卷积神经网络与放射科医师在脑CT检测颅内出血中的性能比较:系统综述与Meta分析
该系统综述与Meta分析检索2012年1月1日至2020年7月20日数据库,纳入6项以放射科医师报告为参考标准的研究,比较卷积神经网络(CNN)与放射科医师在非增强脑CT诊断颅内出血中的诊断准确性。回顾性研究汇总敏感度96.00%(95%CI 93.00%-97.00%)、特异度97.00%(95%CI 90.00%-99.00%)、SROC 98.00%(95%CI 97.00%-99.00%);回顾性联合外部数据集研究汇总敏感度95.00%(95%CI 91.00%-97.00%)、特异度96.00%(95%CI 91.00%-98.00%)、SROC 98.00%(95%CI 97.00%-99.00%)。结论认为回顾性研究中CNN诊断性能与放射科医师相当,外部验证联合回顾性研究显示CNN性能稍差。
要点
- 回顾性研究中CNN诊断颅内出血的汇总敏感度96.00%、特异度97.00%、SROC 98.00%,与放射科医师相当。
- 联合外部数据集研究汇总敏感度95.00%、特异度96.00%、SROC 98.00%,CNN性能较回顾性研究稍差。
- 作者认为亟需采用稳健参考标准及外部数据集验证的研究。
核心结论
- 回顾性研究中CNN诊断性能与放射科医师相当;外部验证联合回顾性研究显示CNN性能稍差;亟需采用稳健参考标准及外部数据集验证的研究。
研究设计与样本
- 系统综述与Meta分析,检索PubMed、Embase、Scopus和Web of Science(2012年1月1日至2020年7月20日),最终纳入6项研究进行Meta分析;纳入标准为接受非增强脑CT、以CNN深度学习算法及放射科医师报告为最低参考标准的患者。
诊断标准与关键数值
- 回顾性研究:CNN对比参考标准汇总敏感度96.00%(95%CI 93.00%-97.00%)、汇总特异度97.00%(95%CI 90.00%-99.00%)、SROC 98.00%(95%CI 97.00%-99.00%)。
- 回顾性联合外部数据集研究:汇总敏感度95.00%(95%CI 91.00%-97.00%)、汇总特异度96.00%(95%CI 91.00%-98.00%)、汇总SROC 98.00%(95%CI 97.00%-99.00%)。
局限性
- 作者指出亟需采用稳健参考标准及外部数据集验证的研究。
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
PURPOSE: To compare the diagnostic accuracy of convolutional neural networks (CNN) with radiologists as the reference standard in the diagnosis of intracranial hemorrhages (ICH) with non contrast computed tomography of the cerebrum (NCTC).
METHODS: PubMed, Embase, Scopus, and Web of Science were searched for the period from 1 January 2012 to 20 July 2020; eligible studies included patients with and without ICH as the target condition undergoing NCTC, studies had deep learning algorithms based on CNNs and radiologists reports as the minimum reference standard. Pooled sensitivities, specificities and a summary receiver operating characteristics curve (SROC) were employed for meta-analysis.
RESULTS: 5,119 records were identified through database searching. Title-screening left 47 studies for full-text assessment and 6 studies for meta-analysis. Comparing the CNN performance to reference standards in the retrospective studies found a pooled sensitivity of 96.00% (95% CI: 93.00% to 97.00%), pooled specificity of 97.00% (95% CI: 90.00% to 99.00%) and SROC of 98.00% (95% CI: 97.00% to 99.00%), and combining retrospective and studies with external datasets found a pooled sensitivity of 95.00% (95% CI: 91.00% to 97.00%), pooled specificity of 96.00% (95% CI: 91.00% to 98.00%) and a pooled SROC of 98.00% (95% CI: 97.00% to 99.00%).
CONCLUSION: This review found the diagnostic performance of CNNs to be equivalent to that of radiologists for retrospective studies. Out-of-sample external validation studies pooled with retrospective studies found CNN performance to be slightly worse. There is a critical need for studies with a robust reference standard and external data-set validation.
引用
- Daugaard Jørgensen, Antulov, Hess, et al. Convolutional neural network performance compared to radiologists in detecting intracranial hemorrhage from brain computed tomography: A systematic review and meta-analysis. Eur J Radiol. 2021. PMID: 34847397. doi:10.1016/j.ejrad.2021.110073
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。