文献速递神经MR

频谱偏差对基于深度学习的卒中MRI分析的影响

Impact of spectrum bias on deep learning-based stroke MRI analysis.
PubMed 文献 · Eur J Radiol · 2025-05-08

本研究为单中心回顾性观察研究,纳入989例疑似卒中成人脑MRI,评估排除不确定急性缺血性病灶(AIL)对深度学习工具诊断比值比的影响,并分析相关因素。排除不确定病例后诊断比值比从68升至278(四倍),模拟病例对照设计则从68升至431(六倍);MRI伪影、病灶较小、幕下位置及病灶较旧与不确定AIL独立相关。

要点

  • 排除不确定急性缺血性病灶病例可使深度学习诊断比值比高估约四倍。
  • MRI伪影、病灶较小、幕下位置和病灶较旧与不确定AIL独立相关。
  • 验证研究应纳入不确定病例并考虑上述因素以避免频谱偏差。

核心结论

  • 排除不确定急性缺血性病灶病例会导致深度学习诊断比值比四倍高估,MRI伪影、病灶较小、幕下位置和病灶较旧与不确定AIL相关,验证研究应予以考虑。

研究设计与样本

  • 单中心回顾性观察研究,纳入2020年1月至2022年4月疑似卒中成人脑MRI共989例,由放射科住院医师、神经放射学家及原放射科报告(多位神经放射学家)识别不确定AIL,评估商用深度学习工具,参考标准为读者分歧或低确定性分级。

诊断标准与关键数值

  • 确定AIL 374例(38%),不确定AIL 63例(6%),无AIL 552例(56%)。
  • 排除不确定病例后诊断比值比从68升至278(四倍增加)。
  • 模拟病例对照设计诊断比值比从68升至431(六倍增加,相比全疾病谱)。

临床应用与阅片要点

  • 原文未据此给出推荐。

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: To evaluate spectrum bias in stroke MRI analysis by excluding cases with uncertain acute ischemic lesions (AIL) and examining patient, imaging, and lesion factors associated with these cases.

MATERIALS AND METHODS: This single-center retrospective observational study included adults with brain MRIs for suspected stroke between January 2020 and April 2022. Diagnostic uncertain AIL were identified through reader disagreement or low certainty grading by a radiology resident, a neuroradiologist, and the original radiology report consisting of various neuroradiologists. A commercially available deep learning tool analyzing brain MRIs for AIL was evaluated to assess the impact of excluding uncertain cases on diagnostic odds ratios. Patient-related, MRI acquisition-related, and lesion-related factors were analyzed using the Wilcoxon rank sum test, χ2 test, and multiple logistic regression. The study was approved by the National Committee on Health Research Ethics.

RESULTS: In 989 patients (median age 73 (IQR: 59-80), 53% female), certain AIL were found in 374 (38%), uncertain AIL in 63 (6%), and no AIL in 552 (56%). Excluding uncertain cases led to a four-fold increase in the diagnostic odds ratio (from 68 to 278), while a simulated case-control design resulted in a six-fold increase compared to the full disease spectrum (from 68 to 431). Independent factors associated with uncertain AIL were MRI artifacts, smaller lesion size, older lesion age, and infratentorial location.

CONCLUSION: Excluding uncertain cases leads to a four-fold overestimation of the diagnostic odds ratio. MRI artifacts, smaller lesion size, infratentorial location, and older lesion age are associated with uncertain AIL and should be accounted for in validation studies.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Krag CH, Müller FC, Gandrup KL, et al. Impact of spectrum bias on deep learning-based stroke MRI analysis. Eur J Radiol. 2025. PMID: 40359732. doi:10.1016/j.ejrad.2025.112161

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。