文献速递神经MR

基于自动化体积分析的数据驱动方法鉴别特发性正常压力脑积水和进行性核上性麻痹

Data-Driven differentiation of idiopathic Normal-Pressure hydrocephalus and progressive supranuclear palsy via automated volumetric analysis.
PubMed 文献 · Neuroradiology · 2025-11-08

研究纳入192例患者(132例特发性正常压力脑积水,60例进行性核上性麻痹),利用T1加权3D脑MRI进行自动化体积分析,提取脑干、体积、中脑/脑桥比值和DESH等特征。机器学习模型(尤其线性支持向量机)鉴别两种疾病的AUROC达0.98,体积分析优于其他特征亚组。

要点

  • 基于T1加权脑MRI的自动化体积分析可高精度鉴别特发性正常压力脑积水和进行性核上性麻痹,线性支持向量机AUROC为0.98。
  • 中脑体积、中脑/脑桥体积比、胼胝体角、外侧裂空虚比、顶点区拥挤比和Evans指数在两组间差异显著。
  • 体积分析亚组的鉴别效能优于脑干、中脑/脑桥比值和DESH亚组。

核心结论

  • 基于深度学习的自动化脑体积分析利用T1加权脑MRI在鉴别特发性正常压力脑积水和进行性核上性麻痹方面达到高诊断准确度(线性支持向量机AUROC=0.98)。

研究设计与样本

  • 研究纳入192例患者(132例特发性正常压力脑积水,60例进行性核上性麻痹),分析T1加权3D脑MRI,采用自动化组件测量采集和基于深度学习的自动化体积分析,并应用机器学习模型评估特征效果。

关键影像表现/征象

  • 中脑体积、中脑/脑桥体积比、胼胝体角、外侧裂空虚比、顶点区拥挤比和Evans指数在特发性正常压力脑积水与进行性核上性麻痹组间差异显著。
  • 影像特征分为脑干亚组、体积亚组、中脑/脑桥比值亚组(含中脑/脑桥面积比和体积比)和DESH亚组(含胼胝体角、外侧裂空虚比、顶点区拥挤比和Evans指数)。

诊断标准与关键数值

  • 线性支持向量机鉴别特发性正常压力脑积水与进行性核上性麻痹的AUROC为0.98。
  • 体积分析亚组的鉴别效能优于其他特征亚组。

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: This study aims to develop automated machine learning methods to differentiate idiopathic normal pressure hydrocephalus (iNPH) from progressive supranuclear palsy (PSP) using advanced imaging features and volumetric analysis.

METHODS: We analyzed T1-weighted 3D brain MRI scans of iNPH and PSP patients using automated component measurement acquisition and deep learning-based automated volumetric analysis. We grouped the MRI features as brainstem subgroup, volumetrics subgroup, midbrain to pons (MP) ratio subgroup (included the midbrain to pons area ratio and volume ratio), and disproportionately enlarged subarachnoid space hydrocephalus (DESH) subgroup (included the callosal angle, Sylvian fissure empty ratio, vertex region crowding ratio, and Evans' index). Key imaging features were quantified, and statistical comparisons were conducted to identify distinguishing characteristics. Machine learning models were applied to evaluate feature effectiveness and improve diagnostic classification accuracy.

RESULTS: This study analyzed 192 patients (132 iNPH, 60 PSP) and found significant differences in midbrain volume, midbrain to pons volume ratio, callosal angle, Sylvian fissure empty ratio, vertex region crowding ratio, and Evans' index. Machine learning models, particularly the linear Support Vector Machine (SVM), achieved high diagnostic accuracy (AUROC = 0.98) in distinguishing iNPH from PSP. Volumetric analysis outperformed other feature subgroups.

CONCLUSION: The deep learning-based automated brain volumetric analysis achieved high diagnostic accuracy in distinguishing iNPH from PSP using T1-weighted brain MR images.

来源:Neuroradiology,查看原文。版权归原作者所有。

引用

  1. Yun S, Song Y, Suh CH, et al. Data-Driven differentiation of idiopathic Normal-Pressure hydrocephalus and progressive supranuclear palsy via automated volumetric analysis. Neuroradiology. 2025. PMID: 41204957. doi:10.1007/s00234-025-03830-8

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。