0.5分钟深度学习脉络丛分割与认知及类淋巴功能
该回顾性研究纳入697例因认知障碍行脑MRI患者,开发基于3D T1WI的深度学习脉络丛体积自动分割方法。模型由三个2.5D U-Net集成,在20例中与手动分割、FreeSurfer对比验证,在574例分级人群中行临床验证。结果显示该方法分割速度远快于FreeSurfer,CPV/ICV随认知分期递增并与DTI-ALPS指数负相关。
要点
- 深度学习CPV分割约0.4分钟,远快于FreeSurfer的188分钟
- CPV/ICV从主观认知下降到AD逐渐升高,提示认知评估价值
- CPV/ICV与DTI-ALPS负相关,提示与类淋巴功能障碍相关
核心结论
- 超快深度学习方法可实现自动化脉络丛体积量化,为神经退行性疾病评估提供临床相关CPV/ICV测量值
研究设计与样本
- 回顾性研究,共纳入697例因认知障碍行脑MRI的患者
- 模型开发使用103例患者的3D T1WI,采用轴位、冠状位、矢状位三个2.5D U-Net集成
- 影像验证在20例患者中比较手动分割、FreeSurfer与所提方法
- 临床验证纳入574例患者,分为主观认知障碍、早期轻度认知障碍、晚期轻度认知障碍或阿尔茨海默病
- 使用ComBat协调处理减少扫描仪相关效应
诊断标准与关键数值
- 深度学习CPV测量与手动分割无显著差异,CPV为1.89 mL与1.84 mL,P=1.00
- 深度学习分割处理时间为0.4分钟,FreeSurfer为188.0分钟,P<0.001
- CPV/颅内体积(ICV)×10³从主观认知障碍的1.02逐步增至阿尔茨海默病的1.16,P=0.004
- 深度学习模型测得的CPV/ICV与DTI-ALPS指数呈负相关,ρ=-0.256,P<0.001
临床应用与阅片要点
- 在日常阅片中可借助该深度学习方法快速获得CPV/ICV,辅助认知障碍分级评估
- CPV/ICV升高需警惕认知障碍向晚期轻度认知障碍或阿尔茨海默病进展
- CPV/ICV降低但DTI-ALPS异常时,需结合类淋巴功能变化综合解读
局限性
- 回顾性研究设计,样本来源于因认知障碍行MRI的患者
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 AND PURPOSE: Choroid plexus volume (CPV) may reflect cognitive impairment and glymphatic dysfunction. However, its clinical use is limited by time-consuming segmentation. We developed an ultrafast deep learning method for automated CPV quantification using 3D T1-weighted images (T1WI).
MATERIALS AND METHODS: This retrospective study included 697 patients who underwent brain MRI for cognitive impairment. The model was developed using 3D T1WI from 103 patients as an ensemble of three 2.5D U-Nets in the axial, coronal, and sagittal planes. Imaging validation was performed for 20 patients by comparing manual segmentation, FreeSurfer, and the proposed method. Clinical validation included 574 patients classified as subjective cognitive impairment (SCI), early mild cognitive impairment (MCI), late MCI, or Alzheimer disease (AD). ComBat harmonization was applied to reduce scanner-related effects. Accuracy, processing time, group differences, and correlations with the diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index were assessed.
RESULTS: After ComBat harmonization, the deep learning-based model was markedly faster than FreeSurfer (0.4 vs. 188.0 minutes; P<0.001), and its CPV measurements showed no significant difference from manual segmentation (1.89 vs. 1.84 mL; P=1.00). CPV/intracranial volume (ICV)×10³ increased progressively across cognitive stages, from 1.02 in SCI to 1.16 in AD (P=0.004). CPV/ICV measured by the deep learning-based model was negatively correlated with the DTI-ALPS index (ρ=-0.256, P<0.001).
CONCLUSION: An ultrafast deep learning method enables automated CPV quantification and provides clinically relevant CPV/ICV measurements for neurodegenerative disease assessment.
引用
- Park, Jung, You, et al. Ultrafast (0.5-Minute) Deep Learning Based Choroid Plexus Segmentation: Links to Cognitive Impairment and Glymphatic Function. AJNR Am J Neuroradiol. 2026. PMID: 42674964. doi:10.3174/ajnr.A9614
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。