep learning (DL) for diagnosing PD were 97% (95%CI: 95%, 98%), 95% (95%CI: 89%, 98%), and 0.98 (95%CI: 0.96, 0.99), respectively.

CONCLUSION: 18F-FDG PET has a high accuracy in differentiating PD from APS, among which AI-assisted automatic classification performs well, with a diagnostic accuracy comparable to that of radiologists, and is expected to become an important auxiliary means of clinical diagnosis in the future.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Zhao T, Wang B, Liang W, et al. Accuracy of 18F-FDG PET Imaging in Differentiating Parkinson's Disease from Atypical Parkinsonian Syndromes: A Systematic Review and Meta-Analysis. Acad Radiol. 2024. PMID: 39183130. doi:10.1016/j.acra.2024.08.016

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。