文献速递神经肿瘤

机器学习:一种用于确定新诊断胶质瘤分级和IDH状态的有用影像学辅助工具

Machine learning: a useful radiological adjunct in determination of a newly diagnosed glioma's grade and IDH status.
PubMed 文献 · J Neurooncol · 2018-05-16

本研究旨在开发一种机器学习算法,辅助放射科医生在常规实践中诊断新发胶质瘤的WHO分级和IDH突变状态。研究先评估神经影像报告对WHO分级的准确性(II级96.49%,III级36.51%,IV级72.9%),再从同一诊断性脑扫描中提取五个MRI参数输入随机森林算法。机器学习在预测肿瘤分级方面达到高准确度(II/III级AUC=98%,II/IV级AUC=100%,III/IV级AUC=97%),并有助于区分IDH状态(AUC=88%)。

要点

  • 神经影像报告对WHO III级胶质瘤的诊断准确性较低(36.51%)。
  • 机器学习预测II/IV级胶质瘤的AUC达100%,敏感性和特异性均为1.0。
  • 机器学习区分IDH状态的AUC为88%,敏感性0.81,特异性0.77。

核心结论

  • 这些数据表明,机器学习能够仅凭常规MRI准确分类弥漫性胶质瘤的WHO分级和IDH状态,无需显著的图像处理,这可能有助于其作为临床实践中的诊断辅助工具。

研究设计与样本

  • 本研究开发了一种机器学习算法,旨在供放射科医生在常规实践中辅助诊断新发胶质瘤的WHO分级和IDH突变状态。
  • 研究从同一诊断性脑扫描中提取五个MRI参数,每位病例耗时不到两分钟,然后将这些数据输入随机森林算法。

主要发现

  • 神经影像报告对WHO分级的准确性为:II级96.49%(95%CI 0.88, 0.99);III级36.51%(95%CI 0.24, 0.50);IV级72.9%(95%CI 0.67, 0.78)。
  • 机器学习预测肿瘤分级的准确度高:II/III级AUC=98%,敏感性=0.82,特异性=0.94;II/IV级AUC=100%,敏感性=1.0,特异性=1.0;III/IV级AUC=97%,敏感性=0.83,特异性=0.97。
  • 机器学习还有助于区分IDH状态:AUC为88%,敏感性=0.81,特异性=0.77。

临床怎么用

  • 作者认为,机器学习能够仅凭常规MRI准确分类弥漫性胶质瘤的WHO分级和IDH状态,无需显著的图像处理,这可能有助于其作为临床实践中的诊断辅助工具。

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)。

原文

INTRODUCTION: Machine learning methods have been introduced as a computer aided diagnostic tool, with applications to glioma characterisation on MRI. Such an algorithmic approach may provide a useful adjunct for a rapid and accurate diagnosis of a glioma. The aim of this study is to devise a machine learning algorithm that may be used by radiologists in routine practice to aid diagnosis of both: WHO grade and IDH mutation status in de novo gliomas. METHODS: To evaluate the status quo, we interrogated the accuracy of neuroradiology reports in relation to WHO grade: grade II 96.49% (95% confidence intervals [CI] 0.88, 0.99); III 36.51% (95% CI 0.24, 0.50); IV 72.9% (95% CI 0.67, 0.78). We derived five MRI parameters from the same diagnostic brain scans, in under two minutes per case, and then supplied these data to a random forest algorithm. RESULTS: Machine learning resulted in a high level of accuracy in prediction of tumour grade: grade II/III; area under the receiver operating characteristic curve (AUC) = 98%, sensitivity = 0.82, specificity = 0.94; grade II/IV; AUC = 100%, sensitivity = 1.0, specificity = 1.0; grade III/IV; AUC = 97%, sensitivity = 0.83, specificity = 0.97. Furthermore, machine learning also facilitated the discrimination of IDH status: AUC of 88%, sensitivity = 0.81, specificity = 0.77. CONCLUSIONS: These data demonstrate the ability of machine learning to accurately classify diffuse gliomas by both WHO grade and IDH status from routine MRI alone-without significant image processing, which may facilitate usage as a diagnostic adjunct in clinical practice.

来源:J Neurooncol,查看原文。版权归原作者所有。

引用

  1. De Looze C, Beausang A, Cryan J, et al. Machine learning: a useful radiological adjunct in determination of a newly diagnosed glioma's grade and IDH status. J Neurooncol. 2018. PMID: 29770897. doi:10.1007/s11060-018-2895-4

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。