文献速递神经CT

深度学习辅助检测颅内出血:验证及对阅片者表现的影响

Deep learning-assisted detection of intracranial hemorrhage: validation and impact on reader performance.
PubMed 文献 · Neuroradiology · 2025-03-21

本研究为关键性临床试验,用三级医院回顾性CT及美国多种族外部数据集验证深度学习算法JLK-ICH检测颅内出血的效能,并让6名非专家阅片者对800例CT在有无JLK-ICH辅助下评分。算法敏感度98.7%、特异度88.5%、AUROC 0.936;辅助后阅片者AUROC由0.953升至0.967(P=0.009),在高度不确定时改善尤为明显。

要点

  • JLK-ICH检测颅内出血敏感度98.7%、特异度88.5%,AUROC 0.936。
  • 非专家阅片者辅助后AUROC 0.967,高于无辅助的0.953(P=0.009)。
  • 阅片者高度不确定时,JLK-ICH辅助改善尤为明显。

核心结论

  • JLK-ICH算法检测所有颅内出血亚型均表现出高准确度。
  • 非专家阅片者在深度学习辅助下显著提高了脑CT诊断准确度。

研究设计与样本

  • 关键性临床试验,回顾性收集三级医院有和无颅内出血患者的CT扫描,由两名专家评估全部扫描、第三名专家复核分歧得出最终诊断。
  • 共评估1370例CT扫描,并使用美国多种族外部数据集进行外部验证。
  • 阅片者表现研究纳入6名非专家阅片者,在洗脱期后分别在有和无JLK-ICH辅助下评估800例CT扫描,对出血存在与否及五点量表置信水平评分。

诊断标准与关键数值

  • JLK-ICH检测颅内出血:敏感度98.7%(95%CI 97.8-99.3%),特异度88.5%(95%CI 83.6-92.3%),AUROC 0.936(95%CI 0.915-0.957)。
  • 阅片者表现研究:有JLK-ICH辅助AUROC 0.967(95%CI 0.953-0.981),无辅助AUROC 0.953(95%CI 0.938-0.957),P=0.009。

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

PURPOSE: Intracranial hemorrhage (ICH) requires urgent treatment, and accurate and timely diagnosis is essential for improving outcomes. This pivotal clinical trial aimed to validate a deep learning algorithm for ICH detection and assess its clinical utility through a reader performance test.

METHODS: Retrospective CT scans from patients with and without ICH were collected from a tertiary hospital. Two experts evaluated all scans, with a third expert reviewing disagreements for the final diagnosis. We analyzed the performance of the deep learning algorithm, JLK-ICH, for all cases and ICH subtypes. Additional external validation was performed using a multi-ethnic U.S.

DATASET: A reader performance study included six non-expert readers who evaluated 800 CT scans, with and without JLK-ICH assistance, following a washout period. ICH presence and five-point scale confidence level for decisions were rated.

RESULTS: A total of 1,370 CT scans were evaluated. The deep learning model showed 98.7% sensitivity (95% confidence interval [CI] 97.8-99.3%), 88.5% specificity (95% CI, 83.6-92.3%), and an area under the receiver operating characteristic curve (AUROC) of 0.936 (95% CI, 0.915-0.957). The model maintained high accuracy across all ICH subtypes, and additional external validation confirmed these results. In the reader performance study, AUROC with JLK-ICH assistance (0.967 [0.953-0.981]) surpassed that without assistance (0.953 [0.938-0.957]; P = 0.009). JLK-ICH particularly improved performance when readers were highly uncertain.

CONCLUSION: The JLK-ICH algorithm demonstrated high accuracy in detecting all ICH subtypes. Non-expert readers significantly improved diagnostic accuracy for brain CT scans with deep learning assistance.

来源:Neuroradiology,查看原文。版权归原作者所有。

引用

  1. Kang DW, Kim M, Park GH, et al. Deep learning-assisted detection of intracranial hemorrhage: validation and impact on reader performance. Neuroradiology. 2025. PMID: 40116947. doi:10.1007/s00234-025-03560-x

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。