文献速递神经CT

基于深度学习的自动ASPECTS计算可提高急性缺血性卒中患者的诊断效率:一项多中心研究

Deep learning-based automatic ASPECTS calculation can improve diagnosis efficiency in patients with acute ischemic stroke: a multicenter study.
PubMed 文献 · Eur Radiol · 2024-07-27

本研究基于四中心2017年1月至2021年10月回顾性收集的1987例平扫CT,开发并验证深度学习自动ASPECTS系统,以专家共识为参考标准。系统在独立测试集(N=220)总体分析AUC为84.97%、ICC为0.84,二分类ASPECTS≥6阈值下敏感度94.61%。系统与医师结合使AUC从67.43升至89.76%,诊断时间从130.6±66.3秒降至33.3±8.3秒(p<0.001)。

要点

  • 系统在测试集总体分析AUC为84.97%、ICC为0.84,与专家评分一致性良好。
  • 二分类ASPECTS≥6阈值下系统诊断敏感度为94.61%,与专家评分ICC=0.65。
  • 系统联合医师使AUC从67.43升至89.76%,诊断时间从130.6±66.3秒降至33.3±8.3秒。

核心结论

  • 所提出的深度学习系统可准确、快速地确定ASPECTS,可能促进早期干预的临床工作流程。
  • 临床应用时仍需医师验证。

研究设计与样本

  • 研究为多中心研究,回顾性收集四中心2017年1月至2021年10月的1987例平扫CT扫描。
  • 深度学习自动ASPECTS系统在开发队列(N=1767)训练,在独立测试队列(N=220)验证。
  • 以经验丰富医师的共识作为参考标准。
  • 另采用13399例患者的真实世界前瞻性应用研究进行临床情境下的系统验证。

关键影像表现/征象

  • 深度学习系统在测试队列总体分析中受试者工作特征曲线下面积(AUC)为84.97%,组内相关系数(ICC)为0.84。
  • 系统与专家评分的一致性为中等(ICC=0.65)。

诊断标准与关键数值

  • 二分类ASPECTS以≥6为阈值时,系统诊断敏感度为94.61%。
  • 系统在测试队列总体分析的AUC为84.97%,ICC为0.84。
  • 系统联合医师使AUC从67.43升至89.76%。
  • 系统联合医师使诊断时间从130.6±66.3秒降至33.3±8.3秒(p<0.001)。
  • 前瞻性临床应用研究中,系统成功处理的扫描94.0%(12591例)被临床医生使用,96%的医师认可工作效率显著改善。

临床应用与阅片要点

  • 深度学习系统可快速给出ASPECTS,联合医师判读可提高诊断AUC并缩短诊断时间。
  • 系统将医师处理时间减少74.8%。
  • 临床应用时系统结果仍需医师验证。

局限性

  • 临床应用时仍需医师验证。

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

OBJECTIVES: The Alberta Stroke Program Early CT Score (ASPECTS), a systematic method for assessing ischemic changes in acute ischemic stroke using non-contrast computed tomography (NCCT), is often interpreted relying on expert experience and can vary between readers. This study aimed to develop a clinically applicable automatic ASPECTS system employing deep learning (DL).

METHODS: This study enrolled 1987 NCCT scans that were retrospectively collected from four centers between January 2017 and October 2021. A DL-based system for automated ASPECTS assessment was trained on a development cohort (N = 1767) and validated on an independent test cohort (N = 220). The consensus of experienced physicians was regarded as a reference standard. The validity and reliability of the proposed system were assessed against physicians' readings. A real-world prospective application study with 13,399 patients was used for system validation in clinical contexts.

RESULTS: The DL-based system achieved an area under the receiver operating characteristic curve (AUC) of 84.97% and an intraclass correlation coefficient (ICC) of 0.84 for overall-level analysis on the test cohort. The system's diagnostic sensitivity was 94.61% for patients with dichotomized ASPECTS at a threshold of ≥ 6, with substantial agreement (ICC = 0.65) with expert ratings. Combining the system with physicians improved AUC from 67.43 to 89.76%, reducing diagnosis time from 130.6 ± 66.3 s to 33.3 ± 8.3 s (p < 0.001). During the application in clinical contexts, 94.0% (12,591) of scans successfully processed by the system were utilized by clinicians, and 96% of physicians acknowledged significant improvement in work efficiency.

CONCLUSION: The proposed DL-based system could accurately and rapidly determine ASPECTS, which might facilitate clinical workflow for early intervention.

CLINICAL RELEVANCE STATEMENT: The deep learning-based automated ASPECTS evaluation system can accurately and rapidly determine ASPECTS for early intervention in clinical workflows, reducing processing time for physicians by 74.8%, but still requires validation by physicians when in clinical applications.

KEY POINTS: The deep learning-based system for ASPECTS quantification has been shown to be non-inferior to expert-rated ASPECTS. This system improved the consistency of ASPECTS evaluation and reduced processing time to 33.3 seconds per scan. 94.0% of scans successfully processed by the system were utilized by clinicians during the prospective clinical application.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Wei J, Shang K, Wei X, et al. Deep learning-based automatic ASPECTS calculation can improve diagnosis efficiency in patients with acute ischemic stroke: a multicenter study. Eur Radiol. 2024. PMID: 39060495. doi:10.1007/s00330-024-10960-9

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。