深度学习模型与专家对CTP诊断急性腔隙性卒中的准确性比较
本研究为回顾性诊断准确性研究，纳入澳大利亚两家综合卒中中心疑诊腔隙性卒中的成人患者，以DWI上临床相关腔隙性梗死为参考标准。比较自动化深度学习模型与卒中神经病学专家对CTP的诊断表现，主要指标为AUC、敏感度和特异度。结果显示最佳AI模型仅用脑血流量图即优于专家共识，AUC为0.82（p=0.003），而临床医生总体准确性较差，平均AUC为0.58，观察者间一致性低（Fleiss κ=0.22）。
要点
- 常规CTP判读腔隙性卒中准确性差且观察者间一致性低，平均AUC仅0.58，Fleiss κ为0.22，报告时需警惕假阴性与假阳性
- 本研究最佳AI模型仅使用脑血流量图即达到AUC 0.82，显著优于神经科专家共识（p=0.003），提示CBF图是模型最关键输入
- AI模型在疑似腔隙性卒中病例中表现接近或优于专家，未来可作为急性卒中流程中的决策支持工具，但尚需前瞻性与外部验证
核心结论
- 在疑诊急性腔隙性卒中的患者中，基于常规CTP的深度学习模型诊断准确性可与卒中神经病学专家相当或更优，最佳模型仅用脑血流量图即优于专家共识（AUC 0.82，p=0.003）。
- 临床医生对CTP判读腔隙性卒中的总体准确性较差（平均AUC 0.58），且观察者间一致性低（Fleiss κ=0.22），提示人工解读CTP在该场景下可靠性有限。
研究设计与样本
- 回顾性诊断准确性研究，纳入澳大利亚新南威尔士州两家综合卒中中心疑诊腔隙性卒中的成人患者，均接受常规CTP和DWI检查
- 以DWI上存在临床相关腔隙性梗死作为参考标准，共485例符合条件患者，其中436例（239例腔隙性卒中，197例类似症）用于模型开发
- 预先设定90%病例用于训练和内部测试卷积神经网络，剩余10%共49例（27例腔隙性卒中，22例类似症）构成独立验证数据集
- 独立验证集由卒中神经病学专家在不了解DWI结果的前提下进行判读，同时由训练好的模型预测，计算AUC、敏感度和特异度
关键影像表现/征象
- 最佳AI模型单纯使用脑血流量图即可达到AUC 0.82，提示CBF图在该任务中比专家综合判读更具判别价值
诊断标准与关键数值
- 临床医生平均AUC为0.58，观察者间一致性低，Fleiss κ为0.22
- 最佳AI模型使用脑血流量图单独预测，AUC为0.82，显著优于神经科专家共识，p=0.003
- AI模型与专家敏感度、特异度的具体数值原文未逐项列出，仅报告AUC及模型与专家共识的比较
临床应用与阅片要点
- 在日常急诊卒中影像流程中，若CTP用于疑诊腔隙性卒中，人工判读可靠性差，应降低对单一CTP人工解读结论的依赖
- 脑血流量图是本研究最佳模型唯一输入，阅片及结构化报告时可优先关注CBF图上的局部低灌注区域
- AI模型可作为辅助决策工具嵌入急性卒中工作流程，但在完成前瞻性验证和外部验证前不应作为独立诊断依据
局限性
- 本研究为回顾性设计，独立验证集仅49例，样本量较小，可能影响敏感度和特异度估计的稳定性
- 模型开发与验证来自同一国家的两家中心，缺乏外部验证，泛化能力未经证实
- 参考标准采用DWI上临床相关腔隙性卒中，未详细说明DWI判读流程及对边界病灶的排除标准
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
BACKGROUND: Accurate diagnosis of lacunar stroke in the acute setting is challenging and often depends on MRI or clinical suspicion. CT perfusion (CTP) has only modest diagnostic accuracy and substantial interobserver variability yet is widely available. Artificial intelligence (AI) based tools may therefore be a valuable decision-support aid to improve the reliability of CTP interpretation.
MATERIALS AND METHODS: We conducted a retrospective diagnostic accuracy study comparing a novel automated deep learning model with expert stroke neurologists for the diagnosis of acute lacunar stroke on CTP. Adults presenting to two comprehensive stroke centers in New South Wales, Australia, with a clinical syndrome suspicious for lacunar stroke who underwent standard-of-care CTP and diffusion-weighted MRI (DWI) were included. The reference standard was the presence of a clinically relevant lacunar infarct on DWI. A predetermined 90% of cases were used to train and internally test a convolutional neural network to predict the presence of a DWI lesion, while the remaining 10% formed a held out validation dataset. These held-out cases were interpreted by stroke neurologists, blinded to DWI, and by the trained model. Accuracy metrics, including area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, were calculated for individual neurologists, neurologist consensus, and the AI model.
RESULTS: Among 485 eligible patients, 436 (239 lacunar strokes and 197 mimics) were used for model development. The remaining 49 patients (27 lacunar strokes, 22 mimics) comprised the held out validation dataset. Overall clinician accuracy was poor (mean AUC 0.58) with low interobserver agreement (Fleiss κ = 0.22). The best-performing AI model, using cerebral blood flow maps alone, outperformed neurologist consensus (AUC 0.82, p = 0.003).
CONCLUSION: In patients with suspected acute lacunar stroke, a deep learning model applied to routinely acquired CTP demonstrated diagnostic accuracy comparable to or better than expert stroke neurologists. These findings support further prospective and external validation and exploration of the model as a decision support tool within acute stroke workflows.
引用
- Thomas, Visser, Garcia-Esperon, et al. Accuracy of Automated Deep Learning versus Expert Clinicians for Diagnosis of Acute Lacunar Stroke on CT Perfusion. AJNR Am J Neuroradiol. 2026. PMID: 42229993. doi:10.3174/ajnr.A9445
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。